Self-evolving second brain with 35 AI skills, 10 agents, and people CRM. Closed-loop harness: a V-model verification lifecycle where the worker never grades its own homework. Plus paired anti-slop design skills for marketing and product UI. Works with Claude Code, Cursor, Kiro, Gemini CLI, Codex.
Python agent-loopagent-pluginsagent-skillsagenticai-agentsclaude-codeclosed-loopcursorgarry-tangbraingstackknowledge-managementloop-engineeringobsidianpeople-crmproductivitysecond-brainself-evolvingverification-harnessworker-agents
refactor: split five oversized skill bodies into bundled references/ (#35)
Huy Tieu622a5e5ea2af
diff --git a/.claude-plugin/plugin.json b/.claude-plugin/plugin.jsonindex 18e81ec..2e0c4bd 100644--- a/.claude-plugin/plugin.json+++ b/.claude-plugin/plugin.json@@ -1,6 +1,6 @@{"name": "cog-second-brain",- "version": "3.10.1",+ "version": "3.10.2","description": "Self-evolving second brain with 33 AI agent skills, 10 agents, and people CRM. Closed-loop harness release: a V-model verification lifecycle (spec to evidence, criterion-traced checkpoints), read-only verifier agents that observe artifacts instead of trusting worker summaries, risk lanes, multi-session ultragoals with a north-star acceptance gate, plus craft skills for writing, visual work, and a paired anti-slop design system for marketing and product UI. Inspired by Garry Tan's gstack specialist sessions, gbrain knowledge patterns, and dwarves-kit closed-loop execution. Works with Claude Code, Antigravity, Cursor, Kiro, Gemini CLI, Codex, and any markdown-reading agent.","author": {"name": "Huy Tieu",diff --git a/.claude/skills/knowledge-consolidation/SKILL.md b/.claude/skills/knowledge-consolidation/SKILL.mdindex 916737c..4180055 100644--- a/.claude/skills/knowledge-consolidation/SKILL.md+++ b/.claude/skills/knowledge-consolidation/SKILL.md@@ -139,608 +139,31 @@ Update and create knowledge base documents:#### Update Existing Frameworks-For each framework that needs updating:--```markdown-----type: "consolidated-knowledge"-domain: "[primary-domain]"-framework: "[framework-name]"-created: "[original-date]"-last_updated: "YYYY-MM-DD"-consolidation_id: "[consolidation-session-id]"-source_documents: [count]-status: "stable|working|emerging"-tags: ["#framework", "#consolidated", "#[topic]"]------# [Framework Name]--## Framework Overview-[Clear description of what this framework is and what it helps with]--**Status:** [Stable | Working | Emerging]-**Last Updated:** [Date]-**Source Insights:** [count] documents analyzed-------## Core Principles--### Principle 1: [Name]-**Statement:** [Clear, concise principle statement]--**Evidence:**-- [[braindump-YYYY-MM-DD]] - [supporting insight]-- [[daily-brief-YYYY-MM-DD]] - [supporting evidence]-- [[checkin-YYYY-MM-DD]] - [pattern observation]--**Evolution:** [How this principle has developed or been refined]--**Confidence:** [High|Medium|Low] - [reasoning]--### Principle 2: [Name]-[Same structure as Principle 1]--### Principle 3: [Name]-[Same structure as Principle 1]-------## Applications & Use Cases--### Use Case 1: [Scenario]-**When to Apply:** [Specific situation]--**How to Apply:**-1. [Step 1]-2. [Step 2]-3. [Step 3]--**Expected Outcomes:** [What to expect]--**Example:** [Real example from user's experience]--### Use Case 2: [Scenario]-[Same structure as Use Case 1]-------## Boundaries & Limitations--**This framework works when:**-- [Condition 1]-- [Condition 2]-- [Condition 3]--**This framework does NOT work when:**-- [Anti-condition 1]-- [Anti-condition 2]-- [Anti-condition 3]--**Common Pitfalls:**-- [Pitfall 1 to avoid]-- [Pitfall 2 to avoid]-------## Evolution & History--### [Date Range 1]: [Initial Development]-**What Emerged:** [How this framework first appeared]--**Catalysts:**-- [Event or insight that triggered initial thinking]--**Early Insights:**-- [[link]] - [early thought]-- [[link]] - [formative insight]--### [Date Range 2]: [Refinement Phase]-**What Changed:** [How framework evolved]--**New Evidence:**-- [[link]] - [supporting experience]-- [[link]] - [refining insight]--**Adjustments Made:**-- [Change 1]-- [Change 2]--### Current State: [Date]-**Current Understanding:** [Latest refined version]--**Recent Validation:**-- [[link]] - [recent application]-- [[link]] - [current evidence]-------## Related Frameworks--- [[framework-2]] - [How they relate]-- [[framework-3]] - [Connection or overlap]-- [[framework-4]] - [When to use which]-------## Future Development--**Questions for Deeper Exploration:**-- [Question 1 to investigate]-- [Question 2 needing more evidence]--**Potential Extensions:**-- [Area 1 for expansion]-- [Area 2 for integration]--**Watch For:**-- [Pattern 1 to monitor]-- [Signal 2 that might invalidate or refine]-------*Consolidated from [X] sources | Confidence: [High/Medium/Low] | Status: [Stable/Working/Emerging]*-```+For each framework that needs updating, use the consolidated-knowledge template in `references/templates.md`.Save to: `05-knowledge/consolidated/[framework-name]-framework.md`#### Create New Frameworks-For newly identified frameworks:--```markdown-----type: "consolidated-knowledge"-domain: "[primary-domain]"-framework: "[framework-name]"-created: "YYYY-MM-DD"-last_updated: "YYYY-MM-DD"-consolidation_id: "[consolidation-session-id]"-source_documents: [count]-status: "emerging"-tags: ["#framework", "#consolidated", "#new", "#[topic]"]------# [New Framework Name]--## Framework Discovery--**Identified:** [Date]-**Based On:** [X] insights from [timeframe]-**Domain:** [Primary domain with cross-domain applications]--**Discovery Context:**-[What pattern recognition revealed this framework]-------## Core Principles--[Same structure as framework updates above]-------[Continue with Applications, Boundaries, Evolution sections...]-```+For newly identified frameworks, use the new-framework template in `references/templates.md`.Save to: `05-knowledge/consolidated/[framework-name]-framework.md`#### Update Pattern Documentation-```markdown-----type: "pattern-analysis"-pattern: "[pattern-name]"-created: "YYYY-MM-DD"-domains: ["domain1", "domain2"]-frequency: "[high|medium|low]"-tags: ["#pattern", "#analysis"]------# Pattern: [Pattern Name]--## Pattern Description-[Clear description of the recurring pattern]--**Frequency:** Appeared in [X] documents over [timeframe]--**Domains:** [Which domains this pattern appears in]--**Significance:** [Why this pattern matters]-------## Occurrences--### [Date 1] - [[source-document-1]]-**Context:** [What was happening]--**Manifestation:** [How pattern appeared]--**Outcome:** [What resulted]--### [Date 2] - [[source-document-2]]-[Same structure]--### [Date 3] - [[source-document-3]]-[Same structure]-------## Analysis--**What Triggers This Pattern:**-- [Trigger 1]-- [Trigger 2]-- [Trigger 3]--**What Follows This Pattern:**-- [Consequence 1]-- [Consequence 2]--**Cross-Domain Implications:**-[How this pattern affects different areas]--**Potential Actions:**-- [Action to amplify if positive]-- [Action to mitigate if negative]-- [Action to understand better]-------## Evolution Over Time--[How this pattern has changed or stayed consistent]-------*Pattern identified through consolidation of [X] sources*-```+Document the pattern using the pattern template in `references/templates.md`.Save to: `05-knowledge/patterns/pattern-[name].md`#### Create Timeline Entries-```markdown-----type: "timeline-entry"-topic: "[major-theme-or-shift]"-date_range: "YYYY-MM-DD to YYYY-MM-DD"-created: "YYYY-MM-DD"-tags: ["#timeline", "#evolution", "#thinking"]------# Thinking Evolution: [Major Theme/Shift]--## Timeline Period-**From:** [Start Date]-**To:** [End Date]-**Duration:** [X weeks/months]-------## What Changed--**Initial State:**-[How thinking/approach started]--**End State:**-[Where thinking/approach ended up]--**Key Shift:**-[The fundamental change that occurred]-------## Catalysts & Triggers--### [Date] - [Trigger Event 1]-**Source:** [[link-to-document]]--**What Happened:** [Description]--**Impact:** [How this triggered change]--### [Date] - [Trigger Event 2]-[Same structure]-------## Evidence Trail--### Early Thinking: [Date Range]-- [[YYYY-MM-DD]] - [Initial thoughts]-- [[YYYY-MM-DD]] - [Early explorations]--### Intermediate Development: [Date Range]-- [[YYYY-MM-DD]] - [Evolving understanding]-- [[YYYY-MM-DD]] - [Testing and refinement]--### Current Understanding: [Date Range]-- [[YYYY-MM-DD]] - [Mature thinking]-- [[YYYY-MM-DD]] - [Latest application]-------## Impact of This Evolution--**On Decisions:**-[How this shift affects decision-making]--**On Strategies:**-[How this shift affects strategic approach]--**On Frameworks:**-[Which frameworks were created or updated]--**On Actions:**-[What changed in behavior or practice]-------## Lessons Learned--**What This Evolution Teaches:**-- [Learning 1]-- [Learning 2]-- [Learning 3]--**Future Implications:**-[What this suggests for future development]-------*Timeline constructed from [X] source documents spanning [timeframe]*-```+Build the timeline entry using the thinking-evolution template in `references/templates.md`.Save to: `05-knowledge/timeline/[topic]-evolution-YYYY-MM.md`### 5. Generate Consolidation Report-Create master consolidation document:--```markdown-----type: "knowledge-consolidation"-domain: "integrated"-date: "YYYY-MM-DD"-consolidation_period: "YYYY-MM-DD to YYYY-MM-DD"-created: "YYYY-MM-DD HH:MM"-sources_analyzed: [number]-frameworks_updated: ["framework1", "framework2"]-frameworks_created: ["new-framework1"]-patterns_identified: [number]-tags: ["#consolidation", "#knowledge", "#frameworks"]------# Knowledge Consolidation - [Date]--## Executive Summary--**Period Analyzed:** [Start date] to [End date]--**Documents Processed:**-- [X] braindumps-- [X] daily briefs-- [X] weekly check-ins-- [X] project documents--**Major Outcomes:**-- **Frameworks Updated:** [count] - [list]-- **New Frameworks Created:** [count] - [list]-- **Patterns Identified:** [count]-- **Timeline Entries:** [count]--**Key Insights Synthesized:**-1. [Major insight 1]-2. [Major insight 2]-3. [Major insight 3]-------## Processing Statistics--- **Total documents analyzed:** [number]-- **Date range:** [start] to [end]-- **Domains covered:** [list]-- **New patterns identified:** [number]-- **Frameworks updated:** [number]-- **New frameworks created:** [number]-- **Timeline entries added:** [number]-- **Archive actions taken:** [number]-------## Major Themes This Period--### Theme 1: [Name]-**Frequency:** Appeared in [X] documents--**Evolution:** [How thinking evolved]--**Key Insights:**-- [[source]] - [insight 1]-- [[source]] - [insight 2]-- [[source]] - [insight 3]--**Framework Implications:**-[How this theme affected or created frameworks]--**Status:** [Stable understanding | Still exploring | Needs more evidence]--### Theme 2: [Name]-[Same structure as Theme 1]-------## Frameworks Updated--### Framework 1: [Name]-**Location:** [[05-knowledge/consolidated/[filename]]]--**What Changed:**-- [Addition/modification 1]-- [Addition/modification 2]--**New Evidence Added:**-- [[source]] - [insight]-- [[source]] - [insight]--**Confidence Change:** [Before] → [After]--**New Applications:**-- [Use case 1]-- [Use case 2]--### Framework 2: [Name]-[Same structure]-------## New Frameworks Created--### New Framework: [Name]-**Location:** [[05-knowledge/consolidated/[filename]]]--**Created:** Based on [X] insights from [timeframe]--**Core Principles:**-1. [Principle 1]-2. [Principle 2]-3. [Principle 3]--**Primary Use Cases:**-- [Use case 1]-- [Use case 2]--**Status:** Emerging (needs more evidence and validation)--**Future Development:**-[What's needed to mature this framework]-------## Patterns Identified--### Pattern 1: [Name]-**Frequency:** [High|Medium|Low]--**Domains:** [Which domains]--**Description:** [What the pattern is]--**Implications:** [Why it matters]--**Documentation:** [[05-knowledge/patterns/[filename]]]--### Pattern 2: [Name]-[Same structure]-------## Thinking Evolution--### Major Shift: [Topic]-**Timeline:** [Date range]--**What Changed:** [Description]--**Catalysts:**-- [Event 1]-- [Event 2]--**Impact:**-[How this shift affects frameworks, decisions, actions]--**Documentation:** [[05-knowledge/timeline/[filename]]]-------## Cross-Cutting Insights--**Connections Across Domains:**-- [Cross-domain insight 1]-- [Cross-domain insight 2]-- [Cross-domain insight 3]--**Contradictions Identified:**-- [Contradiction 1] - [Resolution approach]-- [Contradiction 2] - [Still unresolved]--**Strategic Implications:**-[Higher-level observations about trajectory and direction]-------## Knowledge Base Maintenance--### Updates Made-- ✅ Updated framework: [name]-- ✅ Created new framework: [name]-- ✅ Documented pattern: [name]-- ✅ Added timeline entry: [topic]-- ✅ Archived outdated insights: [list]--### Archive Actions-**Braindumps Processed:**-- Updated metadata from `status: "captured"` to `status: "consolidated"`-- Added consolidation references: `consolidated_in: "[[consolidation-YYYY-MM-DD]]"`--**Superseded Content:**-- Archived: [list of old framework versions or outdated insights]-- Location: `00-inbox/archive/`-------## Future Consolidation Needs--### Ready for Framework Creation-- [ ] [Area 1] - Sufficient evidence gathered - Target: [date]-- [ ] [Area 2] - Pattern established - Target: [date]--### Needs Deeper Analysis-- [ ] [Area 3] - Contradictions to resolve - Target: [date]-- [ ] [Area 4] - Emerging but not yet clear - Target: [date]--### Monitoring Required-- [ ] [Pattern 1] - Watch for additional occurrences-- [ ] [Theme 2] - Track evolution over next [period]-------## Quality Assessment--**Completeness:** [All relevant insights processed?]--**Coherence:** [Frameworks logically consistent?]--**Traceability:** [Clear links to source material?]--**Actionability:** [Frameworks applicable to decisions?]--**Evolution Documented:** [Thinking progression captured?]-------## Next Steps--**Immediate Actions:**-- [Action 1 based on consolidation insights]-- [Action 2 to apply new frameworks]--**Future Consolidation:**-- **Next Consolidation:** [Suggested date]-- **Focus Areas:** [What to emphasize next time]--**Framework Applications:**-- [Decision 1 that could benefit from framework]-- [Situation 2 to apply framework to]-------*Consolidation completed: [Date] | Processed [X] documents | Created/updated [X] frameworks*-```+Create the master consolidation document using the report template in `references/templates.md`.Save to: `05-knowledge/consolidated/consolidation-YYYY-MM-DD.md`diff --git a/.claude/skills/knowledge-consolidation/references/templates.md b/.claude/skills/knowledge-consolidation/references/templates.mdnew file mode 100644index 0000000..cf40b79--- /dev/null+++ b/.claude/skills/knowledge-consolidation/references/templates.md@@ -0,0 +1,594 @@+# Knowledge Consolidation Templates++Templates referenced from `SKILL.md` for the knowledge-consolidation workflow. Each section below is used verbatim at its point of use in the skill.++## Update Existing Frameworks++```markdown+---+type: "consolidated-knowledge"+domain: "[primary-domain]"+framework: "[framework-name]"+created: "[original-date]"+last_updated: "YYYY-MM-DD"+consolidation_id: "[consolidation-session-id]"+source_documents: [count]+status: "stable|working|emerging"+tags: ["#framework", "#consolidated", "#[topic]"]+---++# [Framework Name]++## Framework Overview+[Clear description of what this framework is and what it helps with]++**Status:** [Stable | Working | Emerging]+**Last Updated:** [Date]+**Source Insights:** [count] documents analyzed++---++## Core Principles++### Principle 1: [Name]+**Statement:** [Clear, concise principle statement]++**Evidence:**+- [[braindump-YYYY-MM-DD]] - [supporting insight]+- [[daily-brief-YYYY-MM-DD]] - [supporting evidence]+- [[checkin-YYYY-MM-DD]] - [pattern observation]++**Evolution:** [How this principle has developed or been refined]++**Confidence:** [High|Medium|Low] - [reasoning]++### Principle 2: [Name]+[Same structure as Principle 1]++### Principle 3: [Name]+[Same structure as Principle 1]++---++## Applications & Use Cases++### Use Case 1: [Scenario]+**When to Apply:** [Specific situation]++**How to Apply:**+1. [Step 1]+2. [Step 2]+3. [Step 3]++**Expected Outcomes:** [What to expect]++**Example:** [Real example from user's experience]++### Use Case 2: [Scenario]+[Same structure as Use Case 1]++---++## Boundaries & Limitations++**This framework works when:**+- [Condition 1]+- [Condition 2]+- [Condition 3]++**This framework does NOT work when:**+- [Anti-condition 1]+- [Anti-condition 2]+- [Anti-condition 3]++**Common Pitfalls:**+- [Pitfall 1 to avoid]+- [Pitfall 2 to avoid]++---++## Evolution & History++### [Date Range 1]: [Initial Development]+**What Emerged:** [How this framework first appeared]++**Catalysts:**+- [Event or insight that triggered initial thinking]++**Early Insights:**+- [[link]] - [early thought]+- [[link]] - [formative insight]++### [Date Range 2]: [Refinement Phase]+**What Changed:** [How framework evolved]++**New Evidence:**+- [[link]] - [supporting experience]+- [[link]] - [refining insight]++**Adjustments Made:**+- [Change 1]+- [Change 2]++### Current State: [Date]+**Current Understanding:** [Latest refined version]++**Recent Validation:**+- [[link]] - [recent application]+- [[link]] - [current evidence]++---++## Related Frameworks++- [[framework-2]] - [How they relate]+- [[framework-3]] - [Connection or overlap]+- [[framework-4]] - [When to use which]++---++## Future Development++**Questions for Deeper Exploration:**+- [Question 1 to investigate]+- [Question 2 needing more evidence]++**Potential Extensions:**+- [Area 1 for expansion]+- [Area 2 for integration]++**Watch For:**+- [Pattern 1 to monitor]+- [Signal 2 that might invalidate or refine]++---++*Consolidated from [X] sources | Confidence: [High/Medium/Low] | Status: [Stable/Working/Emerging]*+```++## Create New Frameworks++```markdown+---+type: "consolidated-knowledge"+domain: "[primary-domain]"+framework: "[framework-name]"+created: "YYYY-MM-DD"+last_updated: "YYYY-MM-DD"+consolidation_id: "[consolidation-session-id]"+source_documents: [count]+status: "emerging"+tags: ["#framework", "#consolidated", "#new", "#[topic]"]+---++# [New Framework Name]++## Framework Discovery++**Identified:** [Date]+**Based On:** [X] insights from [timeframe]+**Domain:** [Primary domain with cross-domain applications]++**Discovery Context:**+[What pattern recognition revealed this framework]++---++## Core Principles++[Same structure as framework updates above]++---++[Continue with Applications, Boundaries, Evolution sections...]+```++## Update Pattern Documentation++```markdown+---+type: "pattern-analysis"+pattern: "[pattern-name]"+created: "YYYY-MM-DD"+domains: ["domain1", "domain2"]+frequency: "[high|medium|low]"+tags: ["#pattern", "#analysis"]+---++# Pattern: [Pattern Name]++## Pattern Description+[Clear description of the recurring pattern]++**Frequency:** Appeared in [X] documents over [timeframe]++**Domains:** [Which domains this pattern appears in]++**Significance:** [Why this pattern matters]++---++## Occurrences++### [Date 1] - [[source-document-1]]+**Context:** [What was happening]++**Manifestation:** [How pattern appeared]++**Outcome:** [What resulted]++### [Date 2] - [[source-document-2]]+[Same structure]++### [Date 3] - [[source-document-3]]+[Same structure]++---++## Analysis++**What Triggers This Pattern:**+- [Trigger 1]+- [Trigger 2]+- [Trigger 3]++**What Follows This Pattern:**+- [Consequence 1]+- [Consequence 2]++**Cross-Domain Implications:**+[How this pattern affects different areas]++**Potential Actions:**+- [Action to amplify if positive]+- [Action to mitigate if negative]+- [Action to understand better]++---++## Evolution Over Time++[How this pattern has changed or stayed consistent]++---++*Pattern identified through consolidation of [X] sources*+```++## Create Timeline Entries++```markdown+---+type: "timeline-entry"+topic: "[major-theme-or-shift]"+date_range: "YYYY-MM-DD to YYYY-MM-DD"+created: "YYYY-MM-DD"+tags: ["#timeline", "#evolution", "#thinking"]+---++# Thinking Evolution: [Major Theme/Shift]++## Timeline Period+**From:** [Start Date]+**To:** [End Date]+**Duration:** [X weeks/months]++---++## What Changed++**Initial State:**+[How thinking/approach started]++**End State:**+[Where thinking/approach ended up]++**Key Shift:**+[The fundamental change that occurred]++---++## Catalysts & Triggers++### [Date] - [Trigger Event 1]+**Source:** [[link-to-document]]++**What Happened:** [Description]++**Impact:** [How this triggered change]++### [Date] - [Trigger Event 2]+[Same structure]++---++## Evidence Trail++### Early Thinking: [Date Range]+- [[YYYY-MM-DD]] - [Initial thoughts]+- [[YYYY-MM-DD]] - [Early explorations]++### Intermediate Development: [Date Range]+- [[YYYY-MM-DD]] - [Evolving understanding]+- [[YYYY-MM-DD]] - [Testing and refinement]++### Current Understanding: [Date Range]+- [[YYYY-MM-DD]] - [Mature thinking]+- [[YYYY-MM-DD]] - [Latest application]++---++## Impact of This Evolution++**On Decisions:**+[How this shift affects decision-making]++**On Strategies:**+[How this shift affects strategic approach]++**On Frameworks:**+[Which frameworks were created or updated]++**On Actions:**+[What changed in behavior or practice]++---++## Lessons Learned++**What This Evolution Teaches:**+- [Learning 1]+- [Learning 2]+- [Learning 3]++**Future Implications:**+[What this suggests for future development]++---++*Timeline constructed from [X] source documents spanning [timeframe]*+```++## Generate Consolidation Report++```markdown+---+type: "knowledge-consolidation"+domain: "integrated"+date: "YYYY-MM-DD"+consolidation_period: "YYYY-MM-DD to YYYY-MM-DD"+created: "YYYY-MM-DD HH:MM"+sources_analyzed: [number]+frameworks_updated: ["framework1", "framework2"]+frameworks_created: ["new-framework1"]+patterns_identified: [number]+tags: ["#consolidation", "#knowledge", "#frameworks"]+---++# Knowledge Consolidation - [Date]++## Executive Summary++**Period Analyzed:** [Start date] to [End date]++**Documents Processed:**+- [X] braindumps+- [X] daily briefs+- [X] weekly check-ins+- [X] project documents++**Major Outcomes:**+- **Frameworks Updated:** [count] - [list]+- **New Frameworks Created:** [count] - [list]+- **Patterns Identified:** [count]+- **Timeline Entries:** [count]++**Key Insights Synthesized:**+1. [Major insight 1]+2. [Major insight 2]+3. [Major insight 3]++---++## Processing Statistics++- **Total documents analyzed:** [number]+- **Date range:** [start] to [end]+- **Domains covered:** [list]+- **New patterns identified:** [number]+- **Frameworks updated:** [number]+- **New frameworks created:** [number]+- **Timeline entries added:** [number]+- **Archive actions taken:** [number]++---++## Major Themes This Period++### Theme 1: [Name]+**Frequency:** Appeared in [X] documents++**Evolution:** [How thinking evolved]++**Key Insights:**+- [[source]] - [insight 1]+- [[source]] - [insight 2]+- [[source]] - [insight 3]++**Framework Implications:**+[How this theme affected or created frameworks]++**Status:** [Stable understanding | Still exploring | Needs more evidence]++### Theme 2: [Name]+[Same structure as Theme 1]++---++## Frameworks Updated++### Framework 1: [Name]+**Location:** [[05-knowledge/consolidated/[filename]]]++**What Changed:**+- [Addition/modification 1]+- [Addition/modification 2]++**New Evidence Added:**+- [[source]] - [insight]+- [[source]] - [insight]++**Confidence Change:** [Before] → [After]++**New Applications:**+- [Use case 1]+- [Use case 2]++### Framework 2: [Name]+[Same structure]++---++## New Frameworks Created++### New Framework: [Name]+**Location:** [[05-knowledge/consolidated/[filename]]]++**Created:** Based on [X] insights from [timeframe]++**Core Principles:**+1. [Principle 1]+2. [Principle 2]+3. [Principle 3]++**Primary Use Cases:**+- [Use case 1]+- [Use case 2]++**Status:** Emerging (needs more evidence and validation)++**Future Development:**+[What's needed to mature this framework]++---++## Patterns Identified++### Pattern 1: [Name]+**Frequency:** [High|Medium|Low]++**Domains:** [Which domains]++**Description:** [What the pattern is]++**Implications:** [Why it matters]++**Documentation:** [[05-knowledge/patterns/[filename]]]++### Pattern 2: [Name]+[Same structure]++---++## Thinking Evolution++### Major Shift: [Topic]+**Timeline:** [Date range]++**What Changed:** [Description]++**Catalysts:**+- [Event 1]+- [Event 2]++**Impact:**+[How this shift affects frameworks, decisions, actions]++**Documentation:** [[05-knowledge/timeline/[filename]]]++---++## Cross-Cutting Insights++**Connections Across Domains:**+- [Cross-domain insight 1]+- [Cross-domain insight 2]+- [Cross-domain insight 3]++**Contradictions Identified:**+- [Contradiction 1] - [Resolution approach]+- [Contradiction 2] - [Still unresolved]++**Strategic Implications:**+[Higher-level observations about trajectory and direction]++---++## Knowledge Base Maintenance++### Updates Made+- ✅ Updated framework: [name]+- ✅ Created new framework: [name]+- ✅ Documented pattern: [name]+- ✅ Added timeline entry: [topic]+- ✅ Archived outdated insights: [list]++### Archive Actions+**Braindumps Processed:**+- Updated metadata from `status: "captured"` to `status: "consolidated"`+- Added consolidation references: `consolidated_in: "[[consolidation-YYYY-MM-DD]]"`++**Superseded Content:**+- Archived: [list of old framework versions or outdated insights]+- Location: `00-inbox/archive/`++---++## Future Consolidation Needs++### Ready for Framework Creation+- [ ] [Area 1] - Sufficient evidence gathered - Target: [date]+- [ ] [Area 2] - Pattern established - Target: [date]++### Needs Deeper Analysis+- [ ] [Area 3] - Contradictions to resolve - Target: [date]+- [ ] [Area 4] - Emerging but not yet clear - Target: [date]++### Monitoring Required+- [ ] [Pattern 1] - Watch for additional occurrences+- [ ] [Theme 2] - Track evolution over next [period]++---++## Quality Assessment++**Completeness:** [All relevant insights processed?]++**Coherence:** [Frameworks logically consistent?]++**Traceability:** [Clear links to source material?]++**Actionability:** [Frameworks applicable to decisions?]++**Evolution Documented:** [Thinking progression captured?]++---++## Next Steps++**Immediate Actions:**+- [Action 1 based on consolidation insights]+- [Action 2 to apply new frameworks]++**Future Consolidation:**+- **Next Consolidation:** [Suggested date]+- **Focus Areas:** [What to emphasize next time]++**Framework Applications:**+- [Decision 1 that could benefit from framework]+- [Situation 2 to apply framework to]++---++*Consolidation completed: [Date] | Processed [X] documents | Created/updated [X] frameworks*+```diff --git a/.claude/skills/onboarding/SKILL.md b/.claude/skills/onboarding/SKILL.mdindex 5803157..7788548 100644--- a/.claude/skills/onboarding/SKILL.md+++ b/.claude/skills/onboarding/SKILL.md@@ -177,145 +177,15 @@ After role pack matching, set up the user's integration preferences:### 6. Generate Profile Documents-Create the following markdown files:+Create the four profile documents using the templates in `references/profile-templates.md`.#### `00-inbox/MY-PROFILE.md`-```markdown-----type: profile-created: YYYY-MM-DD-onboarding_completed: true-role_pack: [matched role_id or "custom"]-agent_mode: [solo or team, based on role pack suggestion]-tags: ["#profile", "#config", "#cog"]------# My COG Profile--## About Me-- **Name**: [Name]-- **Role**: [Job/role/main activity]-- **Role Pack**: [Display name from matched role pack, or "Custom" if no match]-- **Profile Created**: [Date]--## Settings-- **Agent Mode**: [solo/team] *(solo = handle everything directly; team = delegate to specialist sub-agents for deeper results)*--## Active Projects-[If they mentioned projects:]-- [[04-projects/[slug]/PROJECT-OVERVIEW|Project Name 1]]-- [[04-projects/[slug]/PROJECT-OVERVIEW|Project Name 2]]--[If no projects:]-*No active projects yet. Add them anytime by editing this file or running onboarding again.*--## Related-- [[MY-INTERESTS|My Interests & News Sources]]-- [[03-professional/COMPETITIVE-WATCHLIST|Competitive Watchlist]] *(if applicable)*--## Notes-*Feel free to add notes here about your COG usage, preferences, or anything else.*-------*Edit this file anytime to update your profile. COG reads it when you use skills.*-```#### `00-inbox/MY-INTERESTS.md`-```markdown-----type: interests-created: YYYY-MM-DD-tags: ["#interests", "#daily-brief", "#config"]------# My Interests & News Sources--*These topics guide my daily intelligence briefings.*--## Topics I'm Interested In-- [Topic 1]-- [Topic 2]-- [Topic 3]-- [Topic 4]-- [Topic 5]--## Preferred News Sources-[If sources were mentioned:]-*Where I like to get information:*-- [Source 1]-- [Source 2]-- [Source 3]--[If no sources mentioned:]-*No specific sources set. COG will search broadly for your topics. Add preferred sources here anytime.*--## Notes-*Add any additional context about your interests here.*-------*Update this file anytime as your interests evolve. Just edit and save—COG will pick up the changes.*-```#### `03-professional/COMPETITIVE-WATCHLIST.md` (only if they mentioned companies/people to track)-```markdown-----type: competitive-intelligence-created: YYYY-MM-DD-tags: ["#competitive", "#intelligence", "#tracking"]------# Competitive Watchlist--*Companies, people, or organizations I'm keeping an eye on.*--## Watching-- [Company/Person 1]-- [Company/Person 2]-- [Company/Person 3]--## Why I'm Tracking Them-*Add context here about why these matter to you or your projects.*-------*When you mention these in braindumps, COG will automatically extract the intel to your project competitive folders.*-```#### For Each Project: `04-projects/[project-slug]/PROJECT-OVERVIEW.md`-```markdown-----type: project-overview-project: [project-name]-slug: [project-slug]-created: YYYY-MM-DD-status: active-tags: ["#project", "#overview"]------# [Project Name]--## What is this project?-[Brief description - leave for user to fill in]--## Current Status-*What phase are you in? What's happening now?*--## Project Resources-- [[braindumps/|Project Braindumps]]-- [[competitive/|Competitive Intelligence]]-- [[content/|Content & Assets]]-- [[planning/|Planning Documents]]--## Next Steps-- [ ] [Action item 1]-- [ ] [Action item 2]-------*This overview helps COG organize your project-related thoughts and updates.*-```### 7. Create Directory StructureBased on configuration, create personalized structure:@@ -359,126 +229,7 @@ Based on configuration, create personalized structure:Generate: `00-inbox/WELCOME-TO-COG.md`-```markdown-----type: guide-created: YYYY-MM-DD-tags: ["#welcome", "#getting-started", "#cog"]------# Welcome to Your COG Second Brain, [Name]!--Your COG is now personalized and ready to use. Here's how to get started:--## Your Profile Documents--I've created these documents to store your preferences:--- **[[MY-PROFILE]]** - Your basic info, role pack, and workflow preferences-- **[[MY-INTERESTS]]** - Topics for your daily briefs-- **[[MY-INTEGRATIONS]]** - Your active and disabled integrations-- **[[03-professional/COMPETITIVE-WATCHLIST]]** - Companies you're tracking *(if applicable)*--**You can edit these files anytime.** COG reads them when you use skills, so your changes take effect immediately.--## Skills for Your Role--[If role pack was matched:]-As a **[Role Display Name]**, these skills are ordered by relevance for you:--[List skills from role pack in order, with brief "why it matters" from the role pack. Format as:]-1. **[skill-name]** — [Role-specific explanation]-2. **[skill-name]** — [Role-specific explanation]-[...continue for all recommended skills]--[If no role pack match:]-Here are COG's core skills available to everyone:--1. **daily-brief** — Personalized news intelligence-2. **braindump** — Capture and classify thoughts-3. **weekly-checkin** — Weekly pattern analysis-4. **knowledge-consolidation** — Build frameworks from scattered notes-5. **url-dump** — Save URLs with auto-extracted insights-6. **update-cog** — Keep COG framework current--## Your Integrations--[If integrations were configured:]-**Active**: [List active integrations]-**Disabled**: [List disabled integrations]--You can change these anytime by editing [[MY-INTEGRATIONS]].--[If no integrations configured:]-No integrations configured yet. COG works great standalone — add integrations anytime by editing `00-inbox/MY-INTEGRATIONS.md`.--## Quick Start--### 1. Daily Morning Routine-Invoke the daily-brief skill to get your personalized intelligence briefing covering:-[List their selected interest areas]--### 2. Capture Your Thoughts-Use the braindump skill to quickly capture ideas, insights, and thoughts. Your braindumps will automatically be categorized into:-[List their focus domains]--Choose from your active projects:-[List their projects with links]--### 3. Weekly Reflection-Every week, use the weekly-checkin skill to review your week's insights and patterns.--## Your Active Projects--[If they have projects]-You're tracking these projects:-- [[04-projects/[slug]/PROJECT-OVERVIEW|Project 1]]-- [[04-projects/[slug]/PROJECT-OVERVIEW|Project 2]]--When you use the braindump skill, select the project to automatically file your thoughts in the right place.--## How COG Uses Your Profile--**Daily Briefs**: Uses [[MY-INTERESTS]] to curate relevant news-**Braindumps**: Offers your projects from [[MY-PROFILE]] as options-**Competitive Intel**: Auto-extracts mentions of companies in [[COMPETITIVE-WATCHLIST]]-**Weekly Check-ins**: Reviews progress across your domains--## Next Steps--1. **Try your first braindump**: Use the braindump skill and start writing-2. **Get your daily brief**: Invoke the daily-brief skill to see curated intelligence-3. **Explore your vault**: All your files are organized in the sidebar-4. **Edit your profile**: Open [[MY-PROFILE]] and customize anytime--## Keeping COG Updated--COG separates your content from framework files. When new versions are released:-- Run `/update-cog` to check for and apply updates-- Or use the shell script: `./cog-update.sh --check`-- Your braindumps, profiles, and notes are **never** touched by updates--Check your current version: `cat COG-VERSION`--## Tips for Success--- **Don't overthink it**: Just dump your thoughts, COG will help organize-- **Be consistent**: Daily briefs and braindumps work best as habits-- **Review weekly**: Use the weekly-checkin skill to see patterns emerge-- **Evolve your setup**: Edit your profile files anytime or run onboarding again to add projects-- **Stay updated**: Run `/update-cog` periodically to get new skills and improvements--## Getting Help--- Check `SETUP.md` for detailed guides-- Visit the GitHub repo for documentation--**Your second brain is learning about you. Let's begin!**-------*You can archive or delete this welcome guide once you're comfortable with COG.*-```+Generate it from the template in `references/welcome-guide.md`.### 9. Wrap-Up (No Menu!)After setup, summarize what was created and suggest a natural next action:diff --git a/.claude/skills/onboarding/references/profile-templates.md b/.claude/skills/onboarding/references/profile-templates.mdnew file mode 100644index 0000000..dee6664--- /dev/null+++ b/.claude/skills/onboarding/references/profile-templates.md@@ -0,0 +1,145 @@+# Profile document templates++Verbatim markdown templates for the four documents created in onboarding Step 6 (Generate Profile Documents). Fill in the bracketed placeholders when generating each file.++## `00-inbox/MY-PROFILE.md`++```markdown+---+type: profile+created: YYYY-MM-DD+onboarding_completed: true+role_pack: [matched role_id or "custom"]+agent_mode: [solo or team, based on role pack suggestion]+tags: ["#profile", "#config", "#cog"]+---++# My COG Profile++## About Me+- **Name**: [Name]+- **Role**: [Job/role/main activity]+- **Role Pack**: [Display name from matched role pack, or "Custom" if no match]+- **Profile Created**: [Date]++## Settings+- **Agent Mode**: [solo/team] *(solo = handle everything directly; team = delegate to specialist sub-agents for deeper results)*++## Active Projects+[If they mentioned projects:]+- [[04-projects/[slug]/PROJECT-OVERVIEW|Project Name 1]]+- [[04-projects/[slug]/PROJECT-OVERVIEW|Project Name 2]]++[If no projects:]+*No active projects yet. Add them anytime by editing this file or running onboarding again.*++## Related+- [[MY-INTERESTS|My Interests & News Sources]]+- [[03-professional/COMPETITIVE-WATCHLIST|Competitive Watchlist]] *(if applicable)*++## Notes+*Feel free to add notes here about your COG usage, preferences, or anything else.*++---++*Edit this file anytime to update your profile. COG reads it when you use skills.*+```++## `00-inbox/MY-INTERESTS.md`++```markdown+---+type: interests+created: YYYY-MM-DD+tags: ["#interests", "#daily-brief", "#config"]+---++# My Interests & News Sources++*These topics guide my daily intelligence briefings.*++## Topics I'm Interested In+- [Topic 1]+- [Topic 2]+- [Topic 3]+- [Topic 4]+- [Topic 5]++## Preferred News Sources+[If sources were mentioned:]+*Where I like to get information:*+- [Source 1]+- [Source 2]+- [Source 3]++[If no sources mentioned:]+*No specific sources set. COG will search broadly for your topics. Add preferred sources here anytime.*++## Notes+*Add any additional context about your interests here.*++---++*Update this file anytime as your interests evolve. Just edit and save—COG will pick up the changes.*+```++## `03-professional/COMPETITIVE-WATCHLIST.md` (only if they mentioned companies/people to track)++```markdown+---+type: competitive-intelligence+created: YYYY-MM-DD+tags: ["#competitive", "#intelligence", "#tracking"]+---++# Competitive Watchlist++*Companies, people, or organizations I'm keeping an eye on.*++## Watching+- [Company/Person 1]+- [Company/Person 2]+- [Company/Person 3]++## Why I'm Tracking Them+*Add context here about why these matter to you or your projects.*++---++*When you mention these in braindumps, COG will automatically extract the intel to your project competitive folders.*+```++## For Each Project: `04-projects/[project-slug]/PROJECT-OVERVIEW.md`++```markdown+---+type: project-overview+project: [project-name]+slug: [project-slug]+created: YYYY-MM-DD+status: active+tags: ["#project", "#overview"]+---++# [Project Name]++## What is this project?+[Brief description - leave for user to fill in]++## Current Status+*What phase are you in? What's happening now?*++## Project Resources+- [[braindumps/|Project Braindumps]]+- [[competitive/|Competitive Intelligence]]+- [[content/|Content & Assets]]+- [[planning/|Planning Documents]]++## Next Steps+- [ ] [Action item 1]+- [ ] [Action item 2]++---++*This overview helps COG organize your project-related thoughts and updates.*+```diff --git a/.claude/skills/onboarding/references/welcome-guide.md b/.claude/skills/onboarding/references/welcome-guide.mdnew file mode 100644index 0000000..278e9b6--- /dev/null+++ b/.claude/skills/onboarding/references/welcome-guide.md@@ -0,0 +1,124 @@+# Welcome guide template++Verbatim markdown template for `00-inbox/WELCOME-TO-COG.md`, generated in onboarding Step 8 (Create Welcome Guide).++```markdown+---+type: guide+created: YYYY-MM-DD+tags: ["#welcome", "#getting-started", "#cog"]+---++# Welcome to Your COG Second Brain, [Name]!++Your COG is now personalized and ready to use. Here's how to get started:++## Your Profile Documents++I've created these documents to store your preferences:++- **[[MY-PROFILE]]** - Your basic info, role pack, and workflow preferences+- **[[MY-INTERESTS]]** - Topics for your daily briefs+- **[[MY-INTEGRATIONS]]** - Your active and disabled integrations+- **[[03-professional/COMPETITIVE-WATCHLIST]]** - Companies you're tracking *(if applicable)*++**You can edit these files anytime.** COG reads them when you use skills, so your changes take effect immediately.++## Skills for Your Role++[If role pack was matched:]+As a **[Role Display Name]**, these skills are ordered by relevance for you:++[List skills from role pack in order, with brief "why it matters" from the role pack. Format as:]+1. **[skill-name]** — [Role-specific explanation]+2. **[skill-name]** — [Role-specific explanation]+[...continue for all recommended skills]++[If no role pack match:]+Here are COG's core skills available to everyone:++1. **daily-brief** — Personalized news intelligence+2. **braindump** — Capture and classify thoughts+3. **weekly-checkin** — Weekly pattern analysis+4. **knowledge-consolidation** — Build frameworks from scattered notes+5. **url-dump** — Save URLs with auto-extracted insights+6. **update-cog** — Keep COG framework current++## Your Integrations++[If integrations were configured:]+**Active**: [List active integrations]+**Disabled**: [List disabled integrations]++You can change these anytime by editing [[MY-INTEGRATIONS]].++[If no integrations configured:]+No integrations configured yet. COG works great standalone — add integrations anytime by editing `00-inbox/MY-INTEGRATIONS.md`.++## Quick Start++### 1. Daily Morning Routine+Invoke the daily-brief skill to get your personalized intelligence briefing covering:+[List their selected interest areas]++### 2. Capture Your Thoughts+Use the braindump skill to quickly capture ideas, insights, and thoughts. Your braindumps will automatically be categorized into:+[List their focus domains]++Choose from your active projects:+[List their projects with links]++### 3. Weekly Reflection+Every week, use the weekly-checkin skill to review your week's insights and patterns.++## Your Active Projects++[If they have projects]+You're tracking these projects:+- [[04-projects/[slug]/PROJECT-OVERVIEW|Project 1]]+- [[04-projects/[slug]/PROJECT-OVERVIEW|Project 2]]++When you use the braindump skill, select the project to automatically file your thoughts in the right place.++## How COG Uses Your Profile++**Daily Briefs**: Uses [[MY-INTERESTS]] to curate relevant news+**Braindumps**: Offers your projects from [[MY-PROFILE]] as options+**Competitive Intel**: Auto-extracts mentions of companies in [[COMPETITIVE-WATCHLIST]]+**Weekly Check-ins**: Reviews progress across your domains++## Next Steps++1. **Try your first braindump**: Use the braindump skill and start writing+2. **Get your daily brief**: Invoke the daily-brief skill to see curated intelligence+3. **Explore your vault**: All your files are organized in the sidebar+4. **Edit your profile**: Open [[MY-PROFILE]] and customize anytime++## Keeping COG Updated++COG separates your content from framework files. When new versions are released:+- Run `/update-cog` to check for and apply updates+- Or use the shell script: `./cog-update.sh --check`+- Your braindumps, profiles, and notes are **never** touched by updates++Check your current version: `cat COG-VERSION`++## Tips for Success++- **Don't overthink it**: Just dump your thoughts, COG will help organize+- **Be consistent**: Daily briefs and braindumps work best as habits+- **Review weekly**: Use the weekly-checkin skill to see patterns emerge+- **Evolve your setup**: Edit your profile files anytime or run onboarding again to add projects+- **Stay updated**: Run `/update-cog` periodically to get new skills and improvements++## Getting Help++- Check `SETUP.md` for detailed guides+- Visit the GitHub repo for documentation++**Your second brain is learning about you. Let's begin!**++---++*You can archive or delete this welcome guide once you're comfortable with COG.*+```diff --git a/.claude/skills/product-ui-taste/SKILL.md b/.claude/skills/product-ui-taste/SKILL.mdindex c5b5926..6e8064d 100644--- a/.claude/skills/product-ui-taste/SKILL.md+++ b/.claude/skills/product-ui-taste/SKILL.md@@ -405,52 +405,7 @@ When the Product Read matches one of these, scaffold the whole skeleton, not a f- **Dashboard/overview**: KPI tile row (Cards) + widget grid + one or two drill-in Tables (rows).- **Admin console with bulk actions**: table + selection persistence + bulk action bar (capped at 5 + overflow) + confirmation dialogs.-### 12.A Block Library (reference implementations)-Full component implementations live in the host system, not duplicated here: reach them via your host system's template/skeleton command or its docs (Appendix B). Three high-value skeletons are worked below because they encode the contracts most often gotten wrong; treat them as the canonical shape, adapt to the host system.--**Block 1 - Index + detail-drawer (frame-first):**-```tsx-// Budget the frame first: nav 256 | table flex | inspector 380-<AppShell sideNav={<SideNav>{/* nav */}</SideNav>} contentPadding={0}>- <Layout>- <LayoutContent>- <ToolbarTableFilter /* search + status/priority filters + overflow (cap 5) */ />- {/* applied-filter chips row + Clear all (Section 7.F) */}- <Table- plugins={[useTableStickyColumns, useTableColumnResize /*, pagination */]}- /* selection persists by row id across page/sort/filter (Section 7.E) */- />- {/* pagination footer; three empty states + ErrorState wired per Section 6 */}- </LayoutContent>- <LayoutPanel width={380} resizable={{minSizePx: 320, maxSizePx: 480}} hasDivider isScrollable>- {selected ? <DetailFields item={selected} /> : <EmptyState title="Nothing selected" />}- </LayoutPanel>- </Layout>-</AppShell>-// Below ~1024px: LayoutPanel overlays Content; SideNav becomes MobileNav.-```--**Block 2 - Table scroll + sticky header + frozen column (the CSS contract a system's hooks satisfy):**-```css-/* ONE wrapper owns both scroll axes; page body never scrolls sideways (Section 4). */-.table-scroll { overflow: auto; max-block-size: 70vh; } /* bounded height => sticky works */-.table-scroll thead th { position: sticky; inset-block-start: 0; z-index: 20; }-/* Frozen first column: sticky + offset + z + SOLID THEME-TOKEN bg + shadow divider, never border */-.col-frozen {- position: sticky; inset-inline-start: 0; z-index: 10;- background: var(--color-surface); /* must also cover hover/selected rows */- box-shadow: inset -1px 0 0 var(--color-border); /* not border-right (double-renders on scroll) */-}-```--**Block 3 - Truncation contract (single-line + multi-line):**-```css-.cell { min-inline-size: 0; } /* required on EVERY flex ancestor or ellipsis no-ops */-.cell .text { overflow: hidden; text-overflow: ellipsis; white-space: nowrap; }-.clamp { /* all four props; NO padding on this node */- display: -webkit-box; -webkit-line-clamp: 2; -webkit-box-orient: vertical; overflow: hidden;-}-```+Full component implementations live in the host system, not duplicated here: reach them via your host system's template/skeleton command or its docs (`references/canonical-sources.md`). Three high-value skeletons are worked in `references/block-skeletons.md` because they encode the contracts most often gotten wrong; treat them as the canonical shape, adapt to the host system.---@@ -557,97 +512,8 @@ If a single box cannot be honestly ticked, fix it before delivering.----# APPENDICES - Source-Backed Reference Material--## Appendix A - Install / CLI per system--```bash-# House design system - resolve the real API before writing UI.-# Most systems ship a CLI or a docs site; use whichever exists.-# 1. find the closest shipped page/block template-# 2. study its layout skeleton-# 3. read real props for every component (never invent props)--# IBM Carbon-npm install @carbon/react @carbon/styles-# Microsoft Fluent UI React v9-npm install @fluentui/react-components-# Atlassian Atlaskit (per-component + tokens)-npm install @atlaskit/tokens @atlaskit/dynamic-table-# Shopify Polaris-npm install @shopify/polaris-# GitHub Primer React-npm install @primer/react styled-components-# Radix Primitives + shadcn/ui + TanStack Table-npm install @radix-ui/react-dialog @radix-ui/react-toast @tanstack/react-table-npx shadcn@latest add table dialog-# Material Web (Material 3)-npm install @material/web-# Ant Design / Mantine + Mantine React Table-npm install antd-npm install @mantine/core @mantine/form mantine-react-table-```--## Appendix B - Canonical sources (real URLs, gsearch-verified)--Consolidated primary sources:--**Frame / layout**-- Carbon 2x grid: https://carbondesignsystem.com/elements/2x-grid/usage/-- Primer PageLayout: https://primer.style/product/components/page-layout-- Material 3 canonical layouts: https://m3.material.io/foundations/adaptive-design/canonical-layouts-- Material 3 list-detail: https://m3.material.io/foundations/layout/canonical-examples/list-detail-- Material 3 supporting-pane: https://m3.material.io/foundations/layout/canonical-examples/supporting-pane-- Container queries: https://www.joshwcomeau.com/css/container-queries-unleashed/--**Overflow / truncation**-- Carbon overflow content: https://carbondesignsystem.com/patterns/overflow-content/-- Primer Truncate: https://primer.style/product/components/truncate/-- CSS line-clamp: https://css-tricks.com/line-clampin/--**State matrix**-- Polaris EmptyState: https://polaris-react.shopify.com/components/layout-and-structure/empty-state-- Carbon empty states: https://carbondesignsystem.com/patterns/empty-states-pattern/-- Carbon loading: https://carbondesignsystem.com/patterns/loading-pattern/-- Primer empty states: https://primer.style/product/ui-patterns/empty-states/-- NN/g skeleton screens: https://www.nngroup.com/articles/skeleton-screens/-- NN/g empty-state design: https://www.nngroup.com/articles/empty-state-interface-design/-- Pencil&Paper empty states: https://www.pencilandpaper.io/articles/empty-states-- Polaris error messages: https://polaris-react.shopify.com/content/error-messages--**Data table**-- Carbon data table: https://carbondesignsystem.com/components/data-table/usage/-- Polaris IndexTable: https://polaris-react.shopify.com/components/tables/index-table-- Ant table scroll: https://ant.design/docs/blog/table-scroll-ghost/-- Ant virtual table: https://ant.design/docs/blog/virtual-table/-- TanStack column sizing: https://tanstack.com/table/latest/docs/guide/column-sizing-- Mantine React Table column pinning: https://www.mantine-react-table.com/docs/guides/column-pinning-- NN/g infinite scroll: https://www.nngroup.com/articles/infinite-scrolling-tips/-- Baymard checkout linear / pagination context: https://baymard.com/blog/checkout-process-should-be-linear-- Pagination vs infinite vs load-more: https://www.smashingmagazine.com/2016/03/pagination-infinite-scrolling-load-more-buttons/--**Forms / flows**-- LukeW web form design: https://www.lukew.com/ff/entry.asp?504-- NN/g web form design: https://www.nngroup.com/articles/web-form-design/-- NN/g form errors: https://www.nngroup.com/articles/errors-forms-design-guidelines/-- Polaris inline error: https://polaris-react.shopify.com/components/selection-and-input/inline-error-- Ant / 2x form pattern: https://2x.ant.design/docs/pattern/form-- Mantine form validation: https://mantine.dev/form/validation/--**Overlays / layering / a11y**-- Radix Dialog: https://www.radix-ui.com/primitives/docs/components/dialog-- Radix Toast: https://www.radix-ui.com/primitives/docs/components/toast-- W3C ARIA alertdialog: https://www.w3.org/WAI/ARIA/apg/patterns/alertdialog/-- W3C ARIA dialog-modal: https://www.w3.org/WAI/ARIA/apg/patterns/dialog-modal/-- W3C ARIA grid data-grids: https://www.w3.org/WAI/ARIA/apg/patterns/grid/examples/data-grids/-- MDN stacking context: https://developer.mozilla.org/en-US/docs/Web/CSS/Guides/Positioned_layout/Stacking_context--**Tokens / density / i18n**-- Atlaskit design tokens: https://atlassian.design/foundations/design-tokens-- Atlaskit spacing: https://atlassian.design/foundations/spacing-- Crowdin UI localization: https://crowdin.com/blog/best-practices-for-ui-localization-- Material 3 accessibility (targets): https://m3.material.io/components/buttons/accessibility--**Modern minimal**-- Linear method: https://linear.app/method/introduction-- Vercel design guidelines: https://vercel.com/design/guidelines+## References+- `references/block-skeletons.md` - worked reference implementations for the three block contracts most often gotten wrong (index + detail-drawer frame, table scroll/sticky-header/frozen-column CSS contract, truncation contract).+- `references/install-commands.md` - Appendix A: package-manager install commands per host design system.+- `references/canonical-sources.md` - Appendix B: gsearch-verified primary-source URLs backing this skill's rules, grouped by topic.+diff --git a/.claude/skills/product-ui-taste/references/block-skeletons.md b/.claude/skills/product-ui-taste/references/block-skeletons.mdnew file mode 100644index 0000000..fd64072--- /dev/null+++ b/.claude/skills/product-ui-taste/references/block-skeletons.md@@ -0,0 +1,51 @@+# Block skeletons++Reference for product-ui-taste: worked reference implementations for the three block contracts most often gotten wrong.++### 12.A Block Library (reference implementations)+Full component implementations live in the host system, not duplicated here: reach them via your host system's template/skeleton command or its docs (Appendix B). Three high-value skeletons are worked below because they encode the contracts most often gotten wrong; treat them as the canonical shape, adapt to the host system.++**Block 1 - Index + detail-drawer (frame-first):**+```tsx+// Budget the frame first: nav 256 | table flex | inspector 380+<AppShell sideNav={<SideNav>{/* nav */}</SideNav>} contentPadding={0}>+ <Layout>+ <LayoutContent>+ <ToolbarTableFilter /* search + status/priority filters + overflow (cap 5) */ />+ {/* applied-filter chips row + Clear all (Section 7.F) */}+ <Table+ plugins={[useTableStickyColumns, useTableColumnResize /*, pagination */]}+ /* selection persists by row id across page/sort/filter (Section 7.E) */+ />+ {/* pagination footer; three empty states + ErrorState wired per Section 6 */}+ </LayoutContent>+ <LayoutPanel width={380} resizable={{minSizePx: 320, maxSizePx: 480}} hasDivider isScrollable>+ {selected ? <DetailFields item={selected} /> : <EmptyState title="Nothing selected" />}+ </LayoutPanel>+ </Layout>+</AppShell>+// Below ~1024px: LayoutPanel overlays Content; SideNav becomes MobileNav.+```++**Block 2 - Table scroll + sticky header + frozen column (the CSS contract a system's hooks satisfy):**+```css+/* ONE wrapper owns both scroll axes; page body never scrolls sideways (Section 4). */+.table-scroll { overflow: auto; max-block-size: 70vh; } /* bounded height => sticky works */+.table-scroll thead th { position: sticky; inset-block-start: 0; z-index: 20; }+/* Frozen first column: sticky + offset + z + SOLID THEME-TOKEN bg + shadow divider, never border */+.col-frozen {+ position: sticky; inset-inline-start: 0; z-index: 10;+ background: var(--color-surface); /* must also cover hover/selected rows */+ box-shadow: inset -1px 0 0 var(--color-border); /* not border-right (double-renders on scroll) */+}+```++**Block 3 - Truncation contract (single-line + multi-line):**+```css+.cell { min-inline-size: 0; } /* required on EVERY flex ancestor or ellipsis no-ops */+.cell .text { overflow: hidden; text-overflow: ellipsis; white-space: nowrap; }+.clamp { /* all four props; NO padding on this node */+ display: -webkit-box; -webkit-line-clamp: 2; -webkit-box-orient: vertical; overflow: hidden;+}+```+diff --git a/.claude/skills/product-ui-taste/references/canonical-sources.md b/.claude/skills/product-ui-taste/references/canonical-sources.mdnew file mode 100644index 0000000..ee68c6c--- /dev/null+++ b/.claude/skills/product-ui-taste/references/canonical-sources.md@@ -0,0 +1,67 @@+# Canonical sources++Reference for product-ui-taste: gsearch-verified primary-source URLs backing this skill's rules, grouped by topic.++## Appendix B - Canonical sources (real URLs, gsearch-verified)++Consolidated primary sources:++**Frame / layout**+- Carbon 2x grid: https://carbondesignsystem.com/elements/2x-grid/usage/+- Primer PageLayout: https://primer.style/product/components/page-layout+- Material 3 canonical layouts: https://m3.material.io/foundations/adaptive-design/canonical-layouts+- Material 3 list-detail: https://m3.material.io/foundations/layout/canonical-examples/list-detail+- Material 3 supporting-pane: https://m3.material.io/foundations/layout/canonical-examples/supporting-pane+- Container queries: https://www.joshwcomeau.com/css/container-queries-unleashed/++**Overflow / truncation**+- Carbon overflow content: https://carbondesignsystem.com/patterns/overflow-content/+- Primer Truncate: https://primer.style/product/components/truncate/+- CSS line-clamp: https://css-tricks.com/line-clampin/++**State matrix**+- Polaris EmptyState: https://polaris-react.shopify.com/components/layout-and-structure/empty-state+- Carbon empty states: https://carbondesignsystem.com/patterns/empty-states-pattern/+- Carbon loading: https://carbondesignsystem.com/patterns/loading-pattern/+- Primer empty states: https://primer.style/product/ui-patterns/empty-states/+- NN/g skeleton screens: https://www.nngroup.com/articles/skeleton-screens/+- NN/g empty-state design: https://www.nngroup.com/articles/empty-state-interface-design/+- Pencil&Paper empty states: https://www.pencilandpaper.io/articles/empty-states+- Polaris error messages: https://polaris-react.shopify.com/content/error-messages++**Data table**+- Carbon data table: https://carbondesignsystem.com/components/data-table/usage/+- Polaris IndexTable: https://polaris-react.shopify.com/components/tables/index-table+- Ant table scroll: https://ant.design/docs/blog/table-scroll-ghost/+- Ant virtual table: https://ant.design/docs/blog/virtual-table/+- TanStack column sizing: https://tanstack.com/table/latest/docs/guide/column-sizing+- Mantine React Table column pinning: https://www.mantine-react-table.com/docs/guides/column-pinning+- NN/g infinite scroll: https://www.nngroup.com/articles/infinite-scrolling-tips/+- Baymard checkout linear / pagination context: https://baymard.com/blog/checkout-process-should-be-linear+- Pagination vs infinite vs load-more: https://www.smashingmagazine.com/2016/03/pagination-infinite-scrolling-load-more-buttons/++**Forms / flows**+- LukeW web form design: https://www.lukew.com/ff/entry.asp?504+- NN/g web form design: https://www.nngroup.com/articles/web-form-design/+- NN/g form errors: https://www.nngroup.com/articles/errors-forms-design-guidelines/+- Polaris inline error: https://polaris-react.shopify.com/components/selection-and-input/inline-error+- Ant / 2x form pattern: https://2x.ant.design/docs/pattern/form+- Mantine form validation: https://mantine.dev/form/validation/++**Overlays / layering / a11y**+- Radix Dialog: https://www.radix-ui.com/primitives/docs/components/dialog+- Radix Toast: https://www.radix-ui.com/primitives/docs/components/toast+- W3C ARIA alertdialog: https://www.w3.org/WAI/ARIA/apg/patterns/alertdialog/+- W3C ARIA dialog-modal: https://www.w3.org/WAI/ARIA/apg/patterns/dialog-modal/+- W3C ARIA grid data-grids: https://www.w3.org/WAI/ARIA/apg/patterns/grid/examples/data-grids/+- MDN stacking context: https://developer.mozilla.org/en-US/docs/Web/CSS/Guides/Positioned_layout/Stacking_context++**Tokens / density / i18n**+- Atlaskit design tokens: https://atlassian.design/foundations/design-tokens+- Atlaskit spacing: https://atlassian.design/foundations/spacing+- Crowdin UI localization: https://crowdin.com/blog/best-practices-for-ui-localization+- Material 3 accessibility (targets): https://m3.material.io/components/buttons/accessibility++**Modern minimal**+- Linear method: https://linear.app/method/introduction+- Vercel design guidelines: https://vercel.com/design/guidelinesdiff --git a/.claude/skills/product-ui-taste/references/install-commands.md b/.claude/skills/product-ui-taste/references/install-commands.mdnew file mode 100644index 0000000..6940073--- /dev/null+++ b/.claude/skills/product-ui-taste/references/install-commands.md@@ -0,0 +1,32 @@+# Install / CLI per system++Reference for product-ui-taste: package-manager install commands for each supported host design system.++## Appendix A - Install / CLI per system++```bash+# House design system - resolve the real API before writing UI.+# Most systems ship a CLI or a docs site; use whichever exists.+# 1. find the closest shipped page/block template+# 2. study its layout skeleton+# 3. read real props for every component (never invent props)++# IBM Carbon+npm install @carbon/react @carbon/styles+# Microsoft Fluent UI React v9+npm install @fluentui/react-components+# Atlassian Atlaskit (per-component + tokens)+npm install @atlaskit/tokens @atlaskit/dynamic-table+# Shopify Polaris+npm install @shopify/polaris+# GitHub Primer React+npm install @primer/react styled-components+# Radix Primitives + shadcn/ui + TanStack Table+npm install @radix-ui/react-dialog @radix-ui/react-toast @tanstack/react-table+npx shadcn@latest add table dialog+# Material Web (Material 3)+npm install @material/web+# Ant Design / Mantine + Mantine React Table+npm install antd+npm install @mantine/core @mantine/form mantine-react-table+```diff --git a/.claude/skills/taste-skill/SKILL.md b/.claude/skills/taste-skill/SKILL.mdindex 9b80a8e..e97c720 100644--- a/.claude/skills/taste-skill/SKILL.md+++ b/.claude/skills/taste-skill/SKILL.md@@ -364,111 +364,13 @@ These are tools, not defaults. Use them when the design read calls for them. **N### 5.A Sticky-Stack - Canonical Skeleton-```tsx-"use client";-import { useRef, useEffect } from "react";-import { gsap } from "gsap";-import { ScrollTrigger } from "gsap/ScrollTrigger";-import { useReducedMotion } from "motion/react";--gsap.registerPlugin(ScrollTrigger);--export function StickyStack({ cards }: { cards: React.ReactNode[] }) {- const ref = useRef<HTMLDivElement>(null);- const reduce = useReducedMotion();-- useEffect(() => {- if (reduce || !ref.current) return;- const ctx = gsap.context(() => {- const cardEls = gsap.utils.toArray<HTMLElement>(".stack-card");- cardEls.forEach((card, i) => {- if (i === cardEls.length - 1) return;- ScrollTrigger.create({- trigger: card,- start: "top top", // pin at viewport top- endTrigger: cardEls[cardEls.length - 1],- end: "top top",- pin: true,- pinSpacing: false,- });- gsap.to(card, {- scale: 0.92,- opacity: 0.55,- ease: "none",- scrollTrigger: {- trigger: cardEls[i + 1],- start: "top bottom",- end: "top top",- scrub: true,- },- });- });- }, ref);- return () => ctx.revert();- }, [reduce]);-- return (- <div ref={ref} className="relative">- {cards.map((card, i) => (- <div- key={i}- className="stack-card sticky top-0 min-h-[100dvh] flex items-center justify-center"- >- {card}- </div>- ))}- </div>- );-}-```+Canonical tsx skeleton: `references/motion-skeletons.md`.Critical points: `start: "top top"`, `pin: true`, every card except the last is pinned, the scale/opacity transform is driven by the NEXT card's scroll trigger (so previous card shrinks as next one arrives).### 5.B Horizontal-Pan - Canonical Skeleton-```tsx-"use client";-import { useRef, useEffect } from "react";-import { gsap } from "gsap";-import { ScrollTrigger } from "gsap/ScrollTrigger";-import { useReducedMotion } from "motion/react";--gsap.registerPlugin(ScrollTrigger);--export function HorizontalPan({ children }: { children: React.ReactNode }) {- const wrap = useRef<HTMLDivElement>(null);- const track = useRef<HTMLDivElement>(null);- const reduce = useReducedMotion();-- useEffect(() => {- if (reduce || !wrap.current || !track.current) return;- const ctx = gsap.context(() => {- const distance = track.current!.scrollWidth - window.innerWidth;- gsap.to(track.current, {- x: -distance,- ease: "none",- scrollTrigger: {- trigger: wrap.current,- start: "top top", // pin starts when section top hits viewport top- end: () => `+=${distance}`, // scroll distance = track width minus viewport- pin: true,- scrub: 1,- invalidateOnRefresh: true,- },- });- }, wrap);- return () => ctx.revert();- }, [reduce]);-- return (- <section ref={wrap} className="relative overflow-hidden">- <div ref={track} className="flex h-[100dvh] items-center">- {children}- </div>- </section>- );-}-```+Canonical tsx skeleton: `references/motion-skeletons.md`.Critical points: `start: "top top"`, `pin: true`, `end: "+=${distance}"` (scroll length = horizontal travel needed), `scrub: 1`. The wrapper is pinned, the inner track slides horizontally as the user scrolls vertically.@@ -476,33 +378,7 @@ Critical points: `start: "top top"`, `pin: true`, `end: "+=${distance}"` (scrollFor simple "items appear as they enter viewport" (no pinning), prefer Motion's `whileInView` over GSAP - lighter, no ScrollTrigger needed:-```tsx-"use client";-import { motion, useReducedMotion } from "motion/react";--export function RevealStagger({ items }: { items: string[] }) {- const reduce = useReducedMotion();- return (- <ul className="grid gap-6">- {items.map((item, i) => (- <motion.li- key={item}- initial={reduce ? false : { opacity: 0, y: 24 }}- whileInView={{ opacity: 1, y: 0 }}- viewport={{ once: true, amount: 0.3 }}- transition={{- duration: 0.6,- delay: i * 0.06,- ease: [0.16, 1, 0.3, 1],- }}- >- {item}- </motion.li>- ))}- </ul>- );-}-```+Canonical tsx skeleton: `references/motion-skeletons.md`.Use this for: feature lists, testimonial grids, logo walls, anything that just needs "enter on scroll." Save GSAP for actual pin/scrub work.@@ -702,84 +578,6 @@ This rule is non-negotiable. The agent has historically ignored em-dash limits w----## 10. REFERENCE VOCABULARY (Pattern Names the Agent Should Know)--This is a vocabulary, not a library. The agent should KNOW these pattern names to communicate about them, design with them in mind, and reach for them when the design read calls for them. **Implementations and code sketches live in the Block Library (Section 12), which is populated iteratively.**--### Hero Paradigms-* **Asymmetric Split Hero** - Text on one side, asset on the other, generous white space.-* **Editorial Manifesto Hero** - Large type, no asset, almost-poster.-* **Video / Media Mask Hero** - Type cut out as mask over video background.-* **Kinetic-Type Hero** - Animated typography as the primary visual.-* **Curtain-Reveal Hero** - Hero parts on scroll like a curtain.-* **Scroll-Pinned Hero** - Hero stays pinned while content scrolls behind.--### Navigation & Menus-* **Mac OS Dock Magnification** - Edge nav, icons scale fluidly on hover.-* **Magnetic Button** - Pulls toward cursor.-* **Gooey Menu** - Sub-items detach like viscous liquid.-* **Dynamic Island** - Morphing pill for status / alerts.-* **Contextual Radial Menu** - Circular menu expanding at click point.-* **Floating Speed Dial** - FAB springing into curved secondary actions.-* **Mega Menu Reveal** - Full-screen dropdown, stagger-fade content.--### Layout & Grids-* **Bento Grid** - Asymmetric tile grouping (Apple Control Center).-* **Masonry Layout** - Staggered grid, no fixed row height.-* **Chroma Grid** - Borders / tiles with subtle animating gradients.-* **Split-Screen Scroll** - Two halves sliding in opposite directions.-* **Sticky-Stack Sections** - Sections that pin and stack on scroll.--### Cards & Containers-* **Parallax Tilt Card** - 3D tilt tracking mouse coordinates.-* **Spotlight Border Card** - Borders illuminate under cursor.-* **Glassmorphism Panel** - Frosted glass with inner refraction.-* **Holographic Foil Card** - Iridescent rainbow shift on hover.-* **Tinder Swipe Stack** - Physical card stack, swipe-away.-* **Morphing Modal** - Button expands into its own dialog.--### Scroll Animations-* **Sticky Scroll Stack** - Cards stick and physically stack.-* **Horizontal Scroll Hijack** - Vertical scroll → horizontal pan.-* **Locomotive / Sequence Scroll** - Video / 3D sequence tied to scrollbar.-* **Zoom Parallax** - Central background image zooming on scroll.-* **Scroll Progress Path** - SVG line drawing along scroll.-* **Liquid Swipe Transition** - Page transition like viscous liquid.--### Galleries & Media-* **Dome Gallery** - 3D panoramic gallery.-* **Coverflow Carousel** - 3D carousel with angled edges.-* **Drag-to-Pan Grid** - Boundless draggable canvas.-* **Accordion Image Slider** - Narrow strips expanding on hover.-* **Hover Image Trail** - Mouse leaves popping image trail.-* **Glitch Effect Image** - RGB-channel shift on hover.--### Typography & Text-* **Kinetic Marquee** - Endless text bands reversing on scroll.-* **Text Mask Reveal** - Massive type as transparent window to video.-* **Text Scramble Effect** - Matrix-style decoding on load / hover.-* **Circular Text Path** - Text curving along spinning circle.-* **Gradient Stroke Animation** - Outlined text with running gradient.-* **Kinetic Typography Grid** - Letters dodging the cursor.--### Micro-Interactions & Effects-* **Particle Explosion Button** - CTA shatters into particles on success.-* **Liquid Pull-to-Refresh** - Reload indicator like detaching droplets.-* **Skeleton Shimmer** - Shifting light reflection across placeholders.-* **Directional Hover-Aware Button** - Fill enters from cursor's exact side.-* **Ripple Click Effect** - Wave from click coordinates.-* **Animated SVG Line Drawing** - Vectors drawing themselves in real time.-* **Mesh Gradient Background** - Organic lava-lamp blobs.-* **Lens Blur Depth** - Background UI blurred to focus foreground action.--### Animation Library Choice-* **Motion (`motion/react`)** - default for UI / Bento / state-change motion.-* **GSAP + ScrollTrigger** - for full-page scrolltelling and scroll hijacks. Isolate in dedicated leaf components with `useEffect` cleanup.-* **Three.js / WebGL** - for canvas backgrounds and 3D scenes. Same isolation rule.-* **NEVER mix GSAP / Three.js with Motion in the same component tree.** They fight over the same frames.------## 11. REDESIGN PROTOCOLThis skill handles **greenfield builds AND redesigns**. Misclassifying the mode is the single biggest source of bad redesign output.@@ -814,7 +612,7 @@ Apply in order - stop when the brief is satisfied:2. **Spacing & rhythm** - increase section padding, fix vertical rhythm.3. **Color recalibration** - desaturate, unify neutrals, keep brand accent.4. **Motion layer** - add `MOTION_INTENSITY`-appropriate micro-interactions to existing components.-5. **Hero & key-section recomposition** - restructure top-of-funnel using Section 10 vocabulary.+5. **Hero & key-section recomposition** - restructure top-of-funnel using the vocabulary in `references/pattern-vocabulary.md`.6. **Full block replacement** - only when the existing block is unsalvageable.### 11.E Decision Tree: Targeted Evolution vs Full Redesign@@ -834,7 +632,7 @@ Never modify without explicit user approval:## 12. THE BLOCK LIBRARY (Contract - Implementations Land Here Iteratively)-The Reference Vocabulary (Section 10) names patterns. The Block Library implements them with real props, real motion specs, and real code sketches.+The Reference Vocabulary (`references/pattern-vocabulary.md`) names patterns. The Block Library implements them with real props, real motion specs, and real code sketches.**Status:** schema defined here. Blocks will be added iteratively. Do not freelance new blocks without following this schema.@@ -982,227 +780,11 @@ If a single checkbox cannot be honestly ticked, the page is not done. Fix it bef----# APPENDICES - Real Source-Backed Reference Material--The sections below are vendored reference content. They give the agent real install commands, real canonical doc links, and real working starter snippets for each design system named in Section 2. Use them to ground decisions in production reality, not training-data fiction.--## Appendix A - Install Commands per Design System--```bash-# Material Web (Material 3)-npm install @material/web--# Fluent UI React (v9)-npm install @fluentui/react-components--# Fluent UI Web Components (framework-free)-npm install @fluentui/web-components @fluentui/tokens--# IBM Carbon-npm install @carbon/react @carbon/styles--# Radix Themes-npm install @radix-ui/themes--# shadcn/ui (open code, owned components)-npx shadcn@latest init-npx shadcn@latest add button card badge separator input--# Primer CSS (GitHub product/devtool UI)-npm install --save @primer/css+## References (vendored reference material, moved out of the body)-# Primer Brand (GitHub marketing UI)-npm install @primer/react-brand--# GOV.UK Frontend-npm install govuk-frontend--# USWDS (US Web Design System)-npm install uswds--# Atlassian Design System (Atlaskit)-yarn add @atlaskit/css-reset @atlaskit/tokens @atlaskit/button @atlaskit/badge @atlaskit/section-message @atlaskit/card--# Bootstrap 5.3-npm install bootstrap--# Shopify Polaris Web Components (Shopify apps only)-# Add this to your app HTML head:-# <meta name="shopify-api-key" content="%SHOPIFY_API_KEY%" />-# <script src="https://cdn.shopify.com/shopifycloud/polaris.js"></script>-```--## Appendix B - Canonical Sources (read these before reinventing)--### Material Web-- https://github.com/material-components/material-web-- https://material-web.dev/theming/material-theming/-- https://m3.material.io/develop/web--### Fluent UI-- https://fluent2.microsoft.design/get-started/develop-- https://fluent2.microsoft.design/components/web/react/-- https://github.com/microsoft/fluentui-- https://learn.microsoft.com/en-us/fluent-ui/web-components/--### Carbon-- https://carbondesignsystem.com/-- https://github.com/carbon-design-system/carbon-- https://carbondesignsystem.com/developing/react-tutorial/overview/-- https://carbondesignsystem.com/developing/web-components-tutorial/overview/--### Shopify Polaris-- https://shopify.dev/docs/api/app-home/web-components-- https://github.com/Shopify/polaris-react-- https://polaris-react.shopify.com/components--### Atlassian-- https://atlassian.design/get-started/develop-- https://atlassian.design/components/button/examples-- https://atlaskit.atlassian.com/packages/design-system/button/example/disabled-- https://atlassian.design/tokens/design-tokens--### Primer-- https://primer.style/-- https://github.com/primer/css-- https://github.com/primer/brand--### GOV.UK-- https://design-system.service.gov.uk/components/button/-- https://design-system.service.gov.uk/styles/layout/-- https://github.com/alphagov/govuk-frontend--### USWDS-- https://designsystem.digital.gov/documentation/developers/-- https://designsystem.digital.gov/components/button/-- https://designsystem.digital.gov/components/card/-- https://github.com/uswds/uswds--### Bootstrap-- https://getbootstrap.com/docs/5.3/layout/grid/-- https://getbootstrap.com/docs/5.3/components/card/--### Tailwind-- https://tailwindcss.com/docs/dark-mode-- https://tailwindcss.com/blog/tailwindcss-v4--### Radix-- https://www.radix-ui.com/themes/docs/components/theme-- https://www.radix-ui.com/themes/docs/components/card-- https://github.com/radix-ui/themes--### shadcn/ui-- https://ui.shadcn.com/docs-- https://ui.shadcn.com/docs/components/card-- https://github.com/shadcn-ui/ui--### Native CSS / W3C standards-- https://developer.mozilla.org/en-US/docs/Web/CSS/Reference/Properties/backdrop-filter-- https://developer.mozilla.org/en-US/docs/Web/CSS/Reference/At-rules/@media/prefers-color-scheme-- https://developer.mozilla.org/en-US/docs/Web/CSS/Reference/At-rules/@media/prefers-reduced-motion-- https://developer.mozilla.org/en-US/docs/Web/CSS/Guides/Grid_layout-- https://developer.mozilla.org/en-US/docs/Web/CSS/Guides/Scroll-driven_animations-- https://drafts.csswg.org/scroll-animations-1/--### Apple Liquid Glass (Apple platforms only)-- https://developer.apple.com/design/human-interface-guidelines/materials-- https://developer.apple.com/documentation/TechnologyOverviews/liquid-glass-- https://developer.apple.com/documentation/TechnologyOverviews/adopting-liquid-glass-- https://developer.apple.com/documentation/SwiftUI/Material-------## Appendix C - Apple Liquid Glass: Honest Web Approximation--Do **not** treat random CSS snippets as official Apple Liquid Glass.--### What is official-Apple documents Liquid Glass inside Apple's Human Interface Guidelines and Developer Documentation for **Apple platforms**. It is a dynamic material used across Apple platform UI. Apple's native implementation belongs to Apple platform APIs and system components, **not a public web CSS package**.--Relevant official docs:-- Apple Human Interface Guidelines → Materials-- Apple Developer Documentation → Liquid Glass-- Apple Developer Documentation → Adopting Liquid Glass-- SwiftUI → Material--### What is NOT official-There is no `liquid-glass.css` from Apple for normal websites.--A web approximation can use:-- `backdrop-filter`-- transparent backgrounds-- layered borders-- highlight overlays-- gradients-- motion-- strong contrast fallbacks--But that is **web glassmorphism / frosted-glass approximation**, not official Apple Liquid Glass. Label it as such in comments.--### Safer web approximation skeleton--```css-.liquid-glass-web-approx {- position: relative;- isolation: isolate;- overflow: hidden;- border-radius: 999px;- border: 1px solid rgb(255 255 255 / .32);- background:- linear-gradient(135deg, rgb(255 255 255 / .30), rgb(255 255 255 / .08)),- rgb(255 255 255 / .12);- backdrop-filter: blur(24px) saturate(180%) contrast(1.05);- -webkit-backdrop-filter: blur(24px) saturate(180%) contrast(1.05);- box-shadow:- inset 0 1px 0 rgb(255 255 255 / .48),- inset 0 -1px 0 rgb(255 255 255 / .12),- 0 18px 60px rgb(0 0 0 / .18);-}--.liquid-glass-web-approx::before {- content: "";- position: absolute;- inset: 0;- z-index: -1;- border-radius: inherit;- background:- radial-gradient(circle at 20% 0%, rgb(255 255 255 / .55), transparent 34%),- linear-gradient(90deg, rgb(255 255 255 / .18), transparent 42%, rgb(255 255 255 / .14));- pointer-events: none;-}--.liquid-glass-web-approx::after {- content: "";- position: absolute;- inset: 1px;- border-radius: inherit;- border: 1px solid rgb(255 255 255 / .14);- pointer-events: none;-}--@media (prefers-color-scheme: dark) {- .liquid-glass-web-approx {- border-color: rgb(255 255 255 / .18);- background:- linear-gradient(135deg, rgb(255 255 255 / .16), rgb(255 255 255 / .04)),- rgb(15 23 42 / .42);- box-shadow:- inset 0 1px 0 rgb(255 255 255 / .22),- 0 18px 60px rgb(0 0 0 / .42);- }-}--@media (prefers-reduced-transparency: reduce) {- .liquid-glass-web-approx {- background: rgb(255 255 255 / .96);- backdrop-filter: none;- -webkit-backdrop-filter: none;- }-}-```--**Important:** `prefers-reduced-transparency` has uneven browser support; test it. Always provide enough contrast even without blur.-----+- `references/pattern-vocabulary.md` - the full Reference Vocabulary (pattern names the agent should know).+- `references/motion-skeletons.md` - canonical tsx code skeletons for the 5.A Sticky-Stack, 5.B Horizontal-Pan, and 5.C Scroll-Reveal Stagger patterns.+- `references/design-systems-install.md` - real install commands per design system named in Section 2.+- `references/canonical-sources.md` - canonical documentation links per design system, read these before reinventing.+- `references/liquid-glass.md` - what is and isn't official Apple Liquid Glass, plus a labeled web CSS approximation.-**End of appendices.** Install commands above are reality anchors. The Apple Liquid Glass skeleton is a labeled approximation, not an Apple-issued package. For canonical docs per design system, consult the system's official docs (links in Section 2 plus Appendix B).diff --git a/.claude/skills/taste-skill/references/canonical-sources.md b/.claude/skills/taste-skill/references/canonical-sources.mdnew file mode 100644index 0000000..4b78d44--- /dev/null+++ b/.claude/skills/taste-skill/references/canonical-sources.md@@ -0,0 +1,83 @@+# Canonical Design System Sources++Canonical documentation links per design system named in taste-skill's Section 2. Read these before reinventing a component that a system already ships.++## Appendix B - Canonical Sources (read these before reinventing)++### Material Web+- https://github.com/material-components/material-web+- https://material-web.dev/theming/material-theming/+- https://m3.material.io/develop/web++### Fluent UI+- https://fluent2.microsoft.design/get-started/develop+- https://fluent2.microsoft.design/components/web/react/+- https://github.com/microsoft/fluentui+- https://learn.microsoft.com/en-us/fluent-ui/web-components/++### Carbon+- https://carbondesignsystem.com/+- https://github.com/carbon-design-system/carbon+- https://carbondesignsystem.com/developing/react-tutorial/overview/+- https://carbondesignsystem.com/developing/web-components-tutorial/overview/++### Shopify Polaris+- https://shopify.dev/docs/api/app-home/web-components+- https://github.com/Shopify/polaris-react+- https://polaris-react.shopify.com/components++### Atlassian+- https://atlassian.design/get-started/develop+- https://atlassian.design/components/button/examples+- https://atlaskit.atlassian.com/packages/design-system/button/example/disabled+- https://atlassian.design/tokens/design-tokens++### Primer+- https://primer.style/+- https://github.com/primer/css+- https://github.com/primer/brand++### GOV.UK+- https://design-system.service.gov.uk/components/button/+- https://design-system.service.gov.uk/styles/layout/+- https://github.com/alphagov/govuk-frontend++### USWDS+- https://designsystem.digital.gov/documentation/developers/+- https://designsystem.digital.gov/components/button/+- https://designsystem.digital.gov/components/card/+- https://github.com/uswds/uswds++### Bootstrap+- https://getbootstrap.com/docs/5.3/layout/grid/+- https://getbootstrap.com/docs/5.3/components/card/++### Tailwind+- https://tailwindcss.com/docs/dark-mode+- https://tailwindcss.com/blog/tailwindcss-v4++### Radix+- https://www.radix-ui.com/themes/docs/components/theme+- https://www.radix-ui.com/themes/docs/components/card+- https://github.com/radix-ui/themes++### shadcn/ui+- https://ui.shadcn.com/docs+- https://ui.shadcn.com/docs/components/card+- https://github.com/shadcn-ui/ui++### Native CSS / W3C standards+- https://developer.mozilla.org/en-US/docs/Web/CSS/Reference/Properties/backdrop-filter+- https://developer.mozilla.org/en-US/docs/Web/CSS/Reference/At-rules/@media/prefers-color-scheme+- https://developer.mozilla.org/en-US/docs/Web/CSS/Reference/At-rules/@media/prefers-reduced-motion+- https://developer.mozilla.org/en-US/docs/Web/CSS/Guides/Grid_layout+- https://developer.mozilla.org/en-US/docs/Web/CSS/Guides/Scroll-driven_animations+- https://drafts.csswg.org/scroll-animations-1/++### Apple Liquid Glass (Apple platforms only)+- https://developer.apple.com/design/human-interface-guidelines/materials+- https://developer.apple.com/documentation/TechnologyOverviews/liquid-glass+- https://developer.apple.com/documentation/TechnologyOverviews/adopting-liquid-glass+- https://developer.apple.com/documentation/SwiftUI/Material++**End of appendices.** Install commands above are reality anchors. The Apple Liquid Glass skeleton is a labeled approximation, not an Apple-issued package. For canonical docs per design system, consult the system's official docs (links in Section 2 plus this file).diff --git a/.claude/skills/taste-skill/references/design-systems-install.md b/.claude/skills/taste-skill/references/design-systems-install.mdnew file mode 100644index 0000000..4c929b0--- /dev/null+++ b/.claude/skills/taste-skill/references/design-systems-install.md@@ -0,0 +1,49 @@+# Design System Install Commands++Real install commands for each design system named in taste-skill's Section 2. Read this before wiring up a design system so the package name and CLI invocation are correct.++## Appendix A - Install Commands per Design System++```bash+# Material Web (Material 3)+npm install @material/web++# Fluent UI React (v9)+npm install @fluentui/react-components++# Fluent UI Web Components (framework-free)+npm install @fluentui/web-components @fluentui/tokens++# IBM Carbon+npm install @carbon/react @carbon/styles++# Radix Themes+npm install @radix-ui/themes++# shadcn/ui (open code, owned components)+npx shadcn@latest init+npx shadcn@latest add button card badge separator input++# Primer CSS (GitHub product/devtool UI)+npm install --save @primer/css++# Primer Brand (GitHub marketing UI)+npm install @primer/react-brand++# GOV.UK Frontend+npm install govuk-frontend++# USWDS (US Web Design System)+npm install uswds++# Atlassian Design System (Atlaskit)+yarn add @atlaskit/css-reset @atlaskit/tokens @atlaskit/button @atlaskit/badge @atlaskit/section-message @atlaskit/card++# Bootstrap 5.3+npm install bootstrap++# Shopify Polaris Web Components (Shopify apps only)+# Add this to your app HTML head:+# <meta name="shopify-api-key" content="%SHOPIFY_API_KEY%" />+# <script src="https://cdn.shopify.com/shopifycloud/polaris.js"></script>+```diff --git a/.claude/skills/taste-skill/references/liquid-glass.md b/.claude/skills/taste-skill/references/liquid-glass.mdnew file mode 100644index 0000000..4e2eb64--- /dev/null+++ b/.claude/skills/taste-skill/references/liquid-glass.md@@ -0,0 +1,94 @@+# Apple Liquid Glass: Honest Web Approximation++What is and isn't official Apple Liquid Glass, and a labeled CSS approximation for the web, for taste-skill's Section 2 design-system decisions.++## Appendix C - Apple Liquid Glass: Honest Web Approximation++Do **not** treat random CSS snippets as official Apple Liquid Glass.++### What is official+Apple documents Liquid Glass inside Apple's Human Interface Guidelines and Developer Documentation for **Apple platforms**. It is a dynamic material used across Apple platform UI. Apple's native implementation belongs to Apple platform APIs and system components, **not a public web CSS package**.++Relevant official docs:+- Apple Human Interface Guidelines → Materials+- Apple Developer Documentation → Liquid Glass+- Apple Developer Documentation → Adopting Liquid Glass+- SwiftUI → Material++### What is NOT official+There is no `liquid-glass.css` from Apple for normal websites.++A web approximation can use:+- `backdrop-filter`+- transparent backgrounds+- layered borders+- highlight overlays+- gradients+- motion+- strong contrast fallbacks++But that is **web glassmorphism / frosted-glass approximation**, not official Apple Liquid Glass. Label it as such in comments.++### Safer web approximation skeleton++```css+.liquid-glass-web-approx {+ position: relative;+ isolation: isolate;+ overflow: hidden;+ border-radius: 999px;+ border: 1px solid rgb(255 255 255 / .32);+ background:+ linear-gradient(135deg, rgb(255 255 255 / .30), rgb(255 255 255 / .08)),+ rgb(255 255 255 / .12);+ backdrop-filter: blur(24px) saturate(180%) contrast(1.05);+ -webkit-backdrop-filter: blur(24px) saturate(180%) contrast(1.05);+ box-shadow:+ inset 0 1px 0 rgb(255 255 255 / .48),+ inset 0 -1px 0 rgb(255 255 255 / .12),+ 0 18px 60px rgb(0 0 0 / .18);+}++.liquid-glass-web-approx::before {+ content: "";+ position: absolute;+ inset: 0;+ z-index: -1;+ border-radius: inherit;+ background:+ radial-gradient(circle at 20% 0%, rgb(255 255 255 / .55), transparent 34%),+ linear-gradient(90deg, rgb(255 255 255 / .18), transparent 42%, rgb(255 255 255 / .14));+ pointer-events: none;+}++.liquid-glass-web-approx::after {+ content: "";+ position: absolute;+ inset: 1px;+ border-radius: inherit;+ border: 1px solid rgb(255 255 255 / .14);+ pointer-events: none;+}++@media (prefers-color-scheme: dark) {+ .liquid-glass-web-approx {+ border-color: rgb(255 255 255 / .18);+ background:+ linear-gradient(135deg, rgb(255 255 255 / .16), rgb(255 255 255 / .04)),+ rgb(15 23 42 / .42);+ box-shadow:+ inset 0 1px 0 rgb(255 255 255 / .22),+ 0 18px 60px rgb(0 0 0 / .42);+ }+}++@media (prefers-reduced-transparency: reduce) {+ .liquid-glass-web-approx {+ background: rgb(255 255 255 / .96);+ backdrop-filter: none;+ -webkit-backdrop-filter: none;+ }+}+```++**Important:** `prefers-reduced-transparency` has uneven browser support; test it. Always provide enough contrast even without blur.diff --git a/.claude/skills/taste-skill/references/motion-skeletons.md b/.claude/skills/taste-skill/references/motion-skeletons.mdnew file mode 100644index 0000000..473d394--- /dev/null+++ b/.claude/skills/taste-skill/references/motion-skeletons.md@@ -0,0 +1,139 @@+# Motion Skeletons++Canonical tsx code skeletons for the GSAP/Motion patterns named in SKILL.md Section 5 (5.A Sticky-Stack, 5.B Horizontal-Pan, 5.C Scroll-Reveal Stagger). Read the matching subsection in SKILL.md for the critical points and failure modes before pasting this in.++### 5.A Sticky-Stack++```tsx+"use client";+import { useRef, useEffect } from "react";+import { gsap } from "gsap";+import { ScrollTrigger } from "gsap/ScrollTrigger";+import { useReducedMotion } from "motion/react";++gsap.registerPlugin(ScrollTrigger);++export function StickyStack({ cards }: { cards: React.ReactNode[] }) {+ const ref = useRef<HTMLDivElement>(null);+ const reduce = useReducedMotion();++ useEffect(() => {+ if (reduce || !ref.current) return;+ const ctx = gsap.context(() => {+ const cardEls = gsap.utils.toArray<HTMLElement>(".stack-card");+ cardEls.forEach((card, i) => {+ if (i === cardEls.length - 1) return;+ ScrollTrigger.create({+ trigger: card,+ start: "top top", // pin at viewport top+ endTrigger: cardEls[cardEls.length - 1],+ end: "top top",+ pin: true,+ pinSpacing: false,+ });+ gsap.to(card, {+ scale: 0.92,+ opacity: 0.55,+ ease: "none",+ scrollTrigger: {+ trigger: cardEls[i + 1],+ start: "top bottom",+ end: "top top",+ scrub: true,+ },+ });+ });+ }, ref);+ return () => ctx.revert();+ }, [reduce]);++ return (+ <div ref={ref} className="relative">+ {cards.map((card, i) => (+ <div+ key={i}+ className="stack-card sticky top-0 min-h-[100dvh] flex items-center justify-center"+ >+ {card}+ </div>+ ))}+ </div>+ );+}+```++### 5.B Horizontal-Pan++```tsx+"use client";+import { useRef, useEffect } from "react";+import { gsap } from "gsap";+import { ScrollTrigger } from "gsap/ScrollTrigger";+import { useReducedMotion } from "motion/react";++gsap.registerPlugin(ScrollTrigger);++export function HorizontalPan({ children }: { children: React.ReactNode }) {+ const wrap = useRef<HTMLDivElement>(null);+ const track = useRef<HTMLDivElement>(null);+ const reduce = useReducedMotion();++ useEffect(() => {+ if (reduce || !wrap.current || !track.current) return;+ const ctx = gsap.context(() => {+ const distance = track.current!.scrollWidth - window.innerWidth;+ gsap.to(track.current, {+ x: -distance,+ ease: "none",+ scrollTrigger: {+ trigger: wrap.current,+ start: "top top", // pin starts when section top hits viewport top+ end: () => `+=${distance}`, // scroll distance = track width minus viewport+ pin: true,+ scrub: 1,+ invalidateOnRefresh: true,+ },+ });+ }, wrap);+ return () => ctx.revert();+ }, [reduce]);++ return (+ <section ref={wrap} className="relative overflow-hidden">+ <div ref={track} className="flex h-[100dvh] items-center">+ {children}+ </div>+ </section>+ );+}+```++### 5.C Scroll-Reveal Stagger++```tsx+"use client";+import { motion, useReducedMotion } from "motion/react";++export function RevealStagger({ items }: { items: string[] }) {+ const reduce = useReducedMotion();+ return (+ <ul className="grid gap-6">+ {items.map((item, i) => (+ <motion.li+ key={item}+ initial={reduce ? false : { opacity: 0, y: 24 }}+ whileInView={{ opacity: 1, y: 0 }}+ viewport={{ once: true, amount: 0.3 }}+ transition={{+ duration: 0.6,+ delay: i * 0.06,+ ease: [0.16, 1, 0.3, 1],+ }}+ >+ {item}+ </motion.li>+ ))}+ </ul>+ );+}+```diff --git a/.claude/skills/taste-skill/references/pattern-vocabulary.md b/.claude/skills/taste-skill/references/pattern-vocabulary.mdnew file mode 100644index 0000000..b4f3e6b--- /dev/null+++ b/.claude/skills/taste-skill/references/pattern-vocabulary.md@@ -0,0 +1,79 @@+# Pattern Vocabulary++The full reference vocabulary of named design/motion patterns taste-skill should recognize and reach for. Section 12 (the Block Library, in SKILL.md) implements a subset of these with real code.++## 10. REFERENCE VOCABULARY (Pattern Names the Agent Should Know)++This is a vocabulary, not a library. The agent should KNOW these pattern names to communicate about them, design with them in mind, and reach for them when the design read calls for them. **Implementations and code sketches live in the Block Library (Section 12), which is populated iteratively.**++### Hero Paradigms+* **Asymmetric Split Hero** - Text on one side, asset on the other, generous white space.+* **Editorial Manifesto Hero** - Large type, no asset, almost-poster.+* **Video / Media Mask Hero** - Type cut out as mask over video background.+* **Kinetic-Type Hero** - Animated typography as the primary visual.+* **Curtain-Reveal Hero** - Hero parts on scroll like a curtain.+* **Scroll-Pinned Hero** - Hero stays pinned while content scrolls behind.++### Navigation & Menus+* **Mac OS Dock Magnification** - Edge nav, icons scale fluidly on hover.+* **Magnetic Button** - Pulls toward cursor.+* **Gooey Menu** - Sub-items detach like viscous liquid.+* **Dynamic Island** - Morphing pill for status / alerts.+* **Contextual Radial Menu** - Circular menu expanding at click point.+* **Floating Speed Dial** - FAB springing into curved secondary actions.+* **Mega Menu Reveal** - Full-screen dropdown, stagger-fade content.++### Layout & Grids+* **Bento Grid** - Asymmetric tile grouping (Apple Control Center).+* **Masonry Layout** - Staggered grid, no fixed row height.+* **Chroma Grid** - Borders / tiles with subtle animating gradients.+* **Split-Screen Scroll** - Two halves sliding in opposite directions.+* **Sticky-Stack Sections** - Sections that pin and stack on scroll.++### Cards & Containers+* **Parallax Tilt Card** - 3D tilt tracking mouse coordinates.+* **Spotlight Border Card** - Borders illuminate under cursor.+* **Glassmorphism Panel** - Frosted glass with inner refraction.+* **Holographic Foil Card** - Iridescent rainbow shift on hover.+* **Tinder Swipe Stack** - Physical card stack, swipe-away.+* **Morphing Modal** - Button expands into its own dialog.++### Scroll Animations+* **Sticky Scroll Stack** - Cards stick and physically stack.+* **Horizontal Scroll Hijack** - Vertical scroll → horizontal pan.+* **Locomotive / Sequence Scroll** - Video / 3D sequence tied to scrollbar.+* **Zoom Parallax** - Central background image zooming on scroll.+* **Scroll Progress Path** - SVG line drawing along scroll.+* **Liquid Swipe Transition** - Page transition like viscous liquid.++### Galleries & Media+* **Dome Gallery** - 3D panoramic gallery.+* **Coverflow Carousel** - 3D carousel with angled edges.+* **Drag-to-Pan Grid** - Boundless draggable canvas.+* **Accordion Image Slider** - Narrow strips expanding on hover.+* **Hover Image Trail** - Mouse leaves popping image trail.+* **Glitch Effect Image** - RGB-channel shift on hover.++### Typography & Text+* **Kinetic Marquee** - Endless text bands reversing on scroll.+* **Text Mask Reveal** - Massive type as transparent window to video.+* **Text Scramble Effect** - Matrix-style decoding on load / hover.+* **Circular Text Path** - Text curving along spinning circle.+* **Gradient Stroke Animation** - Outlined text with running gradient.+* **Kinetic Typography Grid** - Letters dodging the cursor.++### Micro-Interactions & Effects+* **Particle Explosion Button** - CTA shatters into particles on success.+* **Liquid Pull-to-Refresh** - Reload indicator like detaching droplets.+* **Skeleton Shimmer** - Shifting light reflection across placeholders.+* **Directional Hover-Aware Button** - Fill enters from cursor's exact side.+* **Ripple Click Effect** - Wave from click coordinates.+* **Animated SVG Line Drawing** - Vectors drawing themselves in real time.+* **Mesh Gradient Background** - Organic lava-lamp blobs.+* **Lens Blur Depth** - Background UI blurred to focus foreground action.++### Animation Library Choice+* **Motion (`motion/react`)** - default for UI / Bento / state-change motion.+* **GSAP + ScrollTrigger** - for full-page scrolltelling and scroll hijacks. Isolate in dedicated leaf components with `useEffect` cleanup.+* **Three.js / WebGL** - for canvas backgrounds and 3D scenes. Same isolation rule.+* **NEVER mix GSAP / Three.js with Motion in the same component tree.** They fight over the same frames.diff --git a/.claude/skills/team-brief/SKILL.md b/.claude/skills/team-brief/SKILL.mdindex 1e2ee9b..b3c590f 100644--- a/.claude/skills/team-brief/SKILL.md+++ b/.claude/skills/team-brief/SKILL.md@@ -74,290 +74,25 @@ When `/daily-brief` is invoked, the orchestrator (main agent) should:**Launch ALL of these agents in a single message using the Task tool with `run_in_background: true`:**#### Agent 1: "github-analyst" (subagent_type: general-purpose)-```-Query GitHub for dev team activity on [CUSTOMIZE: your-org/your-repo].-Lookback start date: [INSERT LOOKBACK_DATE].-Today's date: [INSERT TODAY_DATE].-Brief type: [Daily Brief / Week Start Brief (Monday)]--Run these gh CLI commands (all date filters use LOOKBACK_DATE as the start):--1. PRs merged since lookback:- gh pr list --repo [CUSTOMIZE: your-org/your-repo] --state merged --search "merged:>=[LOOKBACK_DATE]" --json number,title,author,mergedAt,labels --limit 50--2. PRs opened since lookback:- gh pr list --repo [CUSTOMIZE: your-org/your-repo] --state open --search "created:>=[LOOKBACK_DATE]" --json number,title,author,createdAt,labels --limit 20--3. ALL open PRs (for stale PR detection):- gh pr list --repo [CUSTOMIZE: your-org/your-repo] --state open --json number,title,author,createdAt,reviewDecision,labels,updatedAt --limit 50--4. PR review comments since lookback (to cross-reference with Slack discussions):- gh api repos/[CUSTOMIZE: your-org/your-repo]/pulls/comments --jq '[.[] | select(.created_at >= "[LOOKBACK_DATE]")] | .[] | {pr_url: .pull_request_url, body: .body[0:200], user: .user.login, created_at: .created_at}'--5. Issues closed since lookback:- gh issue list --repo [CUSTOMIZE: your-org/your-repo] --state closed --search "closed:>=[LOOKBACK_DATE]" --json number,title,labels --limit 20--6. Issues opened since lookback:- gh issue list --repo [CUSTOMIZE: your-org/your-repo] --state open --search "created:>=[LOOKBACK_DATE]" --json number,title,labels --limit 20--7. Commits since lookback:- gh api repos/[CUSTOMIZE: your-org/your-repo]/commits --jq '[.[] | select(.commit.author.date >= "[LOOKBACK_DATE]")] | .[] | {sha: .sha[0:7], message: .commit.message | split("\n")[0], author: .commit.author.name, date: .commit.author.date}'--ANALYSIS REQUIRED — Don't just list data, provide insights:--A) **Stale PR Detection**: Flag any open PR created more than 3 days ago with no review decision or with CHANGES_REQUESTED for more than 2 days. Calculate days since creation/last update.--B) **Velocity Snapshot**: How many PRs merged, commits pushed, contributors active. If Monday (weekend window), note the multi-day period and don't compare to a single-day baseline — instead comment on weekend activity level (busy weekend vs. quiet weekend).--C) **Review Bottleneck**: Count PRs waiting for review (REVIEW_REQUIRED). If >5, flag as bottleneck.--D) **PR Comment Themes**: Summarize the key topics being discussed in PR reviews (architecture concerns, bugs, design patterns, etc.)--Return structured data AND insights.-```+Prompt: see `references/agent-prompts.md` § github-analyst.#### Agent 2: "slack-monitor" (subagent_type: general-purpose)*Only spawn if Slack MCP is available*-```-Check Slack [CUSTOMIZE: your-team-channel] channel for key discussions since [LOOKBACK_DATE].-Brief type: [Daily Brief / Week Start Brief (Monday)]-If Monday: cover Friday through Sunday — there may be more threads than usual.--Instructions:-1. Use ToolSearch to load Slack tools-2. Read recent messages from [CUSTOMIZE: your-team-channel] channel (get enough to cover since [LOOKBACK_DATE])-3. For each significant discussion thread, extract:- - Topic / what was discussed- - Decisions made or agreements reached- - Action items mentioned (who agreed to do what)- - Blockers raised- - Customer feedback or external links shared- - Any specific features, PRs, or technical topics referenced--CRITICAL: For each action item or decision, note:-- WHO is responsible-- WHAT they agreed to do-- Whether it references a specific PR, feature, or technical area--Also extract:-- Links shared (competitive intel, articles, tools)-- Questions that were asked but NOT answered-- Discussions that seemed unresolved--Return structured output with clear separation between:-1. Decisions & Agreements (with responsible person)-2. Action Items (with owner)-3. Blockers & Escalations-4. Unresolved Discussions-5. External Links & Intel Shared-6. Feature/Technical Topics Discussed (for cross-referencing with GitHub)-```+Prompt: see `references/agent-prompts.md` § slack-monitor.#### Agent 3: "meeting-reviewer" (subagent_type: general-purpose)-```-Check for meeting notes and standup notes since [LOOKBACK_DATE].-Brief type: [Daily Brief / Week Start Brief (Monday)]-If Monday: check Friday, Saturday, and Sunday for any meeting notes.--Instructions:-1. Look for meeting files in [CUSTOMIZE: path/to/meetings/] with dates from [LOOKBACK_DATE] through today-2. Use Glob to find files: [CUSTOMIZE: path/to/meetings/][LOOKBACK_DATE]*.md (and if Monday, also check Saturday and Sunday dates)-3. Also check [CUSTOMIZE: path/to/checkins/] for recent daily checkins-4. Read any found files--For each meeting/standup found, extract:-- Decisions made-- Action items assigned (WHO + WHAT)-- Features or changes discussed-- Priorities set-- Deadlines mentioned-- Any commitments like "I'll make a quick change to X" or "Let's update Y today"--Return structured list of:-1. Meeting summaries with date-2. All action items with owners-3. All discussed features/changes (for cross-referencing with GitHub PRs/commits and Linear issues)-4. Priorities and deadlines mentioned-```+Prompt: see `references/agent-prompts.md` § meeting-reviewer.#### Agent 4: "linear-tracker" (subagent_type: general-purpose)*Only spawn if Linear MCP is available*-```-Query Linear for work tracking data since [LOOKBACK_DATE].-Brief type: [Daily Brief / Week Start Brief (Monday)]-If Monday: cover Friday through Sunday.--=== CONTEXT OPTIMIZATION RULES (CRITICAL — reduces token usage by ~70%) ===--**DEFAULT FILTERS — apply to ALL list_issues calls:**-- ALWAYS exclude issues with state "Done", "Completed", "Canceled", or "Archived" UNLESS they were updated since [LOOKBACK_DATE] (i.e., only show recently-completed wins, not old closed work).-- ALWAYS set limit: 50 on any list call to prevent overflow.-- NEVER make redundant queries — if you already fetched issues updated since lookback, do NOT re-fetch the same issues in a separate "completed" query. Filter from the data you already have.--**DATA EXTRACTION — from every API response, extract ONLY these fields per issue:**-- identifier (e.g., [CUSTOMIZE: PROJ]-123)-- title-- state (name only)-- priority (number + label)-- assignee (name only)-- updatedAt-- project (name only)-- labels (names only)--Discard everything else (full descriptions, URLs, metadata blobs, nested objects). This is critical — raw Linear responses are 50-100KB each and most of that data is unused.--**QUERY CONSOLIDATION — use minimal API calls:**-Do NOT make 5+ separate list_issues calls. Instead:--Instructions:-1. Use ToolSearch to load Linear tools (search "+linear list issues", "+linear list initiatives", "+linear list milestones", "+linear list projects")-2. Query the following data using Linear MCP tools:-- === ISSUE-LEVEL DATA (2-3 calls max) ===-- a) Issues updated since lookback (THE main query — covers most needs):- Use mcp__claude_ai_Linear__list_issues with updatedAt: "[LOOKBACK_DATE]", limit: 50.- From this ONE response, extract: recently completed issues (wins), issues that moved to In Progress, issues still in Todo, new issues created.-- b) High-priority/urgent + blocked issues (only if not already captured above):- Use mcp__claude_ai_Linear__list_issues with priority: 1 (Urgent), limit: 30.- Only query this separately if the main query didn't surface urgent items.-- c) Blocked/stuck issues:- Look for issues with state "blocked" or "In Progress" with no updates in >2 days. Use the data from query (a) first — only make a separate query if needed.-- === CYCLE & SPRINT DATA (1 call) ===-- d) Current cycle progress:- Use mcp__claude_ai_Linear__list_teams to get team IDs, then mcp__claude_ai_Linear__list_cycles with type: "current" for each team. This shows sprint/cycle health.-- === INITIATIVE DATA (1-2 calls) ===-- e) All active initiatives:- Use mcp__claude_ai_Linear__list_initiatives with includeProjects: true to get initiative names, target dates, health status, progress, and linked projects.- Do NOT call get_initiative for each individual initiative — the list call with includeProjects gives enough data.-- === PROJECT DATA (SKIP separate call) ===-- f) Project data comes from the initiatives query above (includeProjects: true). Do NOT make a separate list_projects call — it returns ~37KB of mostly unused data.-- === MILESTONE DATA (1 call only if needed) ===-- g) Only query milestones if an initiative is At Risk or has an approaching target date (≤14 days). Otherwise skip — milestone data is verbose and rarely actionable day-to-day.--3. For each significant issue, note ONLY:- - Issue identifier, title, assignee name, status, priority, project name- - Whether it has linked PRs (just note yes/no + PR number, don't include full URLs)--4. Build an INITIATIVE HEALTH MAP from the data you already have (do NOT make additional queries):- For each initiative, compile:- - Total issues across linked projects (completed / in-progress / todo / blocked)- - Projects status breakdown- - Key blockers- - Days until target date--ANALYSIS REQUIRED:-A) **Cycle Health**: What % of the current cycle is complete? Are we on pace? How many issues remain vs. days left?-B) **Work Distribution**: Who has the most issues assigned? Anyone overloaded or idle?-C) **Blocked Items**: List anything stuck with reasons if available.-D) **Priority Mismatches**: Any urgent/high-priority issues with no recent activity? Flag them.-E) **New Work vs Planned**: How many issues were created since lookback vs. what was already planned in the cycle? Is scope creeping?-F) **Completed Work**: Celebrate — list what got done and by whom.-G) **Initiative Progress**: For each initiative, report health (on track / at risk / off track) based on:- - % of issues completed vs. days remaining to target date- - Number of blocked items- - Whether projects under the initiative are progressing-H) **Milestone Status**: Only flag milestones that are overdue or at risk. Skip healthy milestones.-I) **Project Rollup**: For each project, summarize progress % and whether it's contributing to initiative goals.--Return structured data AND insights, including the initiative health map.-IMPORTANT: Your total output should be under 5KB of text. Summarize, don't dump raw data.-```+Prompt: see `references/agent-prompts.md` § linear-tracker.#### Agent 5: "braindump-reviewer" (subagent_type: general-purpose)-```-Check for recent braindumps since [LOOKBACK_DATE].-Brief type: [Daily Brief / Week Start Brief (Monday)]-If Monday: check Friday through Sunday.--Instructions:-1. Use Glob to find braindump files matching recent dates:- - [CUSTOMIZE: path/to/braindumps/]braindump-[LOOKBACK_DATE through TODAY]*.md-2. Read any found files--For each braindump found, extract:-- Core themes and strategic thinking-- Decisions being considered or made-- Product direction signals-- Concerns or risks flagged-- Ideas that should be connected to current work-- Any references to specific features, PRs, or team members--Return structured list of:-1. Braindump summaries with date and source-2. Strategic insights and product direction signals-3. Concerns/risks that should appear in the brief-4. Connections to current engineering work (for cross-referencing with GitHub/Linear)-```+Prompt: see `references/agent-prompts.md` § braindump-reviewer.#### Agent 6: "posthog-analyst" (subagent_type: general-purpose)*Only spawn if PostHog MCP is available*-```-Query PostHog for HIGH-LEVEL product metrics only.-Project ID: [CUSTOMIZE: your-posthog-project-id], Dashboard ID: [CUSTOMIZE: your-posthog-dashboard-id].-Lookback start date: [INSERT LOOKBACK_DATE].-Today's date: [INSERT TODAY_DATE].-Brief type: [Daily Brief / Week Start Brief (Monday)]--=== CONTEXT OPTIMIZATION RULES (CRITICAL) ===-- DO NOT query for errors or error details. Skip list-errors entirely.-- DO NOT fetch insights-get-all (returns huge payload of all saved insights). Only use the dashboard.-- DO NOT include raw query results in your output. Summarize into 1-2 lines per metric.-- Your total output should be under 3KB of text.--Instructions:-1. Use ToolSearch to load PostHog tools (search "+posthog")-2. Run ONLY these queries:-- === DASHBOARD OVERVIEW (1 call) ===-- a) Get the main dashboard:- Use mcp__posthog__dashboard-get with dashboard_id: [CUSTOMIZE: your-posthog-dashboard-id].- Extract only: visitor count, signup count, core event count, and any trend data shown.-- === KEY METRICS (3 HogQL queries — combine into period comparison) ===-- b) Current period metrics (single combined query):- Use mcp__posthog__query-run with a HogQL query:- SELECT- countIf(DISTINCT person_id, event = '$pageview') as visitors,- countIf(event = '$pageview') as pageviews,- countIf(DISTINCT person_id, event = 'user_signed_up') as signups,- countIf(event = '[CUSTOMIZE: your_core_event]') as core_events,- countIf(DISTINCT person_id, event = '[CUSTOMIZE: your_core_event]') as core_event_users- FROM events- WHERE timestamp >= '[LOOKBACK_DATE]'-- c) Previous period metrics (for % change calculation):- Run the same query for the PREVIOUS equivalent period.- If daily: day before lookback. If Monday (Fri-Sun): previous Fri-Sun.-- d) Top features (lightweight):- Use mcp__posthog__query-run:- SELECT event, count() as count, count(DISTINCT person_id) as unique_users- FROM events- WHERE timestamp >= '[LOOKBACK_DATE]' AND event NOT LIKE '$%'- GROUP BY event ORDER BY count DESC LIMIT 10--ANALYSIS — Return ONLY high-level insights (no raw data dumps):--A) **Metric Summary**: 1 line each for visitors, sign-ups, core events with ↑↓→ trend and % change.-B) **Anomalies**: Only flag metrics with >20% change. If none, say "No anomalies."-C) **Top Features**: List top 5 features by usage, 1 line each.-D) **One-liner Assessment**: "Product health: [good/concerning/needs attention] — [why in 1 sentence]"--Return a concise summary, NOT raw query results. Target ~1KB output max.-```+Prompt: see `references/agent-prompts.md` § posthog-analyst.### Phase 3: Assembly & Cross-Reference Synthesis (Orchestrator — After All Agents Complete)@@ -522,27 +257,7 @@ The HackMD API token is stored in `.claude/settings/hackmd-token` (one line, no4. **If HackMD API fails**, log the error and continue — the brief should still be posted to Slack without the link. Note in the Slack message: "(HackMD link unavailable)"-**Implementation pattern (Bash):**-```bash-# Step 1: Create note-curl -s -X POST 'https://api.hackmd.io/v1/notes' \- -H "Authorization: Bearer $HACKMD_API_TOKEN" \- -H 'Content-Type: application/json' \- -d '{"title":"...","readPermission":"owner","writePermission":"owner","commentPermission":"disabled","content":"placeholder"}'--# Step 2: Prepare payload and update-python3 -c "-import json-with open('[CUSTOMIZE: path/to/briefs/]daily-brief-YYYY-MM-DD.md') as f:- content = f.read()-with open('/tmp/hackmd-payload.json', 'w') as f:- json.dump({'content': content}, f)-"-curl -s -X PATCH "https://api.hackmd.io/v1/notes/<id>" \- -H "Authorization: Bearer $HACKMD_API_TOKEN" \- -H 'Content-Type: application/json' \- -d @/tmp/hackmd-payload.json-```+**Implementation pattern (Bash):** see `references/publish-templates.md` § HackMD implementation pattern (Bash).### Phase 4: Slack Highlights (After brief is saved — preview before posting)@@ -556,79 +271,9 @@ After presenting the brief summary to the user, **always compose and show the Sl3. **Slack message format** (adapt based on actual content — this is a template, not a rigid format):-**For Monday (Week Start Brief):**-```-:calendar: *Week Start Brief — [DATE] (covering Fri–Sun)*--*Weekend recap:* [X] PRs merged since Friday. [Brief summary of what got done.] :rocket:--*What shipped:*-• [Feature/PR 1 with <https://github.com/[CUSTOMIZE: your-org/your-repo]/pull/XXX|#XXX> link] — [1-line description]-• [Feature/PR 2 with link] — [1-line description]-• [Feature/PR 3 with link] — [1-line description]-------:rotating_light: *Heads up:*-• [Most important alert with PR links and context]-• [Second alert — include who's involved and what's needed]-• [Third alert if relevant]-------:mag: *Key discussions from Slack:*-• *[Topic 1]:* [2-3 sentence summary of the discussion, decisions made, and any open questions.]-• *[Topic 2]:* [Summary with context]--:clipboard: *Open action items:*-• [Person] — [What they need to do] ([source: meeting/Slack thread])-• [Person] — [What they need to do]-------:bar_chart: *Product pulse:*-• [X] visitors ([↑/↓X%]), [X] sign-ups, [X] core events ([↑/↓X%]) | [Any notable anomaly]--:chart_with_upwards_trend: *This week's focus:*-• [Key priority or theme for the week]--:zap: *Quick wins:*-• <https://github.com/[CUSTOMIZE: your-org/your-repo]/pull/XXX|#XXX> and <...|#YYY> are approved — just need someone to merge.+**For Monday (Week Start Brief):** full template in `references/publish-templates.md` § Slack message format — Monday (Week Start Brief).-:link: *Full brief:* [HACKMD_PUBLISH_LINK]-```--**For regular days:**-```-:newspaper: *Daily Brief — [DATE]*--*What shipped:* [X] PRs merged. :rocket:-• [Feature/PR 1 with <https://github.com/[CUSTOMIZE: your-org/your-repo]/pull/XXX|#XXX> link] — [1-line description]-• [Feature/PR 2 with link] — [1-line description]-------:rotating_light: *Heads up:*-• [Alert 1 with PR links, context, and who needs to act]-• [Alert 2 with details]-------:mag: *Key discussions:*-• *[Topic]:* [2-3 sentence summary — what was discussed, any decisions, open questions.]--:clipboard: *Action items:*-• [Person] — [Task] ([from meeting/Slack])-------:bar_chart: *Product pulse:* [X] visitors ([↑/↓X%]) | [X] core events ([↑/↓X%]) | [Any notable anomaly]--:zap: *Quick wins:*-• <https://github.com/[CUSTOMIZE: your-org/your-repo]/pull/XXX|#XXX> and <...|#YYY> are approved — just need someone to merge.--:link: *Full brief:* [HACKMD_PUBLISH_LINK]-```+**For regular days:** full template in `references/publish-templates.md` § Slack message format — regular days.4. **Rules for the Slack message:**- Max 30 lines for Monday briefs, max 20 lines for regular days. More detail than before, but still scannable.@@ -755,65 +400,7 @@ Action items from recent meetings tracked against actual GitHub/Slack/Linear act---## Metadata Template-```yaml-----type: daily-brief-brief_type: daily / week-start # "week-start" if Monday, "daily" otherwise-domain: shared-date: YYYY-MM-DD-lookback_from: YYYY-MM-DD # Friday's date if Monday, yesterday otherwise-created: YYYY-MM-DD HH:MM-tags:- - daily-brief- - team-intelligence-data_sources:- github: true- slack: true/false- linear: true/false- posthog: true/false- meetings: true/false- braindumps: true/false-linear_sync:- issues_synced: X- prs_linked: X- initiative_updates_posted: X- milestones_flagged: X- errors: []-initiatives:- - name: "[CUSTOMIZE: Your Initiative 1]"- health: on_track / at_risk / off_track- progress_pct: X- days_remaining: X- projects_count: X- blocked_issues: X- - name: "[CUSTOMIZE: Your Initiative 2]"- health: on_track / at_risk / off_track- progress_pct: X- days_remaining: X- projects_count: X- blocked_issues: X-linear_cycle:- name: "Cycle X"- progress_pct: X- days_remaining: X- scope_changes: X # issues added mid-cycle-posthog_metrics:- visitors: X- visitors_change_pct: X # vs previous period- signups: X- signups_change_pct: X- core_events: X- core_events_change_pct: X- new_errors: X- top_feature: "feature_name"- anomalies: [] # list of metrics with >20% change-hackmd_url: "" # HackMD publish link, populated in Phase 3.7-stale_prs: X-review_bottleneck: true/false-missing_followups: X-linear_blocked_issues: X-----```+Full YAML frontmatter template for the saved brief file: `references/brief-frontmatter.md`.## Synthesis Rulesdiff --git a/.claude/skills/team-brief/references/agent-prompts.md b/.claude/skills/team-brief/references/agent-prompts.mdnew file mode 100644index 0000000..b6ad88d--- /dev/null+++ b/.claude/skills/team-brief/references/agent-prompts.md@@ -0,0 +1,286 @@+# Team Brief — Phase 2 Agent Prompts++Verbatim sub-agent prompts for the six Phase 2 parallel data-collection agents. Referenced from SKILL.md's `### Phase 2: Parallel Data Collection` section — read this file once you're ready to fill in and dispatch the actual Task calls.++## github-analyst+```+Query GitHub for dev team activity on [CUSTOMIZE: your-org/your-repo].+Lookback start date: [INSERT LOOKBACK_DATE].+Today's date: [INSERT TODAY_DATE].+Brief type: [Daily Brief / Week Start Brief (Monday)]++Run these gh CLI commands (all date filters use LOOKBACK_DATE as the start):++1. PRs merged since lookback:+ gh pr list --repo [CUSTOMIZE: your-org/your-repo] --state merged --search "merged:>=[LOOKBACK_DATE]" --json number,title,author,mergedAt,labels --limit 50++2. PRs opened since lookback:+ gh pr list --repo [CUSTOMIZE: your-org/your-repo] --state open --search "created:>=[LOOKBACK_DATE]" --json number,title,author,createdAt,labels --limit 20++3. ALL open PRs (for stale PR detection):+ gh pr list --repo [CUSTOMIZE: your-org/your-repo] --state open --json number,title,author,createdAt,reviewDecision,labels,updatedAt --limit 50++4. PR review comments since lookback (to cross-reference with Slack discussions):+ gh api repos/[CUSTOMIZE: your-org/your-repo]/pulls/comments --jq '[.[] | select(.created_at >= "[LOOKBACK_DATE]")] | .[] | {pr_url: .pull_request_url, body: .body[0:200], user: .user.login, created_at: .created_at}'++5. Issues closed since lookback:+ gh issue list --repo [CUSTOMIZE: your-org/your-repo] --state closed --search "closed:>=[LOOKBACK_DATE]" --json number,title,labels --limit 20++6. Issues opened since lookback:+ gh issue list --repo [CUSTOMIZE: your-org/your-repo] --state open --search "created:>=[LOOKBACK_DATE]" --json number,title,labels --limit 20++7. Commits since lookback:+ gh api repos/[CUSTOMIZE: your-org/your-repo]/commits --jq '[.[] | select(.commit.author.date >= "[LOOKBACK_DATE]")] | .[] | {sha: .sha[0:7], message: .commit.message | split("\n")[0], author: .commit.author.name, date: .commit.author.date}'++ANALYSIS REQUIRED — Don't just list data, provide insights:++A) **Stale PR Detection**: Flag any open PR created more than 3 days ago with no review decision or with CHANGES_REQUESTED for more than 2 days. Calculate days since creation/last update.++B) **Velocity Snapshot**: How many PRs merged, commits pushed, contributors active. If Monday (weekend window), note the multi-day period and don't compare to a single-day baseline — instead comment on weekend activity level (busy weekend vs. quiet weekend).++C) **Review Bottleneck**: Count PRs waiting for review (REVIEW_REQUIRED). If >5, flag as bottleneck.++D) **PR Comment Themes**: Summarize the key topics being discussed in PR reviews (architecture concerns, bugs, design patterns, etc.)++Return structured data AND insights.+```++## slack-monitor+```+Check Slack [CUSTOMIZE: your-team-channel] channel for key discussions since [LOOKBACK_DATE].+Brief type: [Daily Brief / Week Start Brief (Monday)]+If Monday: cover Friday through Sunday — there may be more threads than usual.++Instructions:+1. Use ToolSearch to load Slack tools+2. Read recent messages from [CUSTOMIZE: your-team-channel] channel (get enough to cover since [LOOKBACK_DATE])+3. For each significant discussion thread, extract:+ - Topic / what was discussed+ - Decisions made or agreements reached+ - Action items mentioned (who agreed to do what)+ - Blockers raised+ - Customer feedback or external links shared+ - Any specific features, PRs, or technical topics referenced++CRITICAL: For each action item or decision, note:+- WHO is responsible+- WHAT they agreed to do+- Whether it references a specific PR, feature, or technical area++Also extract:+- Links shared (competitive intel, articles, tools)+- Questions that were asked but NOT answered+- Discussions that seemed unresolved++Return structured output with clear separation between:+1. Decisions & Agreements (with responsible person)+2. Action Items (with owner)+3. Blockers & Escalations+4. Unresolved Discussions+5. External Links & Intel Shared+6. Feature/Technical Topics Discussed (for cross-referencing with GitHub)+```++## meeting-reviewer+```+Check for meeting notes and standup notes since [LOOKBACK_DATE].+Brief type: [Daily Brief / Week Start Brief (Monday)]+If Monday: check Friday, Saturday, and Sunday for any meeting notes.++Instructions:+1. Look for meeting files in [CUSTOMIZE: path/to/meetings/] with dates from [LOOKBACK_DATE] through today+2. Use Glob to find files: [CUSTOMIZE: path/to/meetings/][LOOKBACK_DATE]*.md (and if Monday, also check Saturday and Sunday dates)+3. Also check [CUSTOMIZE: path/to/checkins/] for recent daily checkins+4. Read any found files++For each meeting/standup found, extract:+- Decisions made+- Action items assigned (WHO + WHAT)+- Features or changes discussed+- Priorities set+- Deadlines mentioned+- Any commitments like "I'll make a quick change to X" or "Let's update Y today"++Return structured list of:+1. Meeting summaries with date+2. All action items with owners+3. All discussed features/changes (for cross-referencing with GitHub PRs/commits and Linear issues)+4. Priorities and deadlines mentioned+```++## linear-tracker+```+Query Linear for work tracking data since [LOOKBACK_DATE].+Brief type: [Daily Brief / Week Start Brief (Monday)]+If Monday: cover Friday through Sunday.++=== CONTEXT OPTIMIZATION RULES (CRITICAL — reduces token usage by ~70%) ===++**DEFAULT FILTERS — apply to ALL list_issues calls:**+- ALWAYS exclude issues with state "Done", "Completed", "Canceled", or "Archived" UNLESS they were updated since [LOOKBACK_DATE] (i.e., only show recently-completed wins, not old closed work).+- ALWAYS set limit: 50 on any list call to prevent overflow.+- NEVER make redundant queries — if you already fetched issues updated since lookback, do NOT re-fetch the same issues in a separate "completed" query. Filter from the data you already have.++**DATA EXTRACTION — from every API response, extract ONLY these fields per issue:**+- identifier (e.g., [CUSTOMIZE: PROJ]-123)+- title+- state (name only)+- priority (number + label)+- assignee (name only)+- updatedAt+- project (name only)+- labels (names only)++Discard everything else (full descriptions, URLs, metadata blobs, nested objects). This is critical — raw Linear responses are 50-100KB each and most of that data is unused.++**QUERY CONSOLIDATION — use minimal API calls:**+Do NOT make 5+ separate list_issues calls. Instead:++Instructions:+1. Use ToolSearch to load Linear tools (search "+linear list issues", "+linear list initiatives", "+linear list milestones", "+linear list projects")+2. Query the following data using Linear MCP tools:++ === ISSUE-LEVEL DATA (2-3 calls max) ===++ a) Issues updated since lookback (THE main query — covers most needs):+ Use mcp__claude_ai_Linear__list_issues with updatedAt: "[LOOKBACK_DATE]", limit: 50.+ From this ONE response, extract: recently completed issues (wins), issues that moved to In Progress, issues still in Todo, new issues created.++ b) High-priority/urgent + blocked issues (only if not already captured above):+ Use mcp__claude_ai_Linear__list_issues with priority: 1 (Urgent), limit: 30.+ Only query this separately if the main query didn't surface urgent items.++ c) Blocked/stuck issues:+ Look for issues with state "blocked" or "In Progress" with no updates in >2 days. Use the data from query (a) first — only make a separate query if needed.++ === CYCLE & SPRINT DATA (1 call) ===++ d) Current cycle progress:+ Use mcp__claude_ai_Linear__list_teams to get team IDs, then mcp__claude_ai_Linear__list_cycles with type: "current" for each team. This shows sprint/cycle health.++ === INITIATIVE DATA (1-2 calls) ===++ e) All active initiatives:+ Use mcp__claude_ai_Linear__list_initiatives with includeProjects: true to get initiative names, target dates, health status, progress, and linked projects.+ Do NOT call get_initiative for each individual initiative — the list call with includeProjects gives enough data.++ === PROJECT DATA (SKIP separate call) ===++ f) Project data comes from the initiatives query above (includeProjects: true). Do NOT make a separate list_projects call — it returns ~37KB of mostly unused data.++ === MILESTONE DATA (1 call only if needed) ===++ g) Only query milestones if an initiative is At Risk or has an approaching target date (≤14 days). Otherwise skip — milestone data is verbose and rarely actionable day-to-day.++3. For each significant issue, note ONLY:+ - Issue identifier, title, assignee name, status, priority, project name+ - Whether it has linked PRs (just note yes/no + PR number, don't include full URLs)++4. Build an INITIATIVE HEALTH MAP from the data you already have (do NOT make additional queries):+ For each initiative, compile:+ - Total issues across linked projects (completed / in-progress / todo / blocked)+ - Projects status breakdown+ - Key blockers+ - Days until target date++ANALYSIS REQUIRED:+A) **Cycle Health**: What % of the current cycle is complete? Are we on pace? How many issues remain vs. days left?+B) **Work Distribution**: Who has the most issues assigned? Anyone overloaded or idle?+C) **Blocked Items**: List anything stuck with reasons if available.+D) **Priority Mismatches**: Any urgent/high-priority issues with no recent activity? Flag them.+E) **New Work vs Planned**: How many issues were created since lookback vs. what was already planned in the cycle? Is scope creeping?+F) **Completed Work**: Celebrate — list what got done and by whom.+G) **Initiative Progress**: For each initiative, report health (on track / at risk / off track) based on:+ - % of issues completed vs. days remaining to target date+ - Number of blocked items+ - Whether projects under the initiative are progressing+H) **Milestone Status**: Only flag milestones that are overdue or at risk. Skip healthy milestones.+I) **Project Rollup**: For each project, summarize progress % and whether it's contributing to initiative goals.++Return structured data AND insights, including the initiative health map.+IMPORTANT: Your total output should be under 5KB of text. Summarize, don't dump raw data.+```++## braindump-reviewer+```+Check for recent braindumps since [LOOKBACK_DATE].+Brief type: [Daily Brief / Week Start Brief (Monday)]+If Monday: check Friday through Sunday.++Instructions:+1. Use Glob to find braindump files matching recent dates:+ - [CUSTOMIZE: path/to/braindumps/]braindump-[LOOKBACK_DATE through TODAY]*.md+2. Read any found files++For each braindump found, extract:+- Core themes and strategic thinking+- Decisions being considered or made+- Product direction signals+- Concerns or risks flagged+- Ideas that should be connected to current work+- Any references to specific features, PRs, or team members++Return structured list of:+1. Braindump summaries with date and source+2. Strategic insights and product direction signals+3. Concerns/risks that should appear in the brief+4. Connections to current engineering work (for cross-referencing with GitHub/Linear)+```++## posthog-analyst+```+Query PostHog for HIGH-LEVEL product metrics only.+Project ID: [CUSTOMIZE: your-posthog-project-id], Dashboard ID: [CUSTOMIZE: your-posthog-dashboard-id].+Lookback start date: [INSERT LOOKBACK_DATE].+Today's date: [INSERT TODAY_DATE].+Brief type: [Daily Brief / Week Start Brief (Monday)]++=== CONTEXT OPTIMIZATION RULES (CRITICAL) ===+- DO NOT query for errors or error details. Skip list-errors entirely.+- DO NOT fetch insights-get-all (returns huge payload of all saved insights). Only use the dashboard.+- DO NOT include raw query results in your output. Summarize into 1-2 lines per metric.+- Your total output should be under 3KB of text.++Instructions:+1. Use ToolSearch to load PostHog tools (search "+posthog")+2. Run ONLY these queries:++ === DASHBOARD OVERVIEW (1 call) ===++ a) Get the main dashboard:+ Use mcp__posthog__dashboard-get with dashboard_id: [CUSTOMIZE: your-posthog-dashboard-id].+ Extract only: visitor count, signup count, core event count, and any trend data shown.++ === KEY METRICS (3 HogQL queries — combine into period comparison) ===++ b) Current period metrics (single combined query):+ Use mcp__posthog__query-run with a HogQL query:+ SELECT+ countIf(DISTINCT person_id, event = '$pageview') as visitors,+ countIf(event = '$pageview') as pageviews,+ countIf(DISTINCT person_id, event = 'user_signed_up') as signups,+ countIf(event = '[CUSTOMIZE: your_core_event]') as core_events,+ countIf(DISTINCT person_id, event = '[CUSTOMIZE: your_core_event]') as core_event_users+ FROM events+ WHERE timestamp >= '[LOOKBACK_DATE]'++ c) Previous period metrics (for % change calculation):+ Run the same query for the PREVIOUS equivalent period.+ If daily: day before lookback. If Monday (Fri-Sun): previous Fri-Sun.++ d) Top features (lightweight):+ Use mcp__posthog__query-run:+ SELECT event, count() as count, count(DISTINCT person_id) as unique_users+ FROM events+ WHERE timestamp >= '[LOOKBACK_DATE]' AND event NOT LIKE '$%'+ GROUP BY event ORDER BY count DESC LIMIT 10++ANALYSIS — Return ONLY high-level insights (no raw data dumps):++A) **Metric Summary**: 1 line each for visitors, sign-ups, core events with ↑↓→ trend and % change.+B) **Anomalies**: Only flag metrics with >20% change. If none, say "No anomalies."+C) **Top Features**: List top 5 features by usage, 1 line each.+D) **One-liner Assessment**: "Product health: [good/concerning/needs attention] — [why in 1 sentence]"++Return a concise summary, NOT raw query results. Target ~1KB output max.+```diff --git a/.claude/skills/team-brief/references/brief-frontmatter.md b/.claude/skills/team-brief/references/brief-frontmatter.mdnew file mode 100644index 0000000..461dbf6--- /dev/null+++ b/.claude/skills/team-brief/references/brief-frontmatter.md@@ -0,0 +1,63 @@+# Team Brief — Metadata Template++Verbatim YAML frontmatter template for the saved daily-brief markdown file, referenced from SKILL.md's `## Metadata Template` heading.++```yaml+---+type: daily-brief+brief_type: daily / week-start # "week-start" if Monday, "daily" otherwise+domain: shared+date: YYYY-MM-DD+lookback_from: YYYY-MM-DD # Friday's date if Monday, yesterday otherwise+created: YYYY-MM-DD HH:MM+tags:+ - daily-brief+ - team-intelligence+data_sources:+ github: true+ slack: true/false+ linear: true/false+ posthog: true/false+ meetings: true/false+ braindumps: true/false+linear_sync:+ issues_synced: X+ prs_linked: X+ initiative_updates_posted: X+ milestones_flagged: X+ errors: []+initiatives:+ - name: "[CUSTOMIZE: Your Initiative 1]"+ health: on_track / at_risk / off_track+ progress_pct: X+ days_remaining: X+ projects_count: X+ blocked_issues: X+ - name: "[CUSTOMIZE: Your Initiative 2]"+ health: on_track / at_risk / off_track+ progress_pct: X+ days_remaining: X+ projects_count: X+ blocked_issues: X+linear_cycle:+ name: "Cycle X"+ progress_pct: X+ days_remaining: X+ scope_changes: X # issues added mid-cycle+posthog_metrics:+ visitors: X+ visitors_change_pct: X # vs previous period+ signups: X+ signups_change_pct: X+ core_events: X+ core_events_change_pct: X+ new_errors: X+ top_feature: "feature_name"+ anomalies: [] # list of metrics with >20% change+hackmd_url: "" # HackMD publish link, populated in Phase 3.7+stale_prs: X+review_bottleneck: true/false+missing_followups: X+linear_blocked_issues: X+---+```diff --git a/.claude/skills/team-brief/references/publish-templates.md b/.claude/skills/team-brief/references/publish-templates.mdnew file mode 100644index 0000000..c3ca9be--- /dev/null+++ b/.claude/skills/team-brief/references/publish-templates.md@@ -0,0 +1,99 @@+# Team Brief — Publish Templates++Verbatim implementation snippets for publishing the brief: the HackMD bash pattern (Phase 3.7) and the two Phase 4 Slack message templates (Monday week-start vs. regular day).++## HackMD implementation pattern (Bash)+```bash+# Step 1: Create note+curl -s -X POST 'https://api.hackmd.io/v1/notes' \+ -H "Authorization: Bearer $HACKMD_API_TOKEN" \+ -H 'Content-Type: application/json' \+ -d '{"title":"...","readPermission":"owner","writePermission":"owner","commentPermission":"disabled","content":"placeholder"}'++# Step 2: Prepare payload and update+python3 -c "+import json+with open('[CUSTOMIZE: path/to/briefs/]daily-brief-YYYY-MM-DD.md') as f:+ content = f.read()+with open('/tmp/hackmd-payload.json', 'w') as f:+ json.dump({'content': content}, f)+"+curl -s -X PATCH "https://api.hackmd.io/v1/notes/<id>" \+ -H "Authorization: Bearer $HACKMD_API_TOKEN" \+ -H 'Content-Type: application/json' \+ -d @/tmp/hackmd-payload.json+```++## Slack message format — Monday (Week Start Brief)+```+:calendar: *Week Start Brief — [DATE] (covering Fri–Sun)*++*Weekend recap:* [X] PRs merged since Friday. [Brief summary of what got done.] :rocket:++*What shipped:*+• [Feature/PR 1 with <https://github.com/[CUSTOMIZE: your-org/your-repo]/pull/XXX|#XXX> link] — [1-line description]+• [Feature/PR 2 with link] — [1-line description]+• [Feature/PR 3 with link] — [1-line description]++---++:rotating_light: *Heads up:*+• [Most important alert with PR links and context]+• [Second alert — include who's involved and what's needed]+• [Third alert if relevant]++---++:mag: *Key discussions from Slack:*+• *[Topic 1]:* [2-3 sentence summary of the discussion, decisions made, and any open questions.]+• *[Topic 2]:* [Summary with context]++:clipboard: *Open action items:*+• [Person] — [What they need to do] ([source: meeting/Slack thread])+• [Person] — [What they need to do]++---++:bar_chart: *Product pulse:*+• [X] visitors ([↑/↓X%]), [X] sign-ups, [X] core events ([↑/↓X%]) | [Any notable anomaly]++:chart_with_upwards_trend: *This week's focus:*+• [Key priority or theme for the week]++:zap: *Quick wins:*+• <https://github.com/[CUSTOMIZE: your-org/your-repo]/pull/XXX|#XXX> and <...|#YYY> are approved — just need someone to merge.++:link: *Full brief:* [HACKMD_PUBLISH_LINK]+```++## Slack message format — regular days+```+:newspaper: *Daily Brief — [DATE]*++*What shipped:* [X] PRs merged. :rocket:+• [Feature/PR 1 with <https://github.com/[CUSTOMIZE: your-org/your-repo]/pull/XXX|#XXX> link] — [1-line description]+• [Feature/PR 2 with link] — [1-line description]++---++:rotating_light: *Heads up:*+• [Alert 1 with PR links, context, and who needs to act]+• [Alert 2 with details]++---++:mag: *Key discussions:*+• *[Topic]:* [2-3 sentence summary — what was discussed, any decisions, open questions.]++:clipboard: *Action items:*+• [Person] — [Task] ([from meeting/Slack])++---++:bar_chart: *Product pulse:* [X] visitors ([↑/↓X%]) | [X] core events ([↑/↓X%]) | [Any notable anomaly]++:zap: *Quick wins:*+• <https://github.com/[CUSTOMIZE: your-org/your-repo]/pull/XXX|#XXX> and <...|#YYY> are approved — just need someone to merge.++:link: *Full brief:* [HACKMD_PUBLISH_LINK]+```diff --git a/.cursor-plugin/plugin.json b/.cursor-plugin/plugin.jsonindex cce0853..d62af4e 100644--- a/.cursor-plugin/plugin.json+++ b/.cursor-plugin/plugin.json@@ -1,7 +1,7 @@{"name": "cog-second-brain","displayName": "COG: Agentic Second Brain",- "version": "3.10.1",+ "version": "3.10.2","description": "Self-evolving second brain powered by AI agents, Obsidian markdown, and Git. 33 skills, 10 agents (6 workers + 4 read-only verifiers), people CRM with tiered enrichment. Closed-loop harness release: V-model verification lifecycle with criterion-traced evidence, risk lanes, multi-session ultragoals with a north-star acceptance gate, craft skills for writing and visuals, and paired anti-slop design skills for marketing and product UI. Works with Claude Code, Cursor, Kiro, Gemini CLI, and Codex.","author": {"name": "Huy Tieu",diff --git a/AGENTS.md b/AGENTS.mdindex 0fed850..9c00ff5 100644--- a/AGENTS.md+++ b/AGENTS.md@@ -43,6 +43,8 @@ This document defines the available commands/skills for AI agents interacting wi**Run this first** if you're new to COG.+**References:** `references/profile-templates.md` (the four profile document templates), `references/welcome-guide.md` (the WELCOME-TO-COG template).+---### /braindump@@ -169,6 +171,8 @@ This document defines the available commands/skills for AI agents interacting wi- Timeline: `05-knowledge/timeline/[topic]-evolution-YYYY-MM.md`- Reports: `05-knowledge/consolidated/consolidation-YYYY-MM-DD.md`+**References:** `references/templates.md` (all five consolidation document templates).+---### /url-dump@@ -254,6 +258,8 @@ This document defines the available commands/skills for AI agents interacting wi**Output location:** `03-professional/team-briefs/team-brief-YYYY-MM-DD.md`+**References:** `references/agent-prompts.md` (the six Phase-2 sub-agent prompts), `references/publish-templates.md` (HackMD + Slack payloads), `references/brief-frontmatter.md` (the metadata template).+---### /meeting-transcript@@ -585,6 +591,8 @@ The following 7 skills raise output quality on writing and visual work. They enc**Boundary:** Landing, portfolio, marketing, editorial. It hands off dashboards, data tables, and multi-step product UI to `/product-ui-taste`. Never run both on the same component.+**References:** `references/pattern-vocabulary.md`, `references/motion-skeletons.md`, `references/design-systems-install.md`, `references/canonical-sources.md`, `references/liquid-glass.md`.+---### /product-ui-taste@@ -608,6 +616,8 @@ The following 7 skills raise output quality on writing and visual work. They enc**Boundary:** The counterpart to `/taste-skill`. Maps to Carbon, Polaris, Atlaskit, Fluent, Primer, Material 3, Radix/shadcn, and Ant.+**References:** `references/block-skeletons.md`, `references/install-commands.md`, `references/canonical-sources.md`.+---### /no-ai-slopdiff --git a/CHANGELOG.md b/CHANGELOG.mdindex b706fbd..029f826 100644--- a/CHANGELOG.md+++ b/CHANGELOG.md@@ -2,6 +2,32 @@All notable changes to COG (Cognition + Obsidian + Git) will be documented in this file.+## [3.10.2] - 2026-08-18++### Changed++#### Oversized skill bodies split into bundled `references/`+Everything after a skill's frontmatter loads into context the moment the skill triggers. Five SKILL.md bodies ran past the 500-line figure in the Agent Skills best-practices guidance, the largest at 87 KB, so a task that never touched the appendix material paid for it anyway. Lookup tables and document templates now live in `references/` files the model reads only when it needs them, following the shape `museum-art`, `data-forms` and `editorial-illustrations` already use.++| skill | body before | body after |+|---|---|---|+| `knowledge-consolidation` | 870 | 293 |+| `onboarding` | 553 | 304 |+| `team-brief` | 886 | 473 |+| `product-ui-taste` | 649 | 515 |+| `taste-skill` | 1204 | 786 |++Every move is verbatim. `product-ui-taste` lands just above the guideline and `taste-skill` well above it: what remains in both is live instruction rather than lookup material, and condensing it would be an editorial rewrite with real behavioral risk, not a mechanical move. Stated plainly rather than forced under the number.++### Fixed++#### Bundled reference files now actually ship to installed users+`cog-update.sh` enumerates individual files in `FRAMEWORK_FILES`, and no `references/*.md` had ever been listed. The 13 files under `museum-art/references/`, `data-forms/references/` and `editorial-illustrations/references/` therefore never reached anyone who installed COG — `museum-art`'s own `## References` section pointed at files those users did not have. All 27 reference files are now registered.++**Existing installs: run `./cog-update.sh` twice for this release.** Your local copy of the updater carries the old `FRAMEWORK_FILES` array, so the first run delivers the trimmed skills and the new updater but not the reference files the new array names; the second run picks them up.++Reported in #29, with the measurements reproduced exactly.+## [3.10.1] - 2026-08-18### Fixeddiff --git a/COG-VERSION b/COG-VERSIONindex f870be2..7b59a5c 100644--- a/COG-VERSION+++ b/COG-VERSION@@ -1 +1 @@-3.10.1+3.10.2diff --git a/cog-update.sh b/cog-update.shindex fa68046..9f9ce62 100755--- a/cog-update.sh+++ b/cog-update.sh@@ -74,6 +74,35 @@ FRAMEWORK_FILES=(".claude/skills/taste-skill/SKILL.md"".claude/skills/product-ui-taste/SKILL.md"+ # Skill reference files (bundled lookup material, loaded on demand)+ ".claude/skills/data-forms/references/forms.md"+ ".claude/skills/editorial-illustrations/references/design-system.md"+ ".claude/skills/editorial-illustrations/references/elements.md"+ ".claude/skills/editorial-illustrations/references/worked-examples.md"+ ".claude/skills/knowledge-consolidation/references/templates.md"+ ".claude/skills/museum-art/references/_synthesis.md"+ ".claude/skills/museum-art/references/artic.md"+ ".claude/skills/museum-art/references/cleveland.md"+ ".claude/skills/museum-art/references/getty.md"+ ".claude/skills/museum-art/references/met.md"+ ".claude/skills/museum-art/references/nga.md"+ ".claude/skills/museum-art/references/rijksmuseum.md"+ ".claude/skills/museum-art/references/smithsonian.md"+ ".claude/skills/museum-art/references/smk.md"+ ".claude/skills/onboarding/references/profile-templates.md"+ ".claude/skills/onboarding/references/welcome-guide.md"+ ".claude/skills/product-ui-taste/references/block-skeletons.md"+ ".claude/skills/product-ui-taste/references/canonical-sources.md"+ ".claude/skills/product-ui-taste/references/install-commands.md"+ ".claude/skills/taste-skill/references/canonical-sources.md"+ ".claude/skills/taste-skill/references/design-systems-install.md"+ ".claude/skills/taste-skill/references/liquid-glass.md"+ ".claude/skills/taste-skill/references/motion-skeletons.md"+ ".claude/skills/taste-skill/references/pattern-vocabulary.md"+ ".claude/skills/team-brief/references/agent-prompts.md"+ ".claude/skills/team-brief/references/brief-frontmatter.md"+ ".claude/skills/team-brief/references/publish-templates.md"+# Role packs".claude/roles/_template.md"".claude/roles/product-manager.md"diff --git a/marketplace-entry.json b/marketplace-entry.jsonindex 4bed0be..ba9c429 100644--- a/marketplace-entry.json+++ b/marketplace-entry.json@@ -7,7 +7,7 @@"url": "https://github.com/huytieu"},"description": "Self-evolving second brain with 33 AI skills, 10 agents, and people CRM. Closed-loop harness release: V-model verification lifecycle with criterion-traced evidence, read-only verifier agents, risk lanes, multi-session ultragoals with a north-star acceptance gate, craft skills for writing and visuals, and paired anti-slop design skills for marketing and product UI. Inspired by Garry Tan's gstack and gbrain, and dwarves-kit. Works with Claude Code, Antigravity, Cursor, Kiro, Gemini CLI, Codex.",- "version": "3.10.1",+ "version": "3.10.2","keywords": ["second-brain","garry-tan",diff --git a/plugin.json b/plugin.jsonindex 30c75f2..8dc33d4 100644--- a/plugin.json+++ b/plugin.json@@ -1,7 +1,7 @@{"$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json","name": "cog-second-brain",- "version": "3.10.1",+ "version": "3.10.2","description": "Self-evolving second brain with 33 AI agent skills, 10 agents, and people CRM. Closed-loop harness: a V-model verification lifecycle (spec to evidence, criterion-traced checkpoints), read-only verifier agents that observe artifacts instead of trusting worker summaries, risk lanes, multi-session ultragoals with a north-star acceptance gate, plus craft skills for writing, visual work, and a paired anti-slop design system for marketing and product UI. Works with Claude Code, Antigravity, Cursor, Kiro, Gemini CLI, Codex, and any Agent Plugins conformant client.","author": {"name": "Huy Tieu",diff --git a/skills/knowledge-consolidation/SKILL.md b/skills/knowledge-consolidation/SKILL.mdindex 916737c..4180055 100644--- a/skills/knowledge-consolidation/SKILL.md+++ b/skills/knowledge-consolidation/SKILL.md@@ -139,608 +139,31 @@ Update and create knowledge base documents:#### Update Existing Frameworks-For each framework that needs updating:--```markdown-----type: "consolidated-knowledge"-domain: "[primary-domain]"-framework: "[framework-name]"-created: "[original-date]"-last_updated: "YYYY-MM-DD"-consolidation_id: "[consolidation-session-id]"-source_documents: [count]-status: "stable|working|emerging"-tags: ["#framework", "#consolidated", "#[topic]"]------# [Framework Name]--## Framework Overview-[Clear description of what this framework is and what it helps with]--**Status:** [Stable | Working | Emerging]-**Last Updated:** [Date]-**Source Insights:** [count] documents analyzed-------## Core Principles--### Principle 1: [Name]-**Statement:** [Clear, concise principle statement]--**Evidence:**-- [[braindump-YYYY-MM-DD]] - [supporting insight]-- [[daily-brief-YYYY-MM-DD]] - [supporting evidence]-- [[checkin-YYYY-MM-DD]] - [pattern observation]--**Evolution:** [How this principle has developed or been refined]--**Confidence:** [High|Medium|Low] - [reasoning]--### Principle 2: [Name]-[Same structure as Principle 1]--### Principle 3: [Name]-[Same structure as Principle 1]-------## Applications & Use Cases--### Use Case 1: [Scenario]-**When to Apply:** [Specific situation]--**How to Apply:**-1. [Step 1]-2. [Step 2]-3. [Step 3]--**Expected Outcomes:** [What to expect]--**Example:** [Real example from user's experience]--### Use Case 2: [Scenario]-[Same structure as Use Case 1]-------## Boundaries & Limitations--**This framework works when:**-- [Condition 1]-- [Condition 2]-- [Condition 3]--**This framework does NOT work when:**-- [Anti-condition 1]-- [Anti-condition 2]-- [Anti-condition 3]--**Common Pitfalls:**-- [Pitfall 1 to avoid]-- [Pitfall 2 to avoid]-------## Evolution & History--### [Date Range 1]: [Initial Development]-**What Emerged:** [How this framework first appeared]--**Catalysts:**-- [Event or insight that triggered initial thinking]--**Early Insights:**-- [[link]] - [early thought]-- [[link]] - [formative insight]--### [Date Range 2]: [Refinement Phase]-**What Changed:** [How framework evolved]--**New Evidence:**-- [[link]] - [supporting experience]-- [[link]] - [refining insight]--**Adjustments Made:**-- [Change 1]-- [Change 2]--### Current State: [Date]-**Current Understanding:** [Latest refined version]--**Recent Validation:**-- [[link]] - [recent application]-- [[link]] - [current evidence]-------## Related Frameworks--- [[framework-2]] - [How they relate]-- [[framework-3]] - [Connection or overlap]-- [[framework-4]] - [When to use which]-------## Future Development--**Questions for Deeper Exploration:**-- [Question 1 to investigate]-- [Question 2 needing more evidence]--**Potential Extensions:**-- [Area 1 for expansion]-- [Area 2 for integration]--**Watch For:**-- [Pattern 1 to monitor]-- [Signal 2 that might invalidate or refine]-------*Consolidated from [X] sources | Confidence: [High/Medium/Low] | Status: [Stable/Working/Emerging]*-```+For each framework that needs updating, use the consolidated-knowledge template in `references/templates.md`.Save to: `05-knowledge/consolidated/[framework-name]-framework.md`#### Create New Frameworks-For newly identified frameworks:--```markdown-----type: "consolidated-knowledge"-domain: "[primary-domain]"-framework: "[framework-name]"-created: "YYYY-MM-DD"-last_updated: "YYYY-MM-DD"-consolidation_id: "[consolidation-session-id]"-source_documents: [count]-status: "emerging"-tags: ["#framework", "#consolidated", "#new", "#[topic]"]------# [New Framework Name]--## Framework Discovery--**Identified:** [Date]-**Based On:** [X] insights from [timeframe]-**Domain:** [Primary domain with cross-domain applications]--**Discovery Context:**-[What pattern recognition revealed this framework]-------## Core Principles--[Same structure as framework updates above]-------[Continue with Applications, Boundaries, Evolution sections...]-```+For newly identified frameworks, use the new-framework template in `references/templates.md`.Save to: `05-knowledge/consolidated/[framework-name]-framework.md`#### Update Pattern Documentation-```markdown-----type: "pattern-analysis"-pattern: "[pattern-name]"-created: "YYYY-MM-DD"-domains: ["domain1", "domain2"]-frequency: "[high|medium|low]"-tags: ["#pattern", "#analysis"]------# Pattern: [Pattern Name]--## Pattern Description-[Clear description of the recurring pattern]--**Frequency:** Appeared in [X] documents over [timeframe]--**Domains:** [Which domains this pattern appears in]--**Significance:** [Why this pattern matters]-------## Occurrences--### [Date 1] - [[source-document-1]]-**Context:** [What was happening]--**Manifestation:** [How pattern appeared]--**Outcome:** [What resulted]--### [Date 2] - [[source-document-2]]-[Same structure]--### [Date 3] - [[source-document-3]]-[Same structure]-------## Analysis--**What Triggers This Pattern:**-- [Trigger 1]-- [Trigger 2]-- [Trigger 3]--**What Follows This Pattern:**-- [Consequence 1]-- [Consequence 2]--**Cross-Domain Implications:**-[How this pattern affects different areas]--**Potential Actions:**-- [Action to amplify if positive]-- [Action to mitigate if negative]-- [Action to understand better]-------## Evolution Over Time--[How this pattern has changed or stayed consistent]-------*Pattern identified through consolidation of [X] sources*-```+Document the pattern using the pattern template in `references/templates.md`.Save to: `05-knowledge/patterns/pattern-[name].md`#### Create Timeline Entries-```markdown-----type: "timeline-entry"-topic: "[major-theme-or-shift]"-date_range: "YYYY-MM-DD to YYYY-MM-DD"-created: "YYYY-MM-DD"-tags: ["#timeline", "#evolution", "#thinking"]------# Thinking Evolution: [Major Theme/Shift]--## Timeline Period-**From:** [Start Date]-**To:** [End Date]-**Duration:** [X weeks/months]-------## What Changed--**Initial State:**-[How thinking/approach started]--**End State:**-[Where thinking/approach ended up]--**Key Shift:**-[The fundamental change that occurred]-------## Catalysts & Triggers--### [Date] - [Trigger Event 1]-**Source:** [[link-to-document]]--**What Happened:** [Description]--**Impact:** [How this triggered change]--### [Date] - [Trigger Event 2]-[Same structure]-------## Evidence Trail--### Early Thinking: [Date Range]-- [[YYYY-MM-DD]] - [Initial thoughts]-- [[YYYY-MM-DD]] - [Early explorations]--### Intermediate Development: [Date Range]-- [[YYYY-MM-DD]] - [Evolving understanding]-- [[YYYY-MM-DD]] - [Testing and refinement]--### Current Understanding: [Date Range]-- [[YYYY-MM-DD]] - [Mature thinking]-- [[YYYY-MM-DD]] - [Latest application]-------## Impact of This Evolution--**On Decisions:**-[How this shift affects decision-making]--**On Strategies:**-[How this shift affects strategic approach]--**On Frameworks:**-[Which frameworks were created or updated]--**On Actions:**-[What changed in behavior or practice]-------## Lessons Learned--**What This Evolution Teaches:**-- [Learning 1]-- [Learning 2]-- [Learning 3]--**Future Implications:**-[What this suggests for future development]-------*Timeline constructed from [X] source documents spanning [timeframe]*-```+Build the timeline entry using the thinking-evolution template in `references/templates.md`.Save to: `05-knowledge/timeline/[topic]-evolution-YYYY-MM.md`### 5. Generate Consolidation Report-Create master consolidation document:--```markdown-----type: "knowledge-consolidation"-domain: "integrated"-date: "YYYY-MM-DD"-consolidation_period: "YYYY-MM-DD to YYYY-MM-DD"-created: "YYYY-MM-DD HH:MM"-sources_analyzed: [number]-frameworks_updated: ["framework1", "framework2"]-frameworks_created: ["new-framework1"]-patterns_identified: [number]-tags: ["#consolidation", "#knowledge", "#frameworks"]------# Knowledge Consolidation - [Date]--## Executive Summary--**Period Analyzed:** [Start date] to [End date]--**Documents Processed:**-- [X] braindumps-- [X] daily briefs-- [X] weekly check-ins-- [X] project documents--**Major Outcomes:**-- **Frameworks Updated:** [count] - [list]-- **New Frameworks Created:** [count] - [list]-- **Patterns Identified:** [count]-- **Timeline Entries:** [count]--**Key Insights Synthesized:**-1. [Major insight 1]-2. [Major insight 2]-3. [Major insight 3]-------## Processing Statistics--- **Total documents analyzed:** [number]-- **Date range:** [start] to [end]-- **Domains covered:** [list]-- **New patterns identified:** [number]-- **Frameworks updated:** [number]-- **New frameworks created:** [number]-- **Timeline entries added:** [number]-- **Archive actions taken:** [number]-------## Major Themes This Period--### Theme 1: [Name]-**Frequency:** Appeared in [X] documents--**Evolution:** [How thinking evolved]--**Key Insights:**-- [[source]] - [insight 1]-- [[source]] - [insight 2]-- [[source]] - [insight 3]--**Framework Implications:**-[How this theme affected or created frameworks]--**Status:** [Stable understanding | Still exploring | Needs more evidence]--### Theme 2: [Name]-[Same structure as Theme 1]-------## Frameworks Updated--### Framework 1: [Name]-**Location:** [[05-knowledge/consolidated/[filename]]]--**What Changed:**-- [Addition/modification 1]-- [Addition/modification 2]--**New Evidence Added:**-- [[source]] - [insight]-- [[source]] - [insight]--**Confidence Change:** [Before] → [After]--**New Applications:**-- [Use case 1]-- [Use case 2]--### Framework 2: [Name]-[Same structure]-------## New Frameworks Created--### New Framework: [Name]-**Location:** [[05-knowledge/consolidated/[filename]]]--**Created:** Based on [X] insights from [timeframe]--**Core Principles:**-1. [Principle 1]-2. [Principle 2]-3. [Principle 3]--**Primary Use Cases:**-- [Use case 1]-- [Use case 2]--**Status:** Emerging (needs more evidence and validation)--**Future Development:**-[What's needed to mature this framework]-------## Patterns Identified--### Pattern 1: [Name]-**Frequency:** [High|Medium|Low]--**Domains:** [Which domains]--**Description:** [What the pattern is]--**Implications:** [Why it matters]--**Documentation:** [[05-knowledge/patterns/[filename]]]--### Pattern 2: [Name]-[Same structure]-------## Thinking Evolution--### Major Shift: [Topic]-**Timeline:** [Date range]--**What Changed:** [Description]--**Catalysts:**-- [Event 1]-- [Event 2]--**Impact:**-[How this shift affects frameworks, decisions, actions]--**Documentation:** [[05-knowledge/timeline/[filename]]]-------## Cross-Cutting Insights--**Connections Across Domains:**-- [Cross-domain insight 1]-- [Cross-domain insight 2]-- [Cross-domain insight 3]--**Contradictions Identified:**-- [Contradiction 1] - [Resolution approach]-- [Contradiction 2] - [Still unresolved]--**Strategic Implications:**-[Higher-level observations about trajectory and direction]-------## Knowledge Base Maintenance--### Updates Made-- ✅ Updated framework: [name]-- ✅ Created new framework: [name]-- ✅ Documented pattern: [name]-- ✅ Added timeline entry: [topic]-- ✅ Archived outdated insights: [list]--### Archive Actions-**Braindumps Processed:**-- Updated metadata from `status: "captured"` to `status: "consolidated"`-- Added consolidation references: `consolidated_in: "[[consolidation-YYYY-MM-DD]]"`--**Superseded Content:**-- Archived: [list of old framework versions or outdated insights]-- Location: `00-inbox/archive/`-------## Future Consolidation Needs--### Ready for Framework Creation-- [ ] [Area 1] - Sufficient evidence gathered - Target: [date]-- [ ] [Area 2] - Pattern established - Target: [date]--### Needs Deeper Analysis-- [ ] [Area 3] - Contradictions to resolve - Target: [date]-- [ ] [Area 4] - Emerging but not yet clear - Target: [date]--### Monitoring Required-- [ ] [Pattern 1] - Watch for additional occurrences-- [ ] [Theme 2] - Track evolution over next [period]-------## Quality Assessment--**Completeness:** [All relevant insights processed?]--**Coherence:** [Frameworks logically consistent?]--**Traceability:** [Clear links to source material?]--**Actionability:** [Frameworks applicable to decisions?]--**Evolution Documented:** [Thinking progression captured?]-------## Next Steps--**Immediate Actions:**-- [Action 1 based on consolidation insights]-- [Action 2 to apply new frameworks]--**Future Consolidation:**-- **Next Consolidation:** [Suggested date]-- **Focus Areas:** [What to emphasize next time]--**Framework Applications:**-- [Decision 1 that could benefit from framework]-- [Situation 2 to apply framework to]-------*Consolidation completed: [Date] | Processed [X] documents | Created/updated [X] frameworks*-```+Create the master consolidation document using the report template in `references/templates.md`.Save to: `05-knowledge/consolidated/consolidation-YYYY-MM-DD.md`diff --git a/skills/knowledge-consolidation/references/templates.md b/skills/knowledge-consolidation/references/templates.mdnew file mode 100644index 0000000..cf40b79--- /dev/null+++ b/skills/knowledge-consolidation/references/templates.md@@ -0,0 +1,594 @@+# Knowledge Consolidation Templates++Templates referenced from `SKILL.md` for the knowledge-consolidation workflow. Each section below is used verbatim at its point of use in the skill.++## Update Existing Frameworks++```markdown+---+type: "consolidated-knowledge"+domain: "[primary-domain]"+framework: "[framework-name]"+created: "[original-date]"+last_updated: "YYYY-MM-DD"+consolidation_id: "[consolidation-session-id]"+source_documents: [count]+status: "stable|working|emerging"+tags: ["#framework", "#consolidated", "#[topic]"]+---++# [Framework Name]++## Framework Overview+[Clear description of what this framework is and what it helps with]++**Status:** [Stable | Working | Emerging]+**Last Updated:** [Date]+**Source Insights:** [count] documents analyzed++---++## Core Principles++### Principle 1: [Name]+**Statement:** [Clear, concise principle statement]++**Evidence:**+- [[braindump-YYYY-MM-DD]] - [supporting insight]+- [[daily-brief-YYYY-MM-DD]] - [supporting evidence]+- [[checkin-YYYY-MM-DD]] - [pattern observation]++**Evolution:** [How this principle has developed or been refined]++**Confidence:** [High|Medium|Low] - [reasoning]++### Principle 2: [Name]+[Same structure as Principle 1]++### Principle 3: [Name]+[Same structure as Principle 1]++---++## Applications & Use Cases++### Use Case 1: [Scenario]+**When to Apply:** [Specific situation]++**How to Apply:**+1. [Step 1]+2. [Step 2]+3. [Step 3]++**Expected Outcomes:** [What to expect]++**Example:** [Real example from user's experience]++### Use Case 2: [Scenario]+[Same structure as Use Case 1]++---++## Boundaries & Limitations++**This framework works when:**+- [Condition 1]+- [Condition 2]+- [Condition 3]++**This framework does NOT work when:**+- [Anti-condition 1]+- [Anti-condition 2]+- [Anti-condition 3]++**Common Pitfalls:**+- [Pitfall 1 to avoid]+- [Pitfall 2 to avoid]++---++## Evolution & History++### [Date Range 1]: [Initial Development]+**What Emerged:** [How this framework first appeared]++**Catalysts:**+- [Event or insight that triggered initial thinking]++**Early Insights:**+- [[link]] - [early thought]+- [[link]] - [formative insight]++### [Date Range 2]: [Refinement Phase]+**What Changed:** [How framework evolved]++**New Evidence:**+- [[link]] - [supporting experience]+- [[link]] - [refining insight]++**Adjustments Made:**+- [Change 1]+- [Change 2]++### Current State: [Date]+**Current Understanding:** [Latest refined version]++**Recent Validation:**+- [[link]] - [recent application]+- [[link]] - [current evidence]++---++## Related Frameworks++- [[framework-2]] - [How they relate]+- [[framework-3]] - [Connection or overlap]+- [[framework-4]] - [When to use which]++---++## Future Development++**Questions for Deeper Exploration:**+- [Question 1 to investigate]+- [Question 2 needing more evidence]++**Potential Extensions:**+- [Area 1 for expansion]+- [Area 2 for integration]++**Watch For:**+- [Pattern 1 to monitor]+- [Signal 2 that might invalidate or refine]++---++*Consolidated from [X] sources | Confidence: [High/Medium/Low] | Status: [Stable/Working/Emerging]*+```++## Create New Frameworks++```markdown+---+type: "consolidated-knowledge"+domain: "[primary-domain]"+framework: "[framework-name]"+created: "YYYY-MM-DD"+last_updated: "YYYY-MM-DD"+consolidation_id: "[consolidation-session-id]"+source_documents: [count]+status: "emerging"+tags: ["#framework", "#consolidated", "#new", "#[topic]"]+---++# [New Framework Name]++## Framework Discovery++**Identified:** [Date]+**Based On:** [X] insights from [timeframe]+**Domain:** [Primary domain with cross-domain applications]++**Discovery Context:**+[What pattern recognition revealed this framework]++---++## Core Principles++[Same structure as framework updates above]++---++[Continue with Applications, Boundaries, Evolution sections...]+```++## Update Pattern Documentation++```markdown+---+type: "pattern-analysis"+pattern: "[pattern-name]"+created: "YYYY-MM-DD"+domains: ["domain1", "domain2"]+frequency: "[high|medium|low]"+tags: ["#pattern", "#analysis"]+---++# Pattern: [Pattern Name]++## Pattern Description+[Clear description of the recurring pattern]++**Frequency:** Appeared in [X] documents over [timeframe]++**Domains:** [Which domains this pattern appears in]++**Significance:** [Why this pattern matters]++---++## Occurrences++### [Date 1] - [[source-document-1]]+**Context:** [What was happening]++**Manifestation:** [How pattern appeared]++**Outcome:** [What resulted]++### [Date 2] - [[source-document-2]]+[Same structure]++### [Date 3] - [[source-document-3]]+[Same structure]++---++## Analysis++**What Triggers This Pattern:**+- [Trigger 1]+- [Trigger 2]+- [Trigger 3]++**What Follows This Pattern:**+- [Consequence 1]+- [Consequence 2]++**Cross-Domain Implications:**+[How this pattern affects different areas]++**Potential Actions:**+- [Action to amplify if positive]+- [Action to mitigate if negative]+- [Action to understand better]++---++## Evolution Over Time++[How this pattern has changed or stayed consistent]++---++*Pattern identified through consolidation of [X] sources*+```++## Create Timeline Entries++```markdown+---+type: "timeline-entry"+topic: "[major-theme-or-shift]"+date_range: "YYYY-MM-DD to YYYY-MM-DD"+created: "YYYY-MM-DD"+tags: ["#timeline", "#evolution", "#thinking"]+---++# Thinking Evolution: [Major Theme/Shift]++## Timeline Period+**From:** [Start Date]+**To:** [End Date]+**Duration:** [X weeks/months]++---++## What Changed++**Initial State:**+[How thinking/approach started]++**End State:**+[Where thinking/approach ended up]++**Key Shift:**+[The fundamental change that occurred]++---++## Catalysts & Triggers++### [Date] - [Trigger Event 1]+**Source:** [[link-to-document]]++**What Happened:** [Description]++**Impact:** [How this triggered change]++### [Date] - [Trigger Event 2]+[Same structure]++---++## Evidence Trail++### Early Thinking: [Date Range]+- [[YYYY-MM-DD]] - [Initial thoughts]+- [[YYYY-MM-DD]] - [Early explorations]++### Intermediate Development: [Date Range]+- [[YYYY-MM-DD]] - [Evolving understanding]+- [[YYYY-MM-DD]] - [Testing and refinement]++### Current Understanding: [Date Range]+- [[YYYY-MM-DD]] - [Mature thinking]+- [[YYYY-MM-DD]] - [Latest application]++---++## Impact of This Evolution++**On Decisions:**+[How this shift affects decision-making]++**On Strategies:**+[How this shift affects strategic approach]++**On Frameworks:**+[Which frameworks were created or updated]++**On Actions:**+[What changed in behavior or practice]++---++## Lessons Learned++**What This Evolution Teaches:**+- [Learning 1]+- [Learning 2]+- [Learning 3]++**Future Implications:**+[What this suggests for future development]++---++*Timeline constructed from [X] source documents spanning [timeframe]*+```++## Generate Consolidation Report++```markdown+---+type: "knowledge-consolidation"+domain: "integrated"+date: "YYYY-MM-DD"+consolidation_period: "YYYY-MM-DD to YYYY-MM-DD"+created: "YYYY-MM-DD HH:MM"+sources_analyzed: [number]+frameworks_updated: ["framework1", "framework2"]+frameworks_created: ["new-framework1"]+patterns_identified: [number]+tags: ["#consolidation", "#knowledge", "#frameworks"]+---++# Knowledge Consolidation - [Date]++## Executive Summary++**Period Analyzed:** [Start date] to [End date]++**Documents Processed:**+- [X] braindumps+- [X] daily briefs+- [X] weekly check-ins+- [X] project documents++**Major Outcomes:**+- **Frameworks Updated:** [count] - [list]+- **New Frameworks Created:** [count] - [list]+- **Patterns Identified:** [count]+- **Timeline Entries:** [count]++**Key Insights Synthesized:**+1. [Major insight 1]+2. [Major insight 2]+3. [Major insight 3]++---++## Processing Statistics++- **Total documents analyzed:** [number]+- **Date range:** [start] to [end]+- **Domains covered:** [list]+- **New patterns identified:** [number]+- **Frameworks updated:** [number]+- **New frameworks created:** [number]+- **Timeline entries added:** [number]+- **Archive actions taken:** [number]++---++## Major Themes This Period++### Theme 1: [Name]+**Frequency:** Appeared in [X] documents++**Evolution:** [How thinking evolved]++**Key Insights:**+- [[source]] - [insight 1]+- [[source]] - [insight 2]+- [[source]] - [insight 3]++**Framework Implications:**+[How this theme affected or created frameworks]++**Status:** [Stable understanding | Still exploring | Needs more evidence]++### Theme 2: [Name]+[Same structure as Theme 1]++---++## Frameworks Updated++### Framework 1: [Name]+**Location:** [[05-knowledge/consolidated/[filename]]]++**What Changed:**+- [Addition/modification 1]+- [Addition/modification 2]++**New Evidence Added:**+- [[source]] - [insight]+- [[source]] - [insight]++**Confidence Change:** [Before] → [After]++**New Applications:**+- [Use case 1]+- [Use case 2]++### Framework 2: [Name]+[Same structure]++---++## New Frameworks Created++### New Framework: [Name]+**Location:** [[05-knowledge/consolidated/[filename]]]++**Created:** Based on [X] insights from [timeframe]++**Core Principles:**+1. [Principle 1]+2. [Principle 2]+3. [Principle 3]++**Primary Use Cases:**+- [Use case 1]+- [Use case 2]++**Status:** Emerging (needs more evidence and validation)++**Future Development:**+[What's needed to mature this framework]++---++## Patterns Identified++### Pattern 1: [Name]+**Frequency:** [High|Medium|Low]++**Domains:** [Which domains]++**Description:** [What the pattern is]++**Implications:** [Why it matters]++**Documentation:** [[05-knowledge/patterns/[filename]]]++### Pattern 2: [Name]+[Same structure]++---++## Thinking Evolution++### Major Shift: [Topic]+**Timeline:** [Date range]++**What Changed:** [Description]++**Catalysts:**+- [Event 1]+- [Event 2]++**Impact:**+[How this shift affects frameworks, decisions, actions]++**Documentation:** [[05-knowledge/timeline/[filename]]]++---++## Cross-Cutting Insights++**Connections Across Domains:**+- [Cross-domain insight 1]+- [Cross-domain insight 2]+- [Cross-domain insight 3]++**Contradictions Identified:**+- [Contradiction 1] - [Resolution approach]+- [Contradiction 2] - [Still unresolved]++**Strategic Implications:**+[Higher-level observations about trajectory and direction]++---++## Knowledge Base Maintenance++### Updates Made+- ✅ Updated framework: [name]+- ✅ Created new framework: [name]+- ✅ Documented pattern: [name]+- ✅ Added timeline entry: [topic]+- ✅ Archived outdated insights: [list]++### Archive Actions+**Braindumps Processed:**+- Updated metadata from `status: "captured"` to `status: "consolidated"`+- Added consolidation references: `consolidated_in: "[[consolidation-YYYY-MM-DD]]"`++**Superseded Content:**+- Archived: [list of old framework versions or outdated insights]+- Location: `00-inbox/archive/`++---++## Future Consolidation Needs++### Ready for Framework Creation+- [ ] [Area 1] - Sufficient evidence gathered - Target: [date]+- [ ] [Area 2] - Pattern established - Target: [date]++### Needs Deeper Analysis+- [ ] [Area 3] - Contradictions to resolve - Target: [date]+- [ ] [Area 4] - Emerging but not yet clear - Target: [date]++### Monitoring Required+- [ ] [Pattern 1] - Watch for additional occurrences+- [ ] [Theme 2] - Track evolution over next [period]++---++## Quality Assessment++**Completeness:** [All relevant insights processed?]++**Coherence:** [Frameworks logically consistent?]++**Traceability:** [Clear links to source material?]++**Actionability:** [Frameworks applicable to decisions?]++**Evolution Documented:** [Thinking progression captured?]++---++## Next Steps++**Immediate Actions:**+- [Action 1 based on consolidation insights]+- [Action 2 to apply new frameworks]++**Future Consolidation:**+- **Next Consolidation:** [Suggested date]+- **Focus Areas:** [What to emphasize next time]++**Framework Applications:**+- [Decision 1 that could benefit from framework]+- [Situation 2 to apply framework to]++---++*Consolidation completed: [Date] | Processed [X] documents | Created/updated [X] frameworks*+```diff --git a/skills/onboarding/SKILL.md b/skills/onboarding/SKILL.mdindex 5803157..7788548 100644--- a/skills/onboarding/SKILL.md+++ b/skills/onboarding/SKILL.md@@ -177,145 +177,15 @@ After role pack matching, set up the user's integration preferences:### 6. Generate Profile Documents-Create the following markdown files:+Create the four profile documents using the templates in `references/profile-templates.md`.#### `00-inbox/MY-PROFILE.md`-```markdown-----type: profile-created: YYYY-MM-DD-onboarding_completed: true-role_pack: [matched role_id or "custom"]-agent_mode: [solo or team, based on role pack suggestion]-tags: ["#profile", "#config", "#cog"]------# My COG Profile--## About Me-- **Name**: [Name]-- **Role**: [Job/role/main activity]-- **Role Pack**: [Display name from matched role pack, or "Custom" if no match]-- **Profile Created**: [Date]--## Settings-- **Agent Mode**: [solo/team] *(solo = handle everything directly; team = delegate to specialist sub-agents for deeper results)*--## Active Projects-[If they mentioned projects:]-- [[04-projects/[slug]/PROJECT-OVERVIEW|Project Name 1]]-- [[04-projects/[slug]/PROJECT-OVERVIEW|Project Name 2]]--[If no projects:]-*No active projects yet. Add them anytime by editing this file or running onboarding again.*--## Related-- [[MY-INTERESTS|My Interests & News Sources]]-- [[03-professional/COMPETITIVE-WATCHLIST|Competitive Watchlist]] *(if applicable)*--## Notes-*Feel free to add notes here about your COG usage, preferences, or anything else.*-------*Edit this file anytime to update your profile. COG reads it when you use skills.*-```#### `00-inbox/MY-INTERESTS.md`-```markdown-----type: interests-created: YYYY-MM-DD-tags: ["#interests", "#daily-brief", "#config"]------# My Interests & News Sources--*These topics guide my daily intelligence briefings.*--## Topics I'm Interested In-- [Topic 1]-- [Topic 2]-- [Topic 3]-- [Topic 4]-- [Topic 5]--## Preferred News Sources-[If sources were mentioned:]-*Where I like to get information:*-- [Source 1]-- [Source 2]-- [Source 3]--[If no sources mentioned:]-*No specific sources set. COG will search broadly for your topics. Add preferred sources here anytime.*--## Notes-*Add any additional context about your interests here.*-------*Update this file anytime as your interests evolve. Just edit and save—COG will pick up the changes.*-```#### `03-professional/COMPETITIVE-WATCHLIST.md` (only if they mentioned companies/people to track)-```markdown-----type: competitive-intelligence-created: YYYY-MM-DD-tags: ["#competitive", "#intelligence", "#tracking"]------# Competitive Watchlist--*Companies, people, or organizations I'm keeping an eye on.*--## Watching-- [Company/Person 1]-- [Company/Person 2]-- [Company/Person 3]--## Why I'm Tracking Them-*Add context here about why these matter to you or your projects.*-------*When you mention these in braindumps, COG will automatically extract the intel to your project competitive folders.*-```#### For Each Project: `04-projects/[project-slug]/PROJECT-OVERVIEW.md`-```markdown-----type: project-overview-project: [project-name]-slug: [project-slug]-created: YYYY-MM-DD-status: active-tags: ["#project", "#overview"]------# [Project Name]--## What is this project?-[Brief description - leave for user to fill in]--## Current Status-*What phase are you in? What's happening now?*--## Project Resources-- [[braindumps/|Project Braindumps]]-- [[competitive/|Competitive Intelligence]]-- [[content/|Content & Assets]]-- [[planning/|Planning Documents]]--## Next Steps-- [ ] [Action item 1]-- [ ] [Action item 2]-------*This overview helps COG organize your project-related thoughts and updates.*-```### 7. Create Directory StructureBased on configuration, create personalized structure:@@ -359,126 +229,7 @@ Based on configuration, create personalized structure:Generate: `00-inbox/WELCOME-TO-COG.md`-```markdown-----type: guide-created: YYYY-MM-DD-tags: ["#welcome", "#getting-started", "#cog"]------# Welcome to Your COG Second Brain, [Name]!--Your COG is now personalized and ready to use. Here's how to get started:--## Your Profile Documents--I've created these documents to store your preferences:--- **[[MY-PROFILE]]** - Your basic info, role pack, and workflow preferences-- **[[MY-INTERESTS]]** - Topics for your daily briefs-- **[[MY-INTEGRATIONS]]** - Your active and disabled integrations-- **[[03-professional/COMPETITIVE-WATCHLIST]]** - Companies you're tracking *(if applicable)*--**You can edit these files anytime.** COG reads them when you use skills, so your changes take effect immediately.--## Skills for Your Role--[If role pack was matched:]-As a **[Role Display Name]**, these skills are ordered by relevance for you:--[List skills from role pack in order, with brief "why it matters" from the role pack. Format as:]-1. **[skill-name]** — [Role-specific explanation]-2. **[skill-name]** — [Role-specific explanation]-[...continue for all recommended skills]--[If no role pack match:]-Here are COG's core skills available to everyone:--1. **daily-brief** — Personalized news intelligence-2. **braindump** — Capture and classify thoughts-3. **weekly-checkin** — Weekly pattern analysis-4. **knowledge-consolidation** — Build frameworks from scattered notes-5. **url-dump** — Save URLs with auto-extracted insights-6. **update-cog** — Keep COG framework current--## Your Integrations--[If integrations were configured:]-**Active**: [List active integrations]-**Disabled**: [List disabled integrations]--You can change these anytime by editing [[MY-INTEGRATIONS]].--[If no integrations configured:]-No integrations configured yet. COG works great standalone — add integrations anytime by editing `00-inbox/MY-INTEGRATIONS.md`.--## Quick Start--### 1. Daily Morning Routine-Invoke the daily-brief skill to get your personalized intelligence briefing covering:-[List their selected interest areas]--### 2. Capture Your Thoughts-Use the braindump skill to quickly capture ideas, insights, and thoughts. Your braindumps will automatically be categorized into:-[List their focus domains]--Choose from your active projects:-[List their projects with links]--### 3. Weekly Reflection-Every week, use the weekly-checkin skill to review your week's insights and patterns.--## Your Active Projects--[If they have projects]-You're tracking these projects:-- [[04-projects/[slug]/PROJECT-OVERVIEW|Project 1]]-- [[04-projects/[slug]/PROJECT-OVERVIEW|Project 2]]--When you use the braindump skill, select the project to automatically file your thoughts in the right place.--## How COG Uses Your Profile--**Daily Briefs**: Uses [[MY-INTERESTS]] to curate relevant news-**Braindumps**: Offers your projects from [[MY-PROFILE]] as options-**Competitive Intel**: Auto-extracts mentions of companies in [[COMPETITIVE-WATCHLIST]]-**Weekly Check-ins**: Reviews progress across your domains--## Next Steps--1. **Try your first braindump**: Use the braindump skill and start writing-2. **Get your daily brief**: Invoke the daily-brief skill to see curated intelligence-3. **Explore your vault**: All your files are organized in the sidebar-4. **Edit your profile**: Open [[MY-PROFILE]] and customize anytime--## Keeping COG Updated--COG separates your content from framework files. When new versions are released:-- Run `/update-cog` to check for and apply updates-- Or use the shell script: `./cog-update.sh --check`-- Your braindumps, profiles, and notes are **never** touched by updates--Check your current version: `cat COG-VERSION`--## Tips for Success--- **Don't overthink it**: Just dump your thoughts, COG will help organize-- **Be consistent**: Daily briefs and braindumps work best as habits-- **Review weekly**: Use the weekly-checkin skill to see patterns emerge-- **Evolve your setup**: Edit your profile files anytime or run onboarding again to add projects-- **Stay updated**: Run `/update-cog` periodically to get new skills and improvements--## Getting Help--- Check `SETUP.md` for detailed guides-- Visit the GitHub repo for documentation--**Your second brain is learning about you. Let's begin!**-------*You can archive or delete this welcome guide once you're comfortable with COG.*-```+Generate it from the template in `references/welcome-guide.md`.### 9. Wrap-Up (No Menu!)After setup, summarize what was created and suggest a natural next action:diff --git a/skills/onboarding/references/profile-templates.md b/skills/onboarding/references/profile-templates.mdnew file mode 100644index 0000000..dee6664--- /dev/null+++ b/skills/onboarding/references/profile-templates.md@@ -0,0 +1,145 @@+# Profile document templates++Verbatim markdown templates for the four documents created in onboarding Step 6 (Generate Profile Documents). Fill in the bracketed placeholders when generating each file.++## `00-inbox/MY-PROFILE.md`++```markdown+---+type: profile+created: YYYY-MM-DD+onboarding_completed: true+role_pack: [matched role_id or "custom"]+agent_mode: [solo or team, based on role pack suggestion]+tags: ["#profile", "#config", "#cog"]+---++# My COG Profile++## About Me+- **Name**: [Name]+- **Role**: [Job/role/main activity]+- **Role Pack**: [Display name from matched role pack, or "Custom" if no match]+- **Profile Created**: [Date]++## Settings+- **Agent Mode**: [solo/team] *(solo = handle everything directly; team = delegate to specialist sub-agents for deeper results)*++## Active Projects+[If they mentioned projects:]+- [[04-projects/[slug]/PROJECT-OVERVIEW|Project Name 1]]+- [[04-projects/[slug]/PROJECT-OVERVIEW|Project Name 2]]++[If no projects:]+*No active projects yet. Add them anytime by editing this file or running onboarding again.*++## Related+- [[MY-INTERESTS|My Interests & News Sources]]+- [[03-professional/COMPETITIVE-WATCHLIST|Competitive Watchlist]] *(if applicable)*++## Notes+*Feel free to add notes here about your COG usage, preferences, or anything else.*++---++*Edit this file anytime to update your profile. COG reads it when you use skills.*+```++## `00-inbox/MY-INTERESTS.md`++```markdown+---+type: interests+created: YYYY-MM-DD+tags: ["#interests", "#daily-brief", "#config"]+---++# My Interests & News Sources++*These topics guide my daily intelligence briefings.*++## Topics I'm Interested In+- [Topic 1]+- [Topic 2]+- [Topic 3]+- [Topic 4]+- [Topic 5]++## Preferred News Sources+[If sources were mentioned:]+*Where I like to get information:*+- [Source 1]+- [Source 2]+- [Source 3]++[If no sources mentioned:]+*No specific sources set. COG will search broadly for your topics. Add preferred sources here anytime.*++## Notes+*Add any additional context about your interests here.*++---++*Update this file anytime as your interests evolve. Just edit and save—COG will pick up the changes.*+```++## `03-professional/COMPETITIVE-WATCHLIST.md` (only if they mentioned companies/people to track)++```markdown+---+type: competitive-intelligence+created: YYYY-MM-DD+tags: ["#competitive", "#intelligence", "#tracking"]+---++# Competitive Watchlist++*Companies, people, or organizations I'm keeping an eye on.*++## Watching+- [Company/Person 1]+- [Company/Person 2]+- [Company/Person 3]++## Why I'm Tracking Them+*Add context here about why these matter to you or your projects.*++---++*When you mention these in braindumps, COG will automatically extract the intel to your project competitive folders.*+```++## For Each Project: `04-projects/[project-slug]/PROJECT-OVERVIEW.md`++```markdown+---+type: project-overview+project: [project-name]+slug: [project-slug]+created: YYYY-MM-DD+status: active+tags: ["#project", "#overview"]+---++# [Project Name]++## What is this project?+[Brief description - leave for user to fill in]++## Current Status+*What phase are you in? What's happening now?*++## Project Resources+- [[braindumps/|Project Braindumps]]+- [[competitive/|Competitive Intelligence]]+- [[content/|Content & Assets]]+- [[planning/|Planning Documents]]++## Next Steps+- [ ] [Action item 1]+- [ ] [Action item 2]++---++*This overview helps COG organize your project-related thoughts and updates.*+```diff --git a/skills/onboarding/references/welcome-guide.md b/skills/onboarding/references/welcome-guide.mdnew file mode 100644index 0000000..278e9b6--- /dev/null+++ b/skills/onboarding/references/welcome-guide.md@@ -0,0 +1,124 @@+# Welcome guide template++Verbatim markdown template for `00-inbox/WELCOME-TO-COG.md`, generated in onboarding Step 8 (Create Welcome Guide).++```markdown+---+type: guide+created: YYYY-MM-DD+tags: ["#welcome", "#getting-started", "#cog"]+---++# Welcome to Your COG Second Brain, [Name]!++Your COG is now personalized and ready to use. Here's how to get started:++## Your Profile Documents++I've created these documents to store your preferences:++- **[[MY-PROFILE]]** - Your basic info, role pack, and workflow preferences+- **[[MY-INTERESTS]]** - Topics for your daily briefs+- **[[MY-INTEGRATIONS]]** - Your active and disabled integrations+- **[[03-professional/COMPETITIVE-WATCHLIST]]** - Companies you're tracking *(if applicable)*++**You can edit these files anytime.** COG reads them when you use skills, so your changes take effect immediately.++## Skills for Your Role++[If role pack was matched:]+As a **[Role Display Name]**, these skills are ordered by relevance for you:++[List skills from role pack in order, with brief "why it matters" from the role pack. Format as:]+1. **[skill-name]** — [Role-specific explanation]+2. **[skill-name]** — [Role-specific explanation]+[...continue for all recommended skills]++[If no role pack match:]+Here are COG's core skills available to everyone:++1. **daily-brief** — Personalized news intelligence+2. **braindump** — Capture and classify thoughts+3. **weekly-checkin** — Weekly pattern analysis+4. **knowledge-consolidation** — Build frameworks from scattered notes+5. **url-dump** — Save URLs with auto-extracted insights+6. **update-cog** — Keep COG framework current++## Your Integrations++[If integrations were configured:]+**Active**: [List active integrations]+**Disabled**: [List disabled integrations]++You can change these anytime by editing [[MY-INTEGRATIONS]].++[If no integrations configured:]+No integrations configured yet. COG works great standalone — add integrations anytime by editing `00-inbox/MY-INTEGRATIONS.md`.++## Quick Start++### 1. Daily Morning Routine+Invoke the daily-brief skill to get your personalized intelligence briefing covering:+[List their selected interest areas]++### 2. Capture Your Thoughts+Use the braindump skill to quickly capture ideas, insights, and thoughts. Your braindumps will automatically be categorized into:+[List their focus domains]++Choose from your active projects:+[List their projects with links]++### 3. Weekly Reflection+Every week, use the weekly-checkin skill to review your week's insights and patterns.++## Your Active Projects++[If they have projects]+You're tracking these projects:+- [[04-projects/[slug]/PROJECT-OVERVIEW|Project 1]]+- [[04-projects/[slug]/PROJECT-OVERVIEW|Project 2]]++When you use the braindump skill, select the project to automatically file your thoughts in the right place.++## How COG Uses Your Profile++**Daily Briefs**: Uses [[MY-INTERESTS]] to curate relevant news+**Braindumps**: Offers your projects from [[MY-PROFILE]] as options+**Competitive Intel**: Auto-extracts mentions of companies in [[COMPETITIVE-WATCHLIST]]+**Weekly Check-ins**: Reviews progress across your domains++## Next Steps++1. **Try your first braindump**: Use the braindump skill and start writing+2. **Get your daily brief**: Invoke the daily-brief skill to see curated intelligence+3. **Explore your vault**: All your files are organized in the sidebar+4. **Edit your profile**: Open [[MY-PROFILE]] and customize anytime++## Keeping COG Updated++COG separates your content from framework files. When new versions are released:+- Run `/update-cog` to check for and apply updates+- Or use the shell script: `./cog-update.sh --check`+- Your braindumps, profiles, and notes are **never** touched by updates++Check your current version: `cat COG-VERSION`++## Tips for Success++- **Don't overthink it**: Just dump your thoughts, COG will help organize+- **Be consistent**: Daily briefs and braindumps work best as habits+- **Review weekly**: Use the weekly-checkin skill to see patterns emerge+- **Evolve your setup**: Edit your profile files anytime or run onboarding again to add projects+- **Stay updated**: Run `/update-cog` periodically to get new skills and improvements++## Getting Help++- Check `SETUP.md` for detailed guides+- Visit the GitHub repo for documentation++**Your second brain is learning about you. Let's begin!**++---++*You can archive or delete this welcome guide once you're comfortable with COG.*+```diff --git a/skills/product-ui-taste/SKILL.md b/skills/product-ui-taste/SKILL.mdindex c5b5926..6e8064d 100644--- a/skills/product-ui-taste/SKILL.md+++ b/skills/product-ui-taste/SKILL.md@@ -405,52 +405,7 @@ When the Product Read matches one of these, scaffold the whole skeleton, not a f- **Dashboard/overview**: KPI tile row (Cards) + widget grid + one or two drill-in Tables (rows).- **Admin console with bulk actions**: table + selection persistence + bulk action bar (capped at 5 + overflow) + confirmation dialogs.-### 12.A Block Library (reference implementations)-Full component implementations live in the host system, not duplicated here: reach them via your host system's template/skeleton command or its docs (Appendix B). Three high-value skeletons are worked below because they encode the contracts most often gotten wrong; treat them as the canonical shape, adapt to the host system.--**Block 1 - Index + detail-drawer (frame-first):**-```tsx-// Budget the frame first: nav 256 | table flex | inspector 380-<AppShell sideNav={<SideNav>{/* nav */}</SideNav>} contentPadding={0}>- <Layout>- <LayoutContent>- <ToolbarTableFilter /* search + status/priority filters + overflow (cap 5) */ />- {/* applied-filter chips row + Clear all (Section 7.F) */}- <Table- plugins={[useTableStickyColumns, useTableColumnResize /*, pagination */]}- /* selection persists by row id across page/sort/filter (Section 7.E) */- />- {/* pagination footer; three empty states + ErrorState wired per Section 6 */}- </LayoutContent>- <LayoutPanel width={380} resizable={{minSizePx: 320, maxSizePx: 480}} hasDivider isScrollable>- {selected ? <DetailFields item={selected} /> : <EmptyState title="Nothing selected" />}- </LayoutPanel>- </Layout>-</AppShell>-// Below ~1024px: LayoutPanel overlays Content; SideNav becomes MobileNav.-```--**Block 2 - Table scroll + sticky header + frozen column (the CSS contract a system's hooks satisfy):**-```css-/* ONE wrapper owns both scroll axes; page body never scrolls sideways (Section 4). */-.table-scroll { overflow: auto; max-block-size: 70vh; } /* bounded height => sticky works */-.table-scroll thead th { position: sticky; inset-block-start: 0; z-index: 20; }-/* Frozen first column: sticky + offset + z + SOLID THEME-TOKEN bg + shadow divider, never border */-.col-frozen {- position: sticky; inset-inline-start: 0; z-index: 10;- background: var(--color-surface); /* must also cover hover/selected rows */- box-shadow: inset -1px 0 0 var(--color-border); /* not border-right (double-renders on scroll) */-}-```--**Block 3 - Truncation contract (single-line + multi-line):**-```css-.cell { min-inline-size: 0; } /* required on EVERY flex ancestor or ellipsis no-ops */-.cell .text { overflow: hidden; text-overflow: ellipsis; white-space: nowrap; }-.clamp { /* all four props; NO padding on this node */- display: -webkit-box; -webkit-line-clamp: 2; -webkit-box-orient: vertical; overflow: hidden;-}-```+Full component implementations live in the host system, not duplicated here: reach them via your host system's template/skeleton command or its docs (`references/canonical-sources.md`). Three high-value skeletons are worked in `references/block-skeletons.md` because they encode the contracts most often gotten wrong; treat them as the canonical shape, adapt to the host system.---@@ -557,97 +512,8 @@ If a single box cannot be honestly ticked, fix it before delivering.----# APPENDICES - Source-Backed Reference Material--## Appendix A - Install / CLI per system--```bash-# House design system - resolve the real API before writing UI.-# Most systems ship a CLI or a docs site; use whichever exists.-# 1. find the closest shipped page/block template-# 2. study its layout skeleton-# 3. read real props for every component (never invent props)--# IBM Carbon-npm install @carbon/react @carbon/styles-# Microsoft Fluent UI React v9-npm install @fluentui/react-components-# Atlassian Atlaskit (per-component + tokens)-npm install @atlaskit/tokens @atlaskit/dynamic-table-# Shopify Polaris-npm install @shopify/polaris-# GitHub Primer React-npm install @primer/react styled-components-# Radix Primitives + shadcn/ui + TanStack Table-npm install @radix-ui/react-dialog @radix-ui/react-toast @tanstack/react-table-npx shadcn@latest add table dialog-# Material Web (Material 3)-npm install @material/web-# Ant Design / Mantine + Mantine React Table-npm install antd-npm install @mantine/core @mantine/form mantine-react-table-```--## Appendix B - Canonical sources (real URLs, gsearch-verified)--Consolidated primary sources:--**Frame / layout**-- Carbon 2x grid: https://carbondesignsystem.com/elements/2x-grid/usage/-- Primer PageLayout: https://primer.style/product/components/page-layout-- Material 3 canonical layouts: https://m3.material.io/foundations/adaptive-design/canonical-layouts-- Material 3 list-detail: https://m3.material.io/foundations/layout/canonical-examples/list-detail-- Material 3 supporting-pane: https://m3.material.io/foundations/layout/canonical-examples/supporting-pane-- Container queries: https://www.joshwcomeau.com/css/container-queries-unleashed/--**Overflow / truncation**-- Carbon overflow content: https://carbondesignsystem.com/patterns/overflow-content/-- Primer Truncate: https://primer.style/product/components/truncate/-- CSS line-clamp: https://css-tricks.com/line-clampin/--**State matrix**-- Polaris EmptyState: https://polaris-react.shopify.com/components/layout-and-structure/empty-state-- Carbon empty states: https://carbondesignsystem.com/patterns/empty-states-pattern/-- Carbon loading: https://carbondesignsystem.com/patterns/loading-pattern/-- Primer empty states: https://primer.style/product/ui-patterns/empty-states/-- NN/g skeleton screens: https://www.nngroup.com/articles/skeleton-screens/-- NN/g empty-state design: https://www.nngroup.com/articles/empty-state-interface-design/-- Pencil&Paper empty states: https://www.pencilandpaper.io/articles/empty-states-- Polaris error messages: https://polaris-react.shopify.com/content/error-messages--**Data table**-- Carbon data table: https://carbondesignsystem.com/components/data-table/usage/-- Polaris IndexTable: https://polaris-react.shopify.com/components/tables/index-table-- Ant table scroll: https://ant.design/docs/blog/table-scroll-ghost/-- Ant virtual table: https://ant.design/docs/blog/virtual-table/-- TanStack column sizing: https://tanstack.com/table/latest/docs/guide/column-sizing-- Mantine React Table column pinning: https://www.mantine-react-table.com/docs/guides/column-pinning-- NN/g infinite scroll: https://www.nngroup.com/articles/infinite-scrolling-tips/-- Baymard checkout linear / pagination context: https://baymard.com/blog/checkout-process-should-be-linear-- Pagination vs infinite vs load-more: https://www.smashingmagazine.com/2016/03/pagination-infinite-scrolling-load-more-buttons/--**Forms / flows**-- LukeW web form design: https://www.lukew.com/ff/entry.asp?504-- NN/g web form design: https://www.nngroup.com/articles/web-form-design/-- NN/g form errors: https://www.nngroup.com/articles/errors-forms-design-guidelines/-- Polaris inline error: https://polaris-react.shopify.com/components/selection-and-input/inline-error-- Ant / 2x form pattern: https://2x.ant.design/docs/pattern/form-- Mantine form validation: https://mantine.dev/form/validation/--**Overlays / layering / a11y**-- Radix Dialog: https://www.radix-ui.com/primitives/docs/components/dialog-- Radix Toast: https://www.radix-ui.com/primitives/docs/components/toast-- W3C ARIA alertdialog: https://www.w3.org/WAI/ARIA/apg/patterns/alertdialog/-- W3C ARIA dialog-modal: https://www.w3.org/WAI/ARIA/apg/patterns/dialog-modal/-- W3C ARIA grid data-grids: https://www.w3.org/WAI/ARIA/apg/patterns/grid/examples/data-grids/-- MDN stacking context: https://developer.mozilla.org/en-US/docs/Web/CSS/Guides/Positioned_layout/Stacking_context--**Tokens / density / i18n**-- Atlaskit design tokens: https://atlassian.design/foundations/design-tokens-- Atlaskit spacing: https://atlassian.design/foundations/spacing-- Crowdin UI localization: https://crowdin.com/blog/best-practices-for-ui-localization-- Material 3 accessibility (targets): https://m3.material.io/components/buttons/accessibility--**Modern minimal**-- Linear method: https://linear.app/method/introduction-- Vercel design guidelines: https://vercel.com/design/guidelines+## References+- `references/block-skeletons.md` - worked reference implementations for the three block contracts most often gotten wrong (index + detail-drawer frame, table scroll/sticky-header/frozen-column CSS contract, truncation contract).+- `references/install-commands.md` - Appendix A: package-manager install commands per host design system.+- `references/canonical-sources.md` - Appendix B: gsearch-verified primary-source URLs backing this skill's rules, grouped by topic.+diff --git a/skills/product-ui-taste/references/block-skeletons.md b/skills/product-ui-taste/references/block-skeletons.mdnew file mode 100644index 0000000..fd64072--- /dev/null+++ b/skills/product-ui-taste/references/block-skeletons.md@@ -0,0 +1,51 @@+# Block skeletons++Reference for product-ui-taste: worked reference implementations for the three block contracts most often gotten wrong.++### 12.A Block Library (reference implementations)+Full component implementations live in the host system, not duplicated here: reach them via your host system's template/skeleton command or its docs (Appendix B). Three high-value skeletons are worked below because they encode the contracts most often gotten wrong; treat them as the canonical shape, adapt to the host system.++**Block 1 - Index + detail-drawer (frame-first):**+```tsx+// Budget the frame first: nav 256 | table flex | inspector 380+<AppShell sideNav={<SideNav>{/* nav */}</SideNav>} contentPadding={0}>+ <Layout>+ <LayoutContent>+ <ToolbarTableFilter /* search + status/priority filters + overflow (cap 5) */ />+ {/* applied-filter chips row + Clear all (Section 7.F) */}+ <Table+ plugins={[useTableStickyColumns, useTableColumnResize /*, pagination */]}+ /* selection persists by row id across page/sort/filter (Section 7.E) */+ />+ {/* pagination footer; three empty states + ErrorState wired per Section 6 */}+ </LayoutContent>+ <LayoutPanel width={380} resizable={{minSizePx: 320, maxSizePx: 480}} hasDivider isScrollable>+ {selected ? <DetailFields item={selected} /> : <EmptyState title="Nothing selected" />}+ </LayoutPanel>+ </Layout>+</AppShell>+// Below ~1024px: LayoutPanel overlays Content; SideNav becomes MobileNav.+```++**Block 2 - Table scroll + sticky header + frozen column (the CSS contract a system's hooks satisfy):**+```css+/* ONE wrapper owns both scroll axes; page body never scrolls sideways (Section 4). */+.table-scroll { overflow: auto; max-block-size: 70vh; } /* bounded height => sticky works */+.table-scroll thead th { position: sticky; inset-block-start: 0; z-index: 20; }+/* Frozen first column: sticky + offset + z + SOLID THEME-TOKEN bg + shadow divider, never border */+.col-frozen {+ position: sticky; inset-inline-start: 0; z-index: 10;+ background: var(--color-surface); /* must also cover hover/selected rows */+ box-shadow: inset -1px 0 0 var(--color-border); /* not border-right (double-renders on scroll) */+}+```++**Block 3 - Truncation contract (single-line + multi-line):**+```css+.cell { min-inline-size: 0; } /* required on EVERY flex ancestor or ellipsis no-ops */+.cell .text { overflow: hidden; text-overflow: ellipsis; white-space: nowrap; }+.clamp { /* all four props; NO padding on this node */+ display: -webkit-box; -webkit-line-clamp: 2; -webkit-box-orient: vertical; overflow: hidden;+}+```+diff --git a/skills/product-ui-taste/references/canonical-sources.md b/skills/product-ui-taste/references/canonical-sources.mdnew file mode 100644index 0000000..ee68c6c--- /dev/null+++ b/skills/product-ui-taste/references/canonical-sources.md@@ -0,0 +1,67 @@+# Canonical sources++Reference for product-ui-taste: gsearch-verified primary-source URLs backing this skill's rules, grouped by topic.++## Appendix B - Canonical sources (real URLs, gsearch-verified)++Consolidated primary sources:++**Frame / layout**+- Carbon 2x grid: https://carbondesignsystem.com/elements/2x-grid/usage/+- Primer PageLayout: https://primer.style/product/components/page-layout+- Material 3 canonical layouts: https://m3.material.io/foundations/adaptive-design/canonical-layouts+- Material 3 list-detail: https://m3.material.io/foundations/layout/canonical-examples/list-detail+- Material 3 supporting-pane: https://m3.material.io/foundations/layout/canonical-examples/supporting-pane+- Container queries: https://www.joshwcomeau.com/css/container-queries-unleashed/++**Overflow / truncation**+- Carbon overflow content: https://carbondesignsystem.com/patterns/overflow-content/+- Primer Truncate: https://primer.style/product/components/truncate/+- CSS line-clamp: https://css-tricks.com/line-clampin/++**State matrix**+- Polaris EmptyState: https://polaris-react.shopify.com/components/layout-and-structure/empty-state+- Carbon empty states: https://carbondesignsystem.com/patterns/empty-states-pattern/+- Carbon loading: https://carbondesignsystem.com/patterns/loading-pattern/+- Primer empty states: https://primer.style/product/ui-patterns/empty-states/+- NN/g skeleton screens: https://www.nngroup.com/articles/skeleton-screens/+- NN/g empty-state design: https://www.nngroup.com/articles/empty-state-interface-design/+- Pencil&Paper empty states: https://www.pencilandpaper.io/articles/empty-states+- Polaris error messages: https://polaris-react.shopify.com/content/error-messages++**Data table**+- Carbon data table: https://carbondesignsystem.com/components/data-table/usage/+- Polaris IndexTable: https://polaris-react.shopify.com/components/tables/index-table+- Ant table scroll: https://ant.design/docs/blog/table-scroll-ghost/+- Ant virtual table: https://ant.design/docs/blog/virtual-table/+- TanStack column sizing: https://tanstack.com/table/latest/docs/guide/column-sizing+- Mantine React Table column pinning: https://www.mantine-react-table.com/docs/guides/column-pinning+- NN/g infinite scroll: https://www.nngroup.com/articles/infinite-scrolling-tips/+- Baymard checkout linear / pagination context: https://baymard.com/blog/checkout-process-should-be-linear+- Pagination vs infinite vs load-more: https://www.smashingmagazine.com/2016/03/pagination-infinite-scrolling-load-more-buttons/++**Forms / flows**+- LukeW web form design: https://www.lukew.com/ff/entry.asp?504+- NN/g web form design: https://www.nngroup.com/articles/web-form-design/+- NN/g form errors: https://www.nngroup.com/articles/errors-forms-design-guidelines/+- Polaris inline error: https://polaris-react.shopify.com/components/selection-and-input/inline-error+- Ant / 2x form pattern: https://2x.ant.design/docs/pattern/form+- Mantine form validation: https://mantine.dev/form/validation/++**Overlays / layering / a11y**+- Radix Dialog: https://www.radix-ui.com/primitives/docs/components/dialog+- Radix Toast: https://www.radix-ui.com/primitives/docs/components/toast+- W3C ARIA alertdialog: https://www.w3.org/WAI/ARIA/apg/patterns/alertdialog/+- W3C ARIA dialog-modal: https://www.w3.org/WAI/ARIA/apg/patterns/dialog-modal/+- W3C ARIA grid data-grids: https://www.w3.org/WAI/ARIA/apg/patterns/grid/examples/data-grids/+- MDN stacking context: https://developer.mozilla.org/en-US/docs/Web/CSS/Guides/Positioned_layout/Stacking_context++**Tokens / density / i18n**+- Atlaskit design tokens: https://atlassian.design/foundations/design-tokens+- Atlaskit spacing: https://atlassian.design/foundations/spacing+- Crowdin UI localization: https://crowdin.com/blog/best-practices-for-ui-localization+- Material 3 accessibility (targets): https://m3.material.io/components/buttons/accessibility++**Modern minimal**+- Linear method: https://linear.app/method/introduction+- Vercel design guidelines: https://vercel.com/design/guidelinesdiff --git a/skills/product-ui-taste/references/install-commands.md b/skills/product-ui-taste/references/install-commands.mdnew file mode 100644index 0000000..6940073--- /dev/null+++ b/skills/product-ui-taste/references/install-commands.md@@ -0,0 +1,32 @@+# Install / CLI per system++Reference for product-ui-taste: package-manager install commands for each supported host design system.++## Appendix A - Install / CLI per system++```bash+# House design system - resolve the real API before writing UI.+# Most systems ship a CLI or a docs site; use whichever exists.+# 1. find the closest shipped page/block template+# 2. study its layout skeleton+# 3. read real props for every component (never invent props)++# IBM Carbon+npm install @carbon/react @carbon/styles+# Microsoft Fluent UI React v9+npm install @fluentui/react-components+# Atlassian Atlaskit (per-component + tokens)+npm install @atlaskit/tokens @atlaskit/dynamic-table+# Shopify Polaris+npm install @shopify/polaris+# GitHub Primer React+npm install @primer/react styled-components+# Radix Primitives + shadcn/ui + TanStack Table+npm install @radix-ui/react-dialog @radix-ui/react-toast @tanstack/react-table+npx shadcn@latest add table dialog+# Material Web (Material 3)+npm install @material/web+# Ant Design / Mantine + Mantine React Table+npm install antd+npm install @mantine/core @mantine/form mantine-react-table+```diff --git a/skills/taste-skill/SKILL.md b/skills/taste-skill/SKILL.mdindex 9b80a8e..e97c720 100644--- a/skills/taste-skill/SKILL.md+++ b/skills/taste-skill/SKILL.md@@ -364,111 +364,13 @@ These are tools, not defaults. Use them when the design read calls for them. **N### 5.A Sticky-Stack - Canonical Skeleton-```tsx-"use client";-import { useRef, useEffect } from "react";-import { gsap } from "gsap";-import { ScrollTrigger } from "gsap/ScrollTrigger";-import { useReducedMotion } from "motion/react";--gsap.registerPlugin(ScrollTrigger);--export function StickyStack({ cards }: { cards: React.ReactNode[] }) {- const ref = useRef<HTMLDivElement>(null);- const reduce = useReducedMotion();-- useEffect(() => {- if (reduce || !ref.current) return;- const ctx = gsap.context(() => {- const cardEls = gsap.utils.toArray<HTMLElement>(".stack-card");- cardEls.forEach((card, i) => {- if (i === cardEls.length - 1) return;- ScrollTrigger.create({- trigger: card,- start: "top top", // pin at viewport top- endTrigger: cardEls[cardEls.length - 1],- end: "top top",- pin: true,- pinSpacing: false,- });- gsap.to(card, {- scale: 0.92,- opacity: 0.55,- ease: "none",- scrollTrigger: {- trigger: cardEls[i + 1],- start: "top bottom",- end: "top top",- scrub: true,- },- });- });- }, ref);- return () => ctx.revert();- }, [reduce]);-- return (- <div ref={ref} className="relative">- {cards.map((card, i) => (- <div- key={i}- className="stack-card sticky top-0 min-h-[100dvh] flex items-center justify-center"- >- {card}- </div>- ))}- </div>- );-}-```+Canonical tsx skeleton: `references/motion-skeletons.md`.Critical points: `start: "top top"`, `pin: true`, every card except the last is pinned, the scale/opacity transform is driven by the NEXT card's scroll trigger (so previous card shrinks as next one arrives).### 5.B Horizontal-Pan - Canonical Skeleton-```tsx-"use client";-import { useRef, useEffect } from "react";-import { gsap } from "gsap";-import { ScrollTrigger } from "gsap/ScrollTrigger";-import { useReducedMotion } from "motion/react";--gsap.registerPlugin(ScrollTrigger);--export function HorizontalPan({ children }: { children: React.ReactNode }) {- const wrap = useRef<HTMLDivElement>(null);- const track = useRef<HTMLDivElement>(null);- const reduce = useReducedMotion();-- useEffect(() => {- if (reduce || !wrap.current || !track.current) return;- const ctx = gsap.context(() => {- const distance = track.current!.scrollWidth - window.innerWidth;- gsap.to(track.current, {- x: -distance,- ease: "none",- scrollTrigger: {- trigger: wrap.current,- start: "top top", // pin starts when section top hits viewport top- end: () => `+=${distance}`, // scroll distance = track width minus viewport- pin: true,- scrub: 1,- invalidateOnRefresh: true,- },- });- }, wrap);- return () => ctx.revert();- }, [reduce]);-- return (- <section ref={wrap} className="relative overflow-hidden">- <div ref={track} className="flex h-[100dvh] items-center">- {children}- </div>- </section>- );-}-```+Canonical tsx skeleton: `references/motion-skeletons.md`.Critical points: `start: "top top"`, `pin: true`, `end: "+=${distance}"` (scroll length = horizontal travel needed), `scrub: 1`. The wrapper is pinned, the inner track slides horizontally as the user scrolls vertically.@@ -476,33 +378,7 @@ Critical points: `start: "top top"`, `pin: true`, `end: "+=${distance}"` (scrollFor simple "items appear as they enter viewport" (no pinning), prefer Motion's `whileInView` over GSAP - lighter, no ScrollTrigger needed:-```tsx-"use client";-import { motion, useReducedMotion } from "motion/react";--export function RevealStagger({ items }: { items: string[] }) {- const reduce = useReducedMotion();- return (- <ul className="grid gap-6">- {items.map((item, i) => (- <motion.li- key={item}- initial={reduce ? false : { opacity: 0, y: 24 }}- whileInView={{ opacity: 1, y: 0 }}- viewport={{ once: true, amount: 0.3 }}- transition={{- duration: 0.6,- delay: i * 0.06,- ease: [0.16, 1, 0.3, 1],- }}- >- {item}- </motion.li>- ))}- </ul>- );-}-```+Canonical tsx skeleton: `references/motion-skeletons.md`.Use this for: feature lists, testimonial grids, logo walls, anything that just needs "enter on scroll." Save GSAP for actual pin/scrub work.@@ -702,84 +578,6 @@ This rule is non-negotiable. The agent has historically ignored em-dash limits w----## 10. REFERENCE VOCABULARY (Pattern Names the Agent Should Know)--This is a vocabulary, not a library. The agent should KNOW these pattern names to communicate about them, design with them in mind, and reach for them when the design read calls for them. **Implementations and code sketches live in the Block Library (Section 12), which is populated iteratively.**--### Hero Paradigms-* **Asymmetric Split Hero** - Text on one side, asset on the other, generous white space.-* **Editorial Manifesto Hero** - Large type, no asset, almost-poster.-* **Video / Media Mask Hero** - Type cut out as mask over video background.-* **Kinetic-Type Hero** - Animated typography as the primary visual.-* **Curtain-Reveal Hero** - Hero parts on scroll like a curtain.-* **Scroll-Pinned Hero** - Hero stays pinned while content scrolls behind.--### Navigation & Menus-* **Mac OS Dock Magnification** - Edge nav, icons scale fluidly on hover.-* **Magnetic Button** - Pulls toward cursor.-* **Gooey Menu** - Sub-items detach like viscous liquid.-* **Dynamic Island** - Morphing pill for status / alerts.-* **Contextual Radial Menu** - Circular menu expanding at click point.-* **Floating Speed Dial** - FAB springing into curved secondary actions.-* **Mega Menu Reveal** - Full-screen dropdown, stagger-fade content.--### Layout & Grids-* **Bento Grid** - Asymmetric tile grouping (Apple Control Center).-* **Masonry Layout** - Staggered grid, no fixed row height.-* **Chroma Grid** - Borders / tiles with subtle animating gradients.-* **Split-Screen Scroll** - Two halves sliding in opposite directions.-* **Sticky-Stack Sections** - Sections that pin and stack on scroll.--### Cards & Containers-* **Parallax Tilt Card** - 3D tilt tracking mouse coordinates.-* **Spotlight Border Card** - Borders illuminate under cursor.-* **Glassmorphism Panel** - Frosted glass with inner refraction.-* **Holographic Foil Card** - Iridescent rainbow shift on hover.-* **Tinder Swipe Stack** - Physical card stack, swipe-away.-* **Morphing Modal** - Button expands into its own dialog.--### Scroll Animations-* **Sticky Scroll Stack** - Cards stick and physically stack.-* **Horizontal Scroll Hijack** - Vertical scroll → horizontal pan.-* **Locomotive / Sequence Scroll** - Video / 3D sequence tied to scrollbar.-* **Zoom Parallax** - Central background image zooming on scroll.-* **Scroll Progress Path** - SVG line drawing along scroll.-* **Liquid Swipe Transition** - Page transition like viscous liquid.--### Galleries & Media-* **Dome Gallery** - 3D panoramic gallery.-* **Coverflow Carousel** - 3D carousel with angled edges.-* **Drag-to-Pan Grid** - Boundless draggable canvas.-* **Accordion Image Slider** - Narrow strips expanding on hover.-* **Hover Image Trail** - Mouse leaves popping image trail.-* **Glitch Effect Image** - RGB-channel shift on hover.--### Typography & Text-* **Kinetic Marquee** - Endless text bands reversing on scroll.-* **Text Mask Reveal** - Massive type as transparent window to video.-* **Text Scramble Effect** - Matrix-style decoding on load / hover.-* **Circular Text Path** - Text curving along spinning circle.-* **Gradient Stroke Animation** - Outlined text with running gradient.-* **Kinetic Typography Grid** - Letters dodging the cursor.--### Micro-Interactions & Effects-* **Particle Explosion Button** - CTA shatters into particles on success.-* **Liquid Pull-to-Refresh** - Reload indicator like detaching droplets.-* **Skeleton Shimmer** - Shifting light reflection across placeholders.-* **Directional Hover-Aware Button** - Fill enters from cursor's exact side.-* **Ripple Click Effect** - Wave from click coordinates.-* **Animated SVG Line Drawing** - Vectors drawing themselves in real time.-* **Mesh Gradient Background** - Organic lava-lamp blobs.-* **Lens Blur Depth** - Background UI blurred to focus foreground action.--### Animation Library Choice-* **Motion (`motion/react`)** - default for UI / Bento / state-change motion.-* **GSAP + ScrollTrigger** - for full-page scrolltelling and scroll hijacks. Isolate in dedicated leaf components with `useEffect` cleanup.-* **Three.js / WebGL** - for canvas backgrounds and 3D scenes. Same isolation rule.-* **NEVER mix GSAP / Three.js with Motion in the same component tree.** They fight over the same frames.------## 11. REDESIGN PROTOCOLThis skill handles **greenfield builds AND redesigns**. Misclassifying the mode is the single biggest source of bad redesign output.@@ -814,7 +612,7 @@ Apply in order - stop when the brief is satisfied:2. **Spacing & rhythm** - increase section padding, fix vertical rhythm.3. **Color recalibration** - desaturate, unify neutrals, keep brand accent.4. **Motion layer** - add `MOTION_INTENSITY`-appropriate micro-interactions to existing components.-5. **Hero & key-section recomposition** - restructure top-of-funnel using Section 10 vocabulary.+5. **Hero & key-section recomposition** - restructure top-of-funnel using the vocabulary in `references/pattern-vocabulary.md`.6. **Full block replacement** - only when the existing block is unsalvageable.### 11.E Decision Tree: Targeted Evolution vs Full Redesign@@ -834,7 +632,7 @@ Never modify without explicit user approval:## 12. THE BLOCK LIBRARY (Contract - Implementations Land Here Iteratively)-The Reference Vocabulary (Section 10) names patterns. The Block Library implements them with real props, real motion specs, and real code sketches.+The Reference Vocabulary (`references/pattern-vocabulary.md`) names patterns. The Block Library implements them with real props, real motion specs, and real code sketches.**Status:** schema defined here. Blocks will be added iteratively. Do not freelance new blocks without following this schema.@@ -982,227 +780,11 @@ If a single checkbox cannot be honestly ticked, the page is not done. Fix it bef----# APPENDICES - Real Source-Backed Reference Material--The sections below are vendored reference content. They give the agent real install commands, real canonical doc links, and real working starter snippets for each design system named in Section 2. Use them to ground decisions in production reality, not training-data fiction.--## Appendix A - Install Commands per Design System--```bash-# Material Web (Material 3)-npm install @material/web--# Fluent UI React (v9)-npm install @fluentui/react-components--# Fluent UI Web Components (framework-free)-npm install @fluentui/web-components @fluentui/tokens--# IBM Carbon-npm install @carbon/react @carbon/styles--# Radix Themes-npm install @radix-ui/themes--# shadcn/ui (open code, owned components)-npx shadcn@latest init-npx shadcn@latest add button card badge separator input--# Primer CSS (GitHub product/devtool UI)-npm install --save @primer/css+## References (vendored reference material, moved out of the body)-# Primer Brand (GitHub marketing UI)-npm install @primer/react-brand--# GOV.UK Frontend-npm install govuk-frontend--# USWDS (US Web Design System)-npm install uswds--# Atlassian Design System (Atlaskit)-yarn add @atlaskit/css-reset @atlaskit/tokens @atlaskit/button @atlaskit/badge @atlaskit/section-message @atlaskit/card--# Bootstrap 5.3-npm install bootstrap--# Shopify Polaris Web Components (Shopify apps only)-# Add this to your app HTML head:-# <meta name="shopify-api-key" content="%SHOPIFY_API_KEY%" />-# <script src="https://cdn.shopify.com/shopifycloud/polaris.js"></script>-```--## Appendix B - Canonical Sources (read these before reinventing)--### Material Web-- https://github.com/material-components/material-web-- https://material-web.dev/theming/material-theming/-- https://m3.material.io/develop/web--### Fluent UI-- https://fluent2.microsoft.design/get-started/develop-- https://fluent2.microsoft.design/components/web/react/-- https://github.com/microsoft/fluentui-- https://learn.microsoft.com/en-us/fluent-ui/web-components/--### Carbon-- https://carbondesignsystem.com/-- https://github.com/carbon-design-system/carbon-- https://carbondesignsystem.com/developing/react-tutorial/overview/-- https://carbondesignsystem.com/developing/web-components-tutorial/overview/--### Shopify Polaris-- https://shopify.dev/docs/api/app-home/web-components-- https://github.com/Shopify/polaris-react-- https://polaris-react.shopify.com/components--### Atlassian-- https://atlassian.design/get-started/develop-- https://atlassian.design/components/button/examples-- https://atlaskit.atlassian.com/packages/design-system/button/example/disabled-- https://atlassian.design/tokens/design-tokens--### Primer-- https://primer.style/-- https://github.com/primer/css-- https://github.com/primer/brand--### GOV.UK-- https://design-system.service.gov.uk/components/button/-- https://design-system.service.gov.uk/styles/layout/-- https://github.com/alphagov/govuk-frontend--### USWDS-- https://designsystem.digital.gov/documentation/developers/-- https://designsystem.digital.gov/components/button/-- https://designsystem.digital.gov/components/card/-- https://github.com/uswds/uswds--### Bootstrap-- https://getbootstrap.com/docs/5.3/layout/grid/-- https://getbootstrap.com/docs/5.3/components/card/--### Tailwind-- https://tailwindcss.com/docs/dark-mode-- https://tailwindcss.com/blog/tailwindcss-v4--### Radix-- https://www.radix-ui.com/themes/docs/components/theme-- https://www.radix-ui.com/themes/docs/components/card-- https://github.com/radix-ui/themes--### shadcn/ui-- https://ui.shadcn.com/docs-- https://ui.shadcn.com/docs/components/card-- https://github.com/shadcn-ui/ui--### Native CSS / W3C standards-- https://developer.mozilla.org/en-US/docs/Web/CSS/Reference/Properties/backdrop-filter-- https://developer.mozilla.org/en-US/docs/Web/CSS/Reference/At-rules/@media/prefers-color-scheme-- https://developer.mozilla.org/en-US/docs/Web/CSS/Reference/At-rules/@media/prefers-reduced-motion-- https://developer.mozilla.org/en-US/docs/Web/CSS/Guides/Grid_layout-- https://developer.mozilla.org/en-US/docs/Web/CSS/Guides/Scroll-driven_animations-- https://drafts.csswg.org/scroll-animations-1/--### Apple Liquid Glass (Apple platforms only)-- https://developer.apple.com/design/human-interface-guidelines/materials-- https://developer.apple.com/documentation/TechnologyOverviews/liquid-glass-- https://developer.apple.com/documentation/TechnologyOverviews/adopting-liquid-glass-- https://developer.apple.com/documentation/SwiftUI/Material-------## Appendix C - Apple Liquid Glass: Honest Web Approximation--Do **not** treat random CSS snippets as official Apple Liquid Glass.--### What is official-Apple documents Liquid Glass inside Apple's Human Interface Guidelines and Developer Documentation for **Apple platforms**. It is a dynamic material used across Apple platform UI. Apple's native implementation belongs to Apple platform APIs and system components, **not a public web CSS package**.--Relevant official docs:-- Apple Human Interface Guidelines → Materials-- Apple Developer Documentation → Liquid Glass-- Apple Developer Documentation → Adopting Liquid Glass-- SwiftUI → Material--### What is NOT official-There is no `liquid-glass.css` from Apple for normal websites.--A web approximation can use:-- `backdrop-filter`-- transparent backgrounds-- layered borders-- highlight overlays-- gradients-- motion-- strong contrast fallbacks--But that is **web glassmorphism / frosted-glass approximation**, not official Apple Liquid Glass. Label it as such in comments.--### Safer web approximation skeleton--```css-.liquid-glass-web-approx {- position: relative;- isolation: isolate;- overflow: hidden;- border-radius: 999px;- border: 1px solid rgb(255 255 255 / .32);- background:- linear-gradient(135deg, rgb(255 255 255 / .30), rgb(255 255 255 / .08)),- rgb(255 255 255 / .12);- backdrop-filter: blur(24px) saturate(180%) contrast(1.05);- -webkit-backdrop-filter: blur(24px) saturate(180%) contrast(1.05);- box-shadow:- inset 0 1px 0 rgb(255 255 255 / .48),- inset 0 -1px 0 rgb(255 255 255 / .12),- 0 18px 60px rgb(0 0 0 / .18);-}--.liquid-glass-web-approx::before {- content: "";- position: absolute;- inset: 0;- z-index: -1;- border-radius: inherit;- background:- radial-gradient(circle at 20% 0%, rgb(255 255 255 / .55), transparent 34%),- linear-gradient(90deg, rgb(255 255 255 / .18), transparent 42%, rgb(255 255 255 / .14));- pointer-events: none;-}--.liquid-glass-web-approx::after {- content: "";- position: absolute;- inset: 1px;- border-radius: inherit;- border: 1px solid rgb(255 255 255 / .14);- pointer-events: none;-}--@media (prefers-color-scheme: dark) {- .liquid-glass-web-approx {- border-color: rgb(255 255 255 / .18);- background:- linear-gradient(135deg, rgb(255 255 255 / .16), rgb(255 255 255 / .04)),- rgb(15 23 42 / .42);- box-shadow:- inset 0 1px 0 rgb(255 255 255 / .22),- 0 18px 60px rgb(0 0 0 / .42);- }-}--@media (prefers-reduced-transparency: reduce) {- .liquid-glass-web-approx {- background: rgb(255 255 255 / .96);- backdrop-filter: none;- -webkit-backdrop-filter: none;- }-}-```--**Important:** `prefers-reduced-transparency` has uneven browser support; test it. Always provide enough contrast even without blur.-----+- `references/pattern-vocabulary.md` - the full Reference Vocabulary (pattern names the agent should know).+- `references/motion-skeletons.md` - canonical tsx code skeletons for the 5.A Sticky-Stack, 5.B Horizontal-Pan, and 5.C Scroll-Reveal Stagger patterns.+- `references/design-systems-install.md` - real install commands per design system named in Section 2.+- `references/canonical-sources.md` - canonical documentation links per design system, read these before reinventing.+- `references/liquid-glass.md` - what is and isn't official Apple Liquid Glass, plus a labeled web CSS approximation.-**End of appendices.** Install commands above are reality anchors. The Apple Liquid Glass skeleton is a labeled approximation, not an Apple-issued package. For canonical docs per design system, consult the system's official docs (links in Section 2 plus Appendix B).diff --git a/skills/taste-skill/references/canonical-sources.md b/skills/taste-skill/references/canonical-sources.mdnew file mode 100644index 0000000..4b78d44--- /dev/null+++ b/skills/taste-skill/references/canonical-sources.md@@ -0,0 +1,83 @@+# Canonical Design System Sources++Canonical documentation links per design system named in taste-skill's Section 2. Read these before reinventing a component that a system already ships.++## Appendix B - Canonical Sources (read these before reinventing)++### Material Web+- https://github.com/material-components/material-web+- https://material-web.dev/theming/material-theming/+- https://m3.material.io/develop/web++### Fluent UI+- https://fluent2.microsoft.design/get-started/develop+- https://fluent2.microsoft.design/components/web/react/+- https://github.com/microsoft/fluentui+- https://learn.microsoft.com/en-us/fluent-ui/web-components/++### Carbon+- https://carbondesignsystem.com/+- https://github.com/carbon-design-system/carbon+- https://carbondesignsystem.com/developing/react-tutorial/overview/+- https://carbondesignsystem.com/developing/web-components-tutorial/overview/++### Shopify Polaris+- https://shopify.dev/docs/api/app-home/web-components+- https://github.com/Shopify/polaris-react+- https://polaris-react.shopify.com/components++### Atlassian+- https://atlassian.design/get-started/develop+- https://atlassian.design/components/button/examples+- https://atlaskit.atlassian.com/packages/design-system/button/example/disabled+- https://atlassian.design/tokens/design-tokens++### Primer+- https://primer.style/+- https://github.com/primer/css+- https://github.com/primer/brand++### GOV.UK+- https://design-system.service.gov.uk/components/button/+- https://design-system.service.gov.uk/styles/layout/+- https://github.com/alphagov/govuk-frontend++### USWDS+- https://designsystem.digital.gov/documentation/developers/+- https://designsystem.digital.gov/components/button/+- https://designsystem.digital.gov/components/card/+- https://github.com/uswds/uswds++### Bootstrap+- https://getbootstrap.com/docs/5.3/layout/grid/+- https://getbootstrap.com/docs/5.3/components/card/++### Tailwind+- https://tailwindcss.com/docs/dark-mode+- https://tailwindcss.com/blog/tailwindcss-v4++### Radix+- https://www.radix-ui.com/themes/docs/components/theme+- https://www.radix-ui.com/themes/docs/components/card+- https://github.com/radix-ui/themes++### shadcn/ui+- https://ui.shadcn.com/docs+- https://ui.shadcn.com/docs/components/card+- https://github.com/shadcn-ui/ui++### Native CSS / W3C standards+- https://developer.mozilla.org/en-US/docs/Web/CSS/Reference/Properties/backdrop-filter+- https://developer.mozilla.org/en-US/docs/Web/CSS/Reference/At-rules/@media/prefers-color-scheme+- https://developer.mozilla.org/en-US/docs/Web/CSS/Reference/At-rules/@media/prefers-reduced-motion+- https://developer.mozilla.org/en-US/docs/Web/CSS/Guides/Grid_layout+- https://developer.mozilla.org/en-US/docs/Web/CSS/Guides/Scroll-driven_animations+- https://drafts.csswg.org/scroll-animations-1/++### Apple Liquid Glass (Apple platforms only)+- https://developer.apple.com/design/human-interface-guidelines/materials+- https://developer.apple.com/documentation/TechnologyOverviews/liquid-glass+- https://developer.apple.com/documentation/TechnologyOverviews/adopting-liquid-glass+- https://developer.apple.com/documentation/SwiftUI/Material++**End of appendices.** Install commands above are reality anchors. The Apple Liquid Glass skeleton is a labeled approximation, not an Apple-issued package. For canonical docs per design system, consult the system's official docs (links in Section 2 plus this file).diff --git a/skills/taste-skill/references/design-systems-install.md b/skills/taste-skill/references/design-systems-install.mdnew file mode 100644index 0000000..4c929b0--- /dev/null+++ b/skills/taste-skill/references/design-systems-install.md@@ -0,0 +1,49 @@+# Design System Install Commands++Real install commands for each design system named in taste-skill's Section 2. Read this before wiring up a design system so the package name and CLI invocation are correct.++## Appendix A - Install Commands per Design System++```bash+# Material Web (Material 3)+npm install @material/web++# Fluent UI React (v9)+npm install @fluentui/react-components++# Fluent UI Web Components (framework-free)+npm install @fluentui/web-components @fluentui/tokens++# IBM Carbon+npm install @carbon/react @carbon/styles++# Radix Themes+npm install @radix-ui/themes++# shadcn/ui (open code, owned components)+npx shadcn@latest init+npx shadcn@latest add button card badge separator input++# Primer CSS (GitHub product/devtool UI)+npm install --save @primer/css++# Primer Brand (GitHub marketing UI)+npm install @primer/react-brand++# GOV.UK Frontend+npm install govuk-frontend++# USWDS (US Web Design System)+npm install uswds++# Atlassian Design System (Atlaskit)+yarn add @atlaskit/css-reset @atlaskit/tokens @atlaskit/button @atlaskit/badge @atlaskit/section-message @atlaskit/card++# Bootstrap 5.3+npm install bootstrap++# Shopify Polaris Web Components (Shopify apps only)+# Add this to your app HTML head:+# <meta name="shopify-api-key" content="%SHOPIFY_API_KEY%" />+# <script src="https://cdn.shopify.com/shopifycloud/polaris.js"></script>+```diff --git a/skills/taste-skill/references/liquid-glass.md b/skills/taste-skill/references/liquid-glass.mdnew file mode 100644index 0000000..4e2eb64--- /dev/null+++ b/skills/taste-skill/references/liquid-glass.md@@ -0,0 +1,94 @@+# Apple Liquid Glass: Honest Web Approximation++What is and isn't official Apple Liquid Glass, and a labeled CSS approximation for the web, for taste-skill's Section 2 design-system decisions.++## Appendix C - Apple Liquid Glass: Honest Web Approximation++Do **not** treat random CSS snippets as official Apple Liquid Glass.++### What is official+Apple documents Liquid Glass inside Apple's Human Interface Guidelines and Developer Documentation for **Apple platforms**. It is a dynamic material used across Apple platform UI. Apple's native implementation belongs to Apple platform APIs and system components, **not a public web CSS package**.++Relevant official docs:+- Apple Human Interface Guidelines → Materials+- Apple Developer Documentation → Liquid Glass+- Apple Developer Documentation → Adopting Liquid Glass+- SwiftUI → Material++### What is NOT official+There is no `liquid-glass.css` from Apple for normal websites.++A web approximation can use:+- `backdrop-filter`+- transparent backgrounds+- layered borders+- highlight overlays+- gradients+- motion+- strong contrast fallbacks++But that is **web glassmorphism / frosted-glass approximation**, not official Apple Liquid Glass. Label it as such in comments.++### Safer web approximation skeleton++```css+.liquid-glass-web-approx {+ position: relative;+ isolation: isolate;+ overflow: hidden;+ border-radius: 999px;+ border: 1px solid rgb(255 255 255 / .32);+ background:+ linear-gradient(135deg, rgb(255 255 255 / .30), rgb(255 255 255 / .08)),+ rgb(255 255 255 / .12);+ backdrop-filter: blur(24px) saturate(180%) contrast(1.05);+ -webkit-backdrop-filter: blur(24px) saturate(180%) contrast(1.05);+ box-shadow:+ inset 0 1px 0 rgb(255 255 255 / .48),+ inset 0 -1px 0 rgb(255 255 255 / .12),+ 0 18px 60px rgb(0 0 0 / .18);+}++.liquid-glass-web-approx::before {+ content: "";+ position: absolute;+ inset: 0;+ z-index: -1;+ border-radius: inherit;+ background:+ radial-gradient(circle at 20% 0%, rgb(255 255 255 / .55), transparent 34%),+ linear-gradient(90deg, rgb(255 255 255 / .18), transparent 42%, rgb(255 255 255 / .14));+ pointer-events: none;+}++.liquid-glass-web-approx::after {+ content: "";+ position: absolute;+ inset: 1px;+ border-radius: inherit;+ border: 1px solid rgb(255 255 255 / .14);+ pointer-events: none;+}++@media (prefers-color-scheme: dark) {+ .liquid-glass-web-approx {+ border-color: rgb(255 255 255 / .18);+ background:+ linear-gradient(135deg, rgb(255 255 255 / .16), rgb(255 255 255 / .04)),+ rgb(15 23 42 / .42);+ box-shadow:+ inset 0 1px 0 rgb(255 255 255 / .22),+ 0 18px 60px rgb(0 0 0 / .42);+ }+}++@media (prefers-reduced-transparency: reduce) {+ .liquid-glass-web-approx {+ background: rgb(255 255 255 / .96);+ backdrop-filter: none;+ -webkit-backdrop-filter: none;+ }+}+```++**Important:** `prefers-reduced-transparency` has uneven browser support; test it. Always provide enough contrast even without blur.diff --git a/skills/taste-skill/references/motion-skeletons.md b/skills/taste-skill/references/motion-skeletons.mdnew file mode 100644index 0000000..473d394--- /dev/null+++ b/skills/taste-skill/references/motion-skeletons.md@@ -0,0 +1,139 @@+# Motion Skeletons++Canonical tsx code skeletons for the GSAP/Motion patterns named in SKILL.md Section 5 (5.A Sticky-Stack, 5.B Horizontal-Pan, 5.C Scroll-Reveal Stagger). Read the matching subsection in SKILL.md for the critical points and failure modes before pasting this in.++### 5.A Sticky-Stack++```tsx+"use client";+import { useRef, useEffect } from "react";+import { gsap } from "gsap";+import { ScrollTrigger } from "gsap/ScrollTrigger";+import { useReducedMotion } from "motion/react";++gsap.registerPlugin(ScrollTrigger);++export function StickyStack({ cards }: { cards: React.ReactNode[] }) {+ const ref = useRef<HTMLDivElement>(null);+ const reduce = useReducedMotion();++ useEffect(() => {+ if (reduce || !ref.current) return;+ const ctx = gsap.context(() => {+ const cardEls = gsap.utils.toArray<HTMLElement>(".stack-card");+ cardEls.forEach((card, i) => {+ if (i === cardEls.length - 1) return;+ ScrollTrigger.create({+ trigger: card,+ start: "top top", // pin at viewport top+ endTrigger: cardEls[cardEls.length - 1],+ end: "top top",+ pin: true,+ pinSpacing: false,+ });+ gsap.to(card, {+ scale: 0.92,+ opacity: 0.55,+ ease: "none",+ scrollTrigger: {+ trigger: cardEls[i + 1],+ start: "top bottom",+ end: "top top",+ scrub: true,+ },+ });+ });+ }, ref);+ return () => ctx.revert();+ }, [reduce]);++ return (+ <div ref={ref} className="relative">+ {cards.map((card, i) => (+ <div+ key={i}+ className="stack-card sticky top-0 min-h-[100dvh] flex items-center justify-center"+ >+ {card}+ </div>+ ))}+ </div>+ );+}+```++### 5.B Horizontal-Pan++```tsx+"use client";+import { useRef, useEffect } from "react";+import { gsap } from "gsap";+import { ScrollTrigger } from "gsap/ScrollTrigger";+import { useReducedMotion } from "motion/react";++gsap.registerPlugin(ScrollTrigger);++export function HorizontalPan({ children }: { children: React.ReactNode }) {+ const wrap = useRef<HTMLDivElement>(null);+ const track = useRef<HTMLDivElement>(null);+ const reduce = useReducedMotion();++ useEffect(() => {+ if (reduce || !wrap.current || !track.current) return;+ const ctx = gsap.context(() => {+ const distance = track.current!.scrollWidth - window.innerWidth;+ gsap.to(track.current, {+ x: -distance,+ ease: "none",+ scrollTrigger: {+ trigger: wrap.current,+ start: "top top", // pin starts when section top hits viewport top+ end: () => `+=${distance}`, // scroll distance = track width minus viewport+ pin: true,+ scrub: 1,+ invalidateOnRefresh: true,+ },+ });+ }, wrap);+ return () => ctx.revert();+ }, [reduce]);++ return (+ <section ref={wrap} className="relative overflow-hidden">+ <div ref={track} className="flex h-[100dvh] items-center">+ {children}+ </div>+ </section>+ );+}+```++### 5.C Scroll-Reveal Stagger++```tsx+"use client";+import { motion, useReducedMotion } from "motion/react";++export function RevealStagger({ items }: { items: string[] }) {+ const reduce = useReducedMotion();+ return (+ <ul className="grid gap-6">+ {items.map((item, i) => (+ <motion.li+ key={item}+ initial={reduce ? false : { opacity: 0, y: 24 }}+ whileInView={{ opacity: 1, y: 0 }}+ viewport={{ once: true, amount: 0.3 }}+ transition={{+ duration: 0.6,+ delay: i * 0.06,+ ease: [0.16, 1, 0.3, 1],+ }}+ >+ {item}+ </motion.li>+ ))}+ </ul>+ );+}+```diff --git a/skills/taste-skill/references/pattern-vocabulary.md b/skills/taste-skill/references/pattern-vocabulary.mdnew file mode 100644index 0000000..b4f3e6b--- /dev/null+++ b/skills/taste-skill/references/pattern-vocabulary.md@@ -0,0 +1,79 @@+# Pattern Vocabulary++The full reference vocabulary of named design/motion patterns taste-skill should recognize and reach for. Section 12 (the Block Library, in SKILL.md) implements a subset of these with real code.++## 10. REFERENCE VOCABULARY (Pattern Names the Agent Should Know)++This is a vocabulary, not a library. The agent should KNOW these pattern names to communicate about them, design with them in mind, and reach for them when the design read calls for them. **Implementations and code sketches live in the Block Library (Section 12), which is populated iteratively.**++### Hero Paradigms+* **Asymmetric Split Hero** - Text on one side, asset on the other, generous white space.+* **Editorial Manifesto Hero** - Large type, no asset, almost-poster.+* **Video / Media Mask Hero** - Type cut out as mask over video background.+* **Kinetic-Type Hero** - Animated typography as the primary visual.+* **Curtain-Reveal Hero** - Hero parts on scroll like a curtain.+* **Scroll-Pinned Hero** - Hero stays pinned while content scrolls behind.++### Navigation & Menus+* **Mac OS Dock Magnification** - Edge nav, icons scale fluidly on hover.+* **Magnetic Button** - Pulls toward cursor.+* **Gooey Menu** - Sub-items detach like viscous liquid.+* **Dynamic Island** - Morphing pill for status / alerts.+* **Contextual Radial Menu** - Circular menu expanding at click point.+* **Floating Speed Dial** - FAB springing into curved secondary actions.+* **Mega Menu Reveal** - Full-screen dropdown, stagger-fade content.++### Layout & Grids+* **Bento Grid** - Asymmetric tile grouping (Apple Control Center).+* **Masonry Layout** - Staggered grid, no fixed row height.+* **Chroma Grid** - Borders / tiles with subtle animating gradients.+* **Split-Screen Scroll** - Two halves sliding in opposite directions.+* **Sticky-Stack Sections** - Sections that pin and stack on scroll.++### Cards & Containers+* **Parallax Tilt Card** - 3D tilt tracking mouse coordinates.+* **Spotlight Border Card** - Borders illuminate under cursor.+* **Glassmorphism Panel** - Frosted glass with inner refraction.+* **Holographic Foil Card** - Iridescent rainbow shift on hover.+* **Tinder Swipe Stack** - Physical card stack, swipe-away.+* **Morphing Modal** - Button expands into its own dialog.++### Scroll Animations+* **Sticky Scroll Stack** - Cards stick and physically stack.+* **Horizontal Scroll Hijack** - Vertical scroll → horizontal pan.+* **Locomotive / Sequence Scroll** - Video / 3D sequence tied to scrollbar.+* **Zoom Parallax** - Central background image zooming on scroll.+* **Scroll Progress Path** - SVG line drawing along scroll.+* **Liquid Swipe Transition** - Page transition like viscous liquid.++### Galleries & Media+* **Dome Gallery** - 3D panoramic gallery.+* **Coverflow Carousel** - 3D carousel with angled edges.+* **Drag-to-Pan Grid** - Boundless draggable canvas.+* **Accordion Image Slider** - Narrow strips expanding on hover.+* **Hover Image Trail** - Mouse leaves popping image trail.+* **Glitch Effect Image** - RGB-channel shift on hover.++### Typography & Text+* **Kinetic Marquee** - Endless text bands reversing on scroll.+* **Text Mask Reveal** - Massive type as transparent window to video.+* **Text Scramble Effect** - Matrix-style decoding on load / hover.+* **Circular Text Path** - Text curving along spinning circle.+* **Gradient Stroke Animation** - Outlined text with running gradient.+* **Kinetic Typography Grid** - Letters dodging the cursor.++### Micro-Interactions & Effects+* **Particle Explosion Button** - CTA shatters into particles on success.+* **Liquid Pull-to-Refresh** - Reload indicator like detaching droplets.+* **Skeleton Shimmer** - Shifting light reflection across placeholders.+* **Directional Hover-Aware Button** - Fill enters from cursor's exact side.+* **Ripple Click Effect** - Wave from click coordinates.+* **Animated SVG Line Drawing** - Vectors drawing themselves in real time.+* **Mesh Gradient Background** - Organic lava-lamp blobs.+* **Lens Blur Depth** - Background UI blurred to focus foreground action.++### Animation Library Choice+* **Motion (`motion/react`)** - default for UI / Bento / state-change motion.+* **GSAP + ScrollTrigger** - for full-page scrolltelling and scroll hijacks. Isolate in dedicated leaf components with `useEffect` cleanup.+* **Three.js / WebGL** - for canvas backgrounds and 3D scenes. Same isolation rule.+* **NEVER mix GSAP / Three.js with Motion in the same component tree.** They fight over the same frames.diff --git a/skills/team-brief/SKILL.md b/skills/team-brief/SKILL.mdindex 1e2ee9b..b3c590f 100644--- a/skills/team-brief/SKILL.md+++ b/skills/team-brief/SKILL.md@@ -74,290 +74,25 @@ When `/daily-brief` is invoked, the orchestrator (main agent) should:**Launch ALL of these agents in a single message using the Task tool with `run_in_background: true`:**#### Agent 1: "github-analyst" (subagent_type: general-purpose)-```-Query GitHub for dev team activity on [CUSTOMIZE: your-org/your-repo].-Lookback start date: [INSERT LOOKBACK_DATE].-Today's date: [INSERT TODAY_DATE].-Brief type: [Daily Brief / Week Start Brief (Monday)]--Run these gh CLI commands (all date filters use LOOKBACK_DATE as the start):--1. PRs merged since lookback:- gh pr list --repo [CUSTOMIZE: your-org/your-repo] --state merged --search "merged:>=[LOOKBACK_DATE]" --json number,title,author,mergedAt,labels --limit 50--2. PRs opened since lookback:- gh pr list --repo [CUSTOMIZE: your-org/your-repo] --state open --search "created:>=[LOOKBACK_DATE]" --json number,title,author,createdAt,labels --limit 20--3. ALL open PRs (for stale PR detection):- gh pr list --repo [CUSTOMIZE: your-org/your-repo] --state open --json number,title,author,createdAt,reviewDecision,labels,updatedAt --limit 50--4. PR review comments since lookback (to cross-reference with Slack discussions):- gh api repos/[CUSTOMIZE: your-org/your-repo]/pulls/comments --jq '[.[] | select(.created_at >= "[LOOKBACK_DATE]")] | .[] | {pr_url: .pull_request_url, body: .body[0:200], user: .user.login, created_at: .created_at}'--5. Issues closed since lookback:- gh issue list --repo [CUSTOMIZE: your-org/your-repo] --state closed --search "closed:>=[LOOKBACK_DATE]" --json number,title,labels --limit 20--6. Issues opened since lookback:- gh issue list --repo [CUSTOMIZE: your-org/your-repo] --state open --search "created:>=[LOOKBACK_DATE]" --json number,title,labels --limit 20--7. Commits since lookback:- gh api repos/[CUSTOMIZE: your-org/your-repo]/commits --jq '[.[] | select(.commit.author.date >= "[LOOKBACK_DATE]")] | .[] | {sha: .sha[0:7], message: .commit.message | split("\n")[0], author: .commit.author.name, date: .commit.author.date}'--ANALYSIS REQUIRED — Don't just list data, provide insights:--A) **Stale PR Detection**: Flag any open PR created more than 3 days ago with no review decision or with CHANGES_REQUESTED for more than 2 days. Calculate days since creation/last update.--B) **Velocity Snapshot**: How many PRs merged, commits pushed, contributors active. If Monday (weekend window), note the multi-day period and don't compare to a single-day baseline — instead comment on weekend activity level (busy weekend vs. quiet weekend).--C) **Review Bottleneck**: Count PRs waiting for review (REVIEW_REQUIRED). If >5, flag as bottleneck.--D) **PR Comment Themes**: Summarize the key topics being discussed in PR reviews (architecture concerns, bugs, design patterns, etc.)--Return structured data AND insights.-```+Prompt: see `references/agent-prompts.md` § github-analyst.#### Agent 2: "slack-monitor" (subagent_type: general-purpose)*Only spawn if Slack MCP is available*-```-Check Slack [CUSTOMIZE: your-team-channel] channel for key discussions since [LOOKBACK_DATE].-Brief type: [Daily Brief / Week Start Brief (Monday)]-If Monday: cover Friday through Sunday — there may be more threads than usual.--Instructions:-1. Use ToolSearch to load Slack tools-2. Read recent messages from [CUSTOMIZE: your-team-channel] channel (get enough to cover since [LOOKBACK_DATE])-3. For each significant discussion thread, extract:- - Topic / what was discussed- - Decisions made or agreements reached- - Action items mentioned (who agreed to do what)- - Blockers raised- - Customer feedback or external links shared- - Any specific features, PRs, or technical topics referenced--CRITICAL: For each action item or decision, note:-- WHO is responsible-- WHAT they agreed to do-- Whether it references a specific PR, feature, or technical area--Also extract:-- Links shared (competitive intel, articles, tools)-- Questions that were asked but NOT answered-- Discussions that seemed unresolved--Return structured output with clear separation between:-1. Decisions & Agreements (with responsible person)-2. Action Items (with owner)-3. Blockers & Escalations-4. Unresolved Discussions-5. External Links & Intel Shared-6. Feature/Technical Topics Discussed (for cross-referencing with GitHub)-```+Prompt: see `references/agent-prompts.md` § slack-monitor.#### Agent 3: "meeting-reviewer" (subagent_type: general-purpose)-```-Check for meeting notes and standup notes since [LOOKBACK_DATE].-Brief type: [Daily Brief / Week Start Brief (Monday)]-If Monday: check Friday, Saturday, and Sunday for any meeting notes.--Instructions:-1. Look for meeting files in [CUSTOMIZE: path/to/meetings/] with dates from [LOOKBACK_DATE] through today-2. Use Glob to find files: [CUSTOMIZE: path/to/meetings/][LOOKBACK_DATE]*.md (and if Monday, also check Saturday and Sunday dates)-3. Also check [CUSTOMIZE: path/to/checkins/] for recent daily checkins-4. Read any found files--For each meeting/standup found, extract:-- Decisions made-- Action items assigned (WHO + WHAT)-- Features or changes discussed-- Priorities set-- Deadlines mentioned-- Any commitments like "I'll make a quick change to X" or "Let's update Y today"--Return structured list of:-1. Meeting summaries with date-2. All action items with owners-3. All discussed features/changes (for cross-referencing with GitHub PRs/commits and Linear issues)-4. Priorities and deadlines mentioned-```+Prompt: see `references/agent-prompts.md` § meeting-reviewer.#### Agent 4: "linear-tracker" (subagent_type: general-purpose)*Only spawn if Linear MCP is available*-```-Query Linear for work tracking data since [LOOKBACK_DATE].-Brief type: [Daily Brief / Week Start Brief (Monday)]-If Monday: cover Friday through Sunday.--=== CONTEXT OPTIMIZATION RULES (CRITICAL — reduces token usage by ~70%) ===--**DEFAULT FILTERS — apply to ALL list_issues calls:**-- ALWAYS exclude issues with state "Done", "Completed", "Canceled", or "Archived" UNLESS they were updated since [LOOKBACK_DATE] (i.e., only show recently-completed wins, not old closed work).-- ALWAYS set limit: 50 on any list call to prevent overflow.-- NEVER make redundant queries — if you already fetched issues updated since lookback, do NOT re-fetch the same issues in a separate "completed" query. Filter from the data you already have.--**DATA EXTRACTION — from every API response, extract ONLY these fields per issue:**-- identifier (e.g., [CUSTOMIZE: PROJ]-123)-- title-- state (name only)-- priority (number + label)-- assignee (name only)-- updatedAt-- project (name only)-- labels (names only)--Discard everything else (full descriptions, URLs, metadata blobs, nested objects). This is critical — raw Linear responses are 50-100KB each and most of that data is unused.--**QUERY CONSOLIDATION — use minimal API calls:**-Do NOT make 5+ separate list_issues calls. Instead:--Instructions:-1. Use ToolSearch to load Linear tools (search "+linear list issues", "+linear list initiatives", "+linear list milestones", "+linear list projects")-2. Query the following data using Linear MCP tools:-- === ISSUE-LEVEL DATA (2-3 calls max) ===-- a) Issues updated since lookback (THE main query — covers most needs):- Use mcp__claude_ai_Linear__list_issues with updatedAt: "[LOOKBACK_DATE]", limit: 50.- From this ONE response, extract: recently completed issues (wins), issues that moved to In Progress, issues still in Todo, new issues created.-- b) High-priority/urgent + blocked issues (only if not already captured above):- Use mcp__claude_ai_Linear__list_issues with priority: 1 (Urgent), limit: 30.- Only query this separately if the main query didn't surface urgent items.-- c) Blocked/stuck issues:- Look for issues with state "blocked" or "In Progress" with no updates in >2 days. Use the data from query (a) first — only make a separate query if needed.-- === CYCLE & SPRINT DATA (1 call) ===-- d) Current cycle progress:- Use mcp__claude_ai_Linear__list_teams to get team IDs, then mcp__claude_ai_Linear__list_cycles with type: "current" for each team. This shows sprint/cycle health.-- === INITIATIVE DATA (1-2 calls) ===-- e) All active initiatives:- Use mcp__claude_ai_Linear__list_initiatives with includeProjects: true to get initiative names, target dates, health status, progress, and linked projects.- Do NOT call get_initiative for each individual initiative — the list call with includeProjects gives enough data.-- === PROJECT DATA (SKIP separate call) ===-- f) Project data comes from the initiatives query above (includeProjects: true). Do NOT make a separate list_projects call — it returns ~37KB of mostly unused data.-- === MILESTONE DATA (1 call only if needed) ===-- g) Only query milestones if an initiative is At Risk or has an approaching target date (≤14 days). Otherwise skip — milestone data is verbose and rarely actionable day-to-day.--3. For each significant issue, note ONLY:- - Issue identifier, title, assignee name, status, priority, project name- - Whether it has linked PRs (just note yes/no + PR number, don't include full URLs)--4. Build an INITIATIVE HEALTH MAP from the data you already have (do NOT make additional queries):- For each initiative, compile:- - Total issues across linked projects (completed / in-progress / todo / blocked)- - Projects status breakdown- - Key blockers- - Days until target date--ANALYSIS REQUIRED:-A) **Cycle Health**: What % of the current cycle is complete? Are we on pace? How many issues remain vs. days left?-B) **Work Distribution**: Who has the most issues assigned? Anyone overloaded or idle?-C) **Blocked Items**: List anything stuck with reasons if available.-D) **Priority Mismatches**: Any urgent/high-priority issues with no recent activity? Flag them.-E) **New Work vs Planned**: How many issues were created since lookback vs. what was already planned in the cycle? Is scope creeping?-F) **Completed Work**: Celebrate — list what got done and by whom.-G) **Initiative Progress**: For each initiative, report health (on track / at risk / off track) based on:- - % of issues completed vs. days remaining to target date- - Number of blocked items- - Whether projects under the initiative are progressing-H) **Milestone Status**: Only flag milestones that are overdue or at risk. Skip healthy milestones.-I) **Project Rollup**: For each project, summarize progress % and whether it's contributing to initiative goals.--Return structured data AND insights, including the initiative health map.-IMPORTANT: Your total output should be under 5KB of text. Summarize, don't dump raw data.-```+Prompt: see `references/agent-prompts.md` § linear-tracker.#### Agent 5: "braindump-reviewer" (subagent_type: general-purpose)-```-Check for recent braindumps since [LOOKBACK_DATE].-Brief type: [Daily Brief / Week Start Brief (Monday)]-If Monday: check Friday through Sunday.--Instructions:-1. Use Glob to find braindump files matching recent dates:- - [CUSTOMIZE: path/to/braindumps/]braindump-[LOOKBACK_DATE through TODAY]*.md-2. Read any found files--For each braindump found, extract:-- Core themes and strategic thinking-- Decisions being considered or made-- Product direction signals-- Concerns or risks flagged-- Ideas that should be connected to current work-- Any references to specific features, PRs, or team members--Return structured list of:-1. Braindump summaries with date and source-2. Strategic insights and product direction signals-3. Concerns/risks that should appear in the brief-4. Connections to current engineering work (for cross-referencing with GitHub/Linear)-```+Prompt: see `references/agent-prompts.md` § braindump-reviewer.#### Agent 6: "posthog-analyst" (subagent_type: general-purpose)*Only spawn if PostHog MCP is available*-```-Query PostHog for HIGH-LEVEL product metrics only.-Project ID: [CUSTOMIZE: your-posthog-project-id], Dashboard ID: [CUSTOMIZE: your-posthog-dashboard-id].-Lookback start date: [INSERT LOOKBACK_DATE].-Today's date: [INSERT TODAY_DATE].-Brief type: [Daily Brief / Week Start Brief (Monday)]--=== CONTEXT OPTIMIZATION RULES (CRITICAL) ===-- DO NOT query for errors or error details. Skip list-errors entirely.-- DO NOT fetch insights-get-all (returns huge payload of all saved insights). Only use the dashboard.-- DO NOT include raw query results in your output. Summarize into 1-2 lines per metric.-- Your total output should be under 3KB of text.--Instructions:-1. Use ToolSearch to load PostHog tools (search "+posthog")-2. Run ONLY these queries:-- === DASHBOARD OVERVIEW (1 call) ===-- a) Get the main dashboard:- Use mcp__posthog__dashboard-get with dashboard_id: [CUSTOMIZE: your-posthog-dashboard-id].- Extract only: visitor count, signup count, core event count, and any trend data shown.-- === KEY METRICS (3 HogQL queries — combine into period comparison) ===-- b) Current period metrics (single combined query):- Use mcp__posthog__query-run with a HogQL query:- SELECT- countIf(DISTINCT person_id, event = '$pageview') as visitors,- countIf(event = '$pageview') as pageviews,- countIf(DISTINCT person_id, event = 'user_signed_up') as signups,- countIf(event = '[CUSTOMIZE: your_core_event]') as core_events,- countIf(DISTINCT person_id, event = '[CUSTOMIZE: your_core_event]') as core_event_users- FROM events- WHERE timestamp >= '[LOOKBACK_DATE]'-- c) Previous period metrics (for % change calculation):- Run the same query for the PREVIOUS equivalent period.- If daily: day before lookback. If Monday (Fri-Sun): previous Fri-Sun.-- d) Top features (lightweight):- Use mcp__posthog__query-run:- SELECT event, count() as count, count(DISTINCT person_id) as unique_users- FROM events- WHERE timestamp >= '[LOOKBACK_DATE]' AND event NOT LIKE '$%'- GROUP BY event ORDER BY count DESC LIMIT 10--ANALYSIS — Return ONLY high-level insights (no raw data dumps):--A) **Metric Summary**: 1 line each for visitors, sign-ups, core events with ↑↓→ trend and % change.-B) **Anomalies**: Only flag metrics with >20% change. If none, say "No anomalies."-C) **Top Features**: List top 5 features by usage, 1 line each.-D) **One-liner Assessment**: "Product health: [good/concerning/needs attention] — [why in 1 sentence]"--Return a concise summary, NOT raw query results. Target ~1KB output max.-```+Prompt: see `references/agent-prompts.md` § posthog-analyst.### Phase 3: Assembly & Cross-Reference Synthesis (Orchestrator — After All Agents Complete)@@ -522,27 +257,7 @@ The HackMD API token is stored in `.claude/settings/hackmd-token` (one line, no4. **If HackMD API fails**, log the error and continue — the brief should still be posted to Slack without the link. Note in the Slack message: "(HackMD link unavailable)"-**Implementation pattern (Bash):**-```bash-# Step 1: Create note-curl -s -X POST 'https://api.hackmd.io/v1/notes' \- -H "Authorization: Bearer $HACKMD_API_TOKEN" \- -H 'Content-Type: application/json' \- -d '{"title":"...","readPermission":"owner","writePermission":"owner","commentPermission":"disabled","content":"placeholder"}'--# Step 2: Prepare payload and update-python3 -c "-import json-with open('[CUSTOMIZE: path/to/briefs/]daily-brief-YYYY-MM-DD.md') as f:- content = f.read()-with open('/tmp/hackmd-payload.json', 'w') as f:- json.dump({'content': content}, f)-"-curl -s -X PATCH "https://api.hackmd.io/v1/notes/<id>" \- -H "Authorization: Bearer $HACKMD_API_TOKEN" \- -H 'Content-Type: application/json' \- -d @/tmp/hackmd-payload.json-```+**Implementation pattern (Bash):** see `references/publish-templates.md` § HackMD implementation pattern (Bash).### Phase 4: Slack Highlights (After brief is saved — preview before posting)@@ -556,79 +271,9 @@ After presenting the brief summary to the user, **always compose and show the Sl3. **Slack message format** (adapt based on actual content — this is a template, not a rigid format):-**For Monday (Week Start Brief):**-```-:calendar: *Week Start Brief — [DATE] (covering Fri–Sun)*--*Weekend recap:* [X] PRs merged since Friday. [Brief summary of what got done.] :rocket:--*What shipped:*-• [Feature/PR 1 with <https://github.com/[CUSTOMIZE: your-org/your-repo]/pull/XXX|#XXX> link] — [1-line description]-• [Feature/PR 2 with link] — [1-line description]-• [Feature/PR 3 with link] — [1-line description]-------:rotating_light: *Heads up:*-• [Most important alert with PR links and context]-• [Second alert — include who's involved and what's needed]-• [Third alert if relevant]-------:mag: *Key discussions from Slack:*-• *[Topic 1]:* [2-3 sentence summary of the discussion, decisions made, and any open questions.]-• *[Topic 2]:* [Summary with context]--:clipboard: *Open action items:*-• [Person] — [What they need to do] ([source: meeting/Slack thread])-• [Person] — [What they need to do]-------:bar_chart: *Product pulse:*-• [X] visitors ([↑/↓X%]), [X] sign-ups, [X] core events ([↑/↓X%]) | [Any notable anomaly]--:chart_with_upwards_trend: *This week's focus:*-• [Key priority or theme for the week]--:zap: *Quick wins:*-• <https://github.com/[CUSTOMIZE: your-org/your-repo]/pull/XXX|#XXX> and <...|#YYY> are approved — just need someone to merge.+**For Monday (Week Start Brief):** full template in `references/publish-templates.md` § Slack message format — Monday (Week Start Brief).-:link: *Full brief:* [HACKMD_PUBLISH_LINK]-```--**For regular days:**-```-:newspaper: *Daily Brief — [DATE]*--*What shipped:* [X] PRs merged. :rocket:-• [Feature/PR 1 with <https://github.com/[CUSTOMIZE: your-org/your-repo]/pull/XXX|#XXX> link] — [1-line description]-• [Feature/PR 2 with link] — [1-line description]-------:rotating_light: *Heads up:*-• [Alert 1 with PR links, context, and who needs to act]-• [Alert 2 with details]-------:mag: *Key discussions:*-• *[Topic]:* [2-3 sentence summary — what was discussed, any decisions, open questions.]--:clipboard: *Action items:*-• [Person] — [Task] ([from meeting/Slack])-------:bar_chart: *Product pulse:* [X] visitors ([↑/↓X%]) | [X] core events ([↑/↓X%]) | [Any notable anomaly]--:zap: *Quick wins:*-• <https://github.com/[CUSTOMIZE: your-org/your-repo]/pull/XXX|#XXX> and <...|#YYY> are approved — just need someone to merge.--:link: *Full brief:* [HACKMD_PUBLISH_LINK]-```+**For regular days:** full template in `references/publish-templates.md` § Slack message format — regular days.4. **Rules for the Slack message:**- Max 30 lines for Monday briefs, max 20 lines for regular days. More detail than before, but still scannable.@@ -755,65 +400,7 @@ Action items from recent meetings tracked against actual GitHub/Slack/Linear act---## Metadata Template-```yaml-----type: daily-brief-brief_type: daily / week-start # "week-start" if Monday, "daily" otherwise-domain: shared-date: YYYY-MM-DD-lookback_from: YYYY-MM-DD # Friday's date if Monday, yesterday otherwise-created: YYYY-MM-DD HH:MM-tags:- - daily-brief- - team-intelligence-data_sources:- github: true- slack: true/false- linear: true/false- posthog: true/false- meetings: true/false- braindumps: true/false-linear_sync:- issues_synced: X- prs_linked: X- initiative_updates_posted: X- milestones_flagged: X- errors: []-initiatives:- - name: "[CUSTOMIZE: Your Initiative 1]"- health: on_track / at_risk / off_track- progress_pct: X- days_remaining: X- projects_count: X- blocked_issues: X- - name: "[CUSTOMIZE: Your Initiative 2]"- health: on_track / at_risk / off_track- progress_pct: X- days_remaining: X- projects_count: X- blocked_issues: X-linear_cycle:- name: "Cycle X"- progress_pct: X- days_remaining: X- scope_changes: X # issues added mid-cycle-posthog_metrics:- visitors: X- visitors_change_pct: X # vs previous period- signups: X- signups_change_pct: X- core_events: X- core_events_change_pct: X- new_errors: X- top_feature: "feature_name"- anomalies: [] # list of metrics with >20% change-hackmd_url: "" # HackMD publish link, populated in Phase 3.7-stale_prs: X-review_bottleneck: true/false-missing_followups: X-linear_blocked_issues: X-----```+Full YAML frontmatter template for the saved brief file: `references/brief-frontmatter.md`.## Synthesis Rulesdiff --git a/skills/team-brief/references/agent-prompts.md b/skills/team-brief/references/agent-prompts.mdnew file mode 100644index 0000000..b6ad88d--- /dev/null+++ b/skills/team-brief/references/agent-prompts.md@@ -0,0 +1,286 @@+# Team Brief — Phase 2 Agent Prompts++Verbatim sub-agent prompts for the six Phase 2 parallel data-collection agents. Referenced from SKILL.md's `### Phase 2: Parallel Data Collection` section — read this file once you're ready to fill in and dispatch the actual Task calls.++## github-analyst+```+Query GitHub for dev team activity on [CUSTOMIZE: your-org/your-repo].+Lookback start date: [INSERT LOOKBACK_DATE].+Today's date: [INSERT TODAY_DATE].+Brief type: [Daily Brief / Week Start Brief (Monday)]++Run these gh CLI commands (all date filters use LOOKBACK_DATE as the start):++1. PRs merged since lookback:+ gh pr list --repo [CUSTOMIZE: your-org/your-repo] --state merged --search "merged:>=[LOOKBACK_DATE]" --json number,title,author,mergedAt,labels --limit 50++2. PRs opened since lookback:+ gh pr list --repo [CUSTOMIZE: your-org/your-repo] --state open --search "created:>=[LOOKBACK_DATE]" --json number,title,author,createdAt,labels --limit 20++3. ALL open PRs (for stale PR detection):+ gh pr list --repo [CUSTOMIZE: your-org/your-repo] --state open --json number,title,author,createdAt,reviewDecision,labels,updatedAt --limit 50++4. PR review comments since lookback (to cross-reference with Slack discussions):+ gh api repos/[CUSTOMIZE: your-org/your-repo]/pulls/comments --jq '[.[] | select(.created_at >= "[LOOKBACK_DATE]")] | .[] | {pr_url: .pull_request_url, body: .body[0:200], user: .user.login, created_at: .created_at}'++5. Issues closed since lookback:+ gh issue list --repo [CUSTOMIZE: your-org/your-repo] --state closed --search "closed:>=[LOOKBACK_DATE]" --json number,title,labels --limit 20++6. Issues opened since lookback:+ gh issue list --repo [CUSTOMIZE: your-org/your-repo] --state open --search "created:>=[LOOKBACK_DATE]" --json number,title,labels --limit 20++7. Commits since lookback:+ gh api repos/[CUSTOMIZE: your-org/your-repo]/commits --jq '[.[] | select(.commit.author.date >= "[LOOKBACK_DATE]")] | .[] | {sha: .sha[0:7], message: .commit.message | split("\n")[0], author: .commit.author.name, date: .commit.author.date}'++ANALYSIS REQUIRED — Don't just list data, provide insights:++A) **Stale PR Detection**: Flag any open PR created more than 3 days ago with no review decision or with CHANGES_REQUESTED for more than 2 days. Calculate days since creation/last update.++B) **Velocity Snapshot**: How many PRs merged, commits pushed, contributors active. If Monday (weekend window), note the multi-day period and don't compare to a single-day baseline — instead comment on weekend activity level (busy weekend vs. quiet weekend).++C) **Review Bottleneck**: Count PRs waiting for review (REVIEW_REQUIRED). If >5, flag as bottleneck.++D) **PR Comment Themes**: Summarize the key topics being discussed in PR reviews (architecture concerns, bugs, design patterns, etc.)++Return structured data AND insights.+```++## slack-monitor+```+Check Slack [CUSTOMIZE: your-team-channel] channel for key discussions since [LOOKBACK_DATE].+Brief type: [Daily Brief / Week Start Brief (Monday)]+If Monday: cover Friday through Sunday — there may be more threads than usual.++Instructions:+1. Use ToolSearch to load Slack tools+2. Read recent messages from [CUSTOMIZE: your-team-channel] channel (get enough to cover since [LOOKBACK_DATE])+3. For each significant discussion thread, extract:+ - Topic / what was discussed+ - Decisions made or agreements reached+ - Action items mentioned (who agreed to do what)+ - Blockers raised+ - Customer feedback or external links shared+ - Any specific features, PRs, or technical topics referenced++CRITICAL: For each action item or decision, note:+- WHO is responsible+- WHAT they agreed to do+- Whether it references a specific PR, feature, or technical area++Also extract:+- Links shared (competitive intel, articles, tools)+- Questions that were asked but NOT answered+- Discussions that seemed unresolved++Return structured output with clear separation between:+1. Decisions & Agreements (with responsible person)+2. Action Items (with owner)+3. Blockers & Escalations+4. Unresolved Discussions+5. External Links & Intel Shared+6. Feature/Technical Topics Discussed (for cross-referencing with GitHub)+```++## meeting-reviewer+```+Check for meeting notes and standup notes since [LOOKBACK_DATE].+Brief type: [Daily Brief / Week Start Brief (Monday)]+If Monday: check Friday, Saturday, and Sunday for any meeting notes.++Instructions:+1. Look for meeting files in [CUSTOMIZE: path/to/meetings/] with dates from [LOOKBACK_DATE] through today+2. Use Glob to find files: [CUSTOMIZE: path/to/meetings/][LOOKBACK_DATE]*.md (and if Monday, also check Saturday and Sunday dates)+3. Also check [CUSTOMIZE: path/to/checkins/] for recent daily checkins+4. Read any found files++For each meeting/standup found, extract:+- Decisions made+- Action items assigned (WHO + WHAT)+- Features or changes discussed+- Priorities set+- Deadlines mentioned+- Any commitments like "I'll make a quick change to X" or "Let's update Y today"++Return structured list of:+1. Meeting summaries with date+2. All action items with owners+3. All discussed features/changes (for cross-referencing with GitHub PRs/commits and Linear issues)+4. Priorities and deadlines mentioned+```++## linear-tracker+```+Query Linear for work tracking data since [LOOKBACK_DATE].+Brief type: [Daily Brief / Week Start Brief (Monday)]+If Monday: cover Friday through Sunday.++=== CONTEXT OPTIMIZATION RULES (CRITICAL — reduces token usage by ~70%) ===++**DEFAULT FILTERS — apply to ALL list_issues calls:**+- ALWAYS exclude issues with state "Done", "Completed", "Canceled", or "Archived" UNLESS they were updated since [LOOKBACK_DATE] (i.e., only show recently-completed wins, not old closed work).+- ALWAYS set limit: 50 on any list call to prevent overflow.+- NEVER make redundant queries — if you already fetched issues updated since lookback, do NOT re-fetch the same issues in a separate "completed" query. Filter from the data you already have.++**DATA EXTRACTION — from every API response, extract ONLY these fields per issue:**+- identifier (e.g., [CUSTOMIZE: PROJ]-123)+- title+- state (name only)+- priority (number + label)+- assignee (name only)+- updatedAt+- project (name only)+- labels (names only)++Discard everything else (full descriptions, URLs, metadata blobs, nested objects). This is critical — raw Linear responses are 50-100KB each and most of that data is unused.++**QUERY CONSOLIDATION — use minimal API calls:**+Do NOT make 5+ separate list_issues calls. Instead:++Instructions:+1. Use ToolSearch to load Linear tools (search "+linear list issues", "+linear list initiatives", "+linear list milestones", "+linear list projects")+2. Query the following data using Linear MCP tools:++ === ISSUE-LEVEL DATA (2-3 calls max) ===++ a) Issues updated since lookback (THE main query — covers most needs):+ Use mcp__claude_ai_Linear__list_issues with updatedAt: "[LOOKBACK_DATE]", limit: 50.+ From this ONE response, extract: recently completed issues (wins), issues that moved to In Progress, issues still in Todo, new issues created.++ b) High-priority/urgent + blocked issues (only if not already captured above):+ Use mcp__claude_ai_Linear__list_issues with priority: 1 (Urgent), limit: 30.+ Only query this separately if the main query didn't surface urgent items.++ c) Blocked/stuck issues:+ Look for issues with state "blocked" or "In Progress" with no updates in >2 days. Use the data from query (a) first — only make a separate query if needed.++ === CYCLE & SPRINT DATA (1 call) ===++ d) Current cycle progress:+ Use mcp__claude_ai_Linear__list_teams to get team IDs, then mcp__claude_ai_Linear__list_cycles with type: "current" for each team. This shows sprint/cycle health.++ === INITIATIVE DATA (1-2 calls) ===++ e) All active initiatives:+ Use mcp__claude_ai_Linear__list_initiatives with includeProjects: true to get initiative names, target dates, health status, progress, and linked projects.+ Do NOT call get_initiative for each individual initiative — the list call with includeProjects gives enough data.++ === PROJECT DATA (SKIP separate call) ===++ f) Project data comes from the initiatives query above (includeProjects: true). Do NOT make a separate list_projects call — it returns ~37KB of mostly unused data.++ === MILESTONE DATA (1 call only if needed) ===++ g) Only query milestones if an initiative is At Risk or has an approaching target date (≤14 days). Otherwise skip — milestone data is verbose and rarely actionable day-to-day.++3. For each significant issue, note ONLY:+ - Issue identifier, title, assignee name, status, priority, project name+ - Whether it has linked PRs (just note yes/no + PR number, don't include full URLs)++4. Build an INITIATIVE HEALTH MAP from the data you already have (do NOT make additional queries):+ For each initiative, compile:+ - Total issues across linked projects (completed / in-progress / todo / blocked)+ - Projects status breakdown+ - Key blockers+ - Days until target date++ANALYSIS REQUIRED:+A) **Cycle Health**: What % of the current cycle is complete? Are we on pace? How many issues remain vs. days left?+B) **Work Distribution**: Who has the most issues assigned? Anyone overloaded or idle?+C) **Blocked Items**: List anything stuck with reasons if available.+D) **Priority Mismatches**: Any urgent/high-priority issues with no recent activity? Flag them.+E) **New Work vs Planned**: How many issues were created since lookback vs. what was already planned in the cycle? Is scope creeping?+F) **Completed Work**: Celebrate — list what got done and by whom.+G) **Initiative Progress**: For each initiative, report health (on track / at risk / off track) based on:+ - % of issues completed vs. days remaining to target date+ - Number of blocked items+ - Whether projects under the initiative are progressing+H) **Milestone Status**: Only flag milestones that are overdue or at risk. Skip healthy milestones.+I) **Project Rollup**: For each project, summarize progress % and whether it's contributing to initiative goals.++Return structured data AND insights, including the initiative health map.+IMPORTANT: Your total output should be under 5KB of text. Summarize, don't dump raw data.+```++## braindump-reviewer+```+Check for recent braindumps since [LOOKBACK_DATE].+Brief type: [Daily Brief / Week Start Brief (Monday)]+If Monday: check Friday through Sunday.++Instructions:+1. Use Glob to find braindump files matching recent dates:+ - [CUSTOMIZE: path/to/braindumps/]braindump-[LOOKBACK_DATE through TODAY]*.md+2. Read any found files++For each braindump found, extract:+- Core themes and strategic thinking+- Decisions being considered or made+- Product direction signals+- Concerns or risks flagged+- Ideas that should be connected to current work+- Any references to specific features, PRs, or team members++Return structured list of:+1. Braindump summaries with date and source+2. Strategic insights and product direction signals+3. Concerns/risks that should appear in the brief+4. Connections to current engineering work (for cross-referencing with GitHub/Linear)+```++## posthog-analyst+```+Query PostHog for HIGH-LEVEL product metrics only.+Project ID: [CUSTOMIZE: your-posthog-project-id], Dashboard ID: [CUSTOMIZE: your-posthog-dashboard-id].+Lookback start date: [INSERT LOOKBACK_DATE].+Today's date: [INSERT TODAY_DATE].+Brief type: [Daily Brief / Week Start Brief (Monday)]++=== CONTEXT OPTIMIZATION RULES (CRITICAL) ===+- DO NOT query for errors or error details. Skip list-errors entirely.+- DO NOT fetch insights-get-all (returns huge payload of all saved insights). Only use the dashboard.+- DO NOT include raw query results in your output. Summarize into 1-2 lines per metric.+- Your total output should be under 3KB of text.++Instructions:+1. Use ToolSearch to load PostHog tools (search "+posthog")+2. Run ONLY these queries:++ === DASHBOARD OVERVIEW (1 call) ===++ a) Get the main dashboard:+ Use mcp__posthog__dashboard-get with dashboard_id: [CUSTOMIZE: your-posthog-dashboard-id].+ Extract only: visitor count, signup count, core event count, and any trend data shown.++ === KEY METRICS (3 HogQL queries — combine into period comparison) ===++ b) Current period metrics (single combined query):+ Use mcp__posthog__query-run with a HogQL query:+ SELECT+ countIf(DISTINCT person_id, event = '$pageview') as visitors,+ countIf(event = '$pageview') as pageviews,+ countIf(DISTINCT person_id, event = 'user_signed_up') as signups,+ countIf(event = '[CUSTOMIZE: your_core_event]') as core_events,+ countIf(DISTINCT person_id, event = '[CUSTOMIZE: your_core_event]') as core_event_users+ FROM events+ WHERE timestamp >= '[LOOKBACK_DATE]'++ c) Previous period metrics (for % change calculation):+ Run the same query for the PREVIOUS equivalent period.+ If daily: day before lookback. If Monday (Fri-Sun): previous Fri-Sun.++ d) Top features (lightweight):+ Use mcp__posthog__query-run:+ SELECT event, count() as count, count(DISTINCT person_id) as unique_users+ FROM events+ WHERE timestamp >= '[LOOKBACK_DATE]' AND event NOT LIKE '$%'+ GROUP BY event ORDER BY count DESC LIMIT 10++ANALYSIS — Return ONLY high-level insights (no raw data dumps):++A) **Metric Summary**: 1 line each for visitors, sign-ups, core events with ↑↓→ trend and % change.+B) **Anomalies**: Only flag metrics with >20% change. If none, say "No anomalies."+C) **Top Features**: List top 5 features by usage, 1 line each.+D) **One-liner Assessment**: "Product health: [good/concerning/needs attention] — [why in 1 sentence]"++Return a concise summary, NOT raw query results. Target ~1KB output max.+```diff --git a/skills/team-brief/references/brief-frontmatter.md b/skills/team-brief/references/brief-frontmatter.mdnew file mode 100644index 0000000..461dbf6--- /dev/null+++ b/skills/team-brief/references/brief-frontmatter.md@@ -0,0 +1,63 @@+# Team Brief — Metadata Template++Verbatim YAML frontmatter template for the saved daily-brief markdown file, referenced from SKILL.md's `## Metadata Template` heading.++```yaml+---+type: daily-brief+brief_type: daily / week-start # "week-start" if Monday, "daily" otherwise+domain: shared+date: YYYY-MM-DD+lookback_from: YYYY-MM-DD # Friday's date if Monday, yesterday otherwise+created: YYYY-MM-DD HH:MM+tags:+ - daily-brief+ - team-intelligence+data_sources:+ github: true+ slack: true/false+ linear: true/false+ posthog: true/false+ meetings: true/false+ braindumps: true/false+linear_sync:+ issues_synced: X+ prs_linked: X+ initiative_updates_posted: X+ milestones_flagged: X+ errors: []+initiatives:+ - name: "[CUSTOMIZE: Your Initiative 1]"+ health: on_track / at_risk / off_track+ progress_pct: X+ days_remaining: X+ projects_count: X+ blocked_issues: X+ - name: "[CUSTOMIZE: Your Initiative 2]"+ health: on_track / at_risk / off_track+ progress_pct: X+ days_remaining: X+ projects_count: X+ blocked_issues: X+linear_cycle:+ name: "Cycle X"+ progress_pct: X+ days_remaining: X+ scope_changes: X # issues added mid-cycle+posthog_metrics:+ visitors: X+ visitors_change_pct: X # vs previous period+ signups: X+ signups_change_pct: X+ core_events: X+ core_events_change_pct: X+ new_errors: X+ top_feature: "feature_name"+ anomalies: [] # list of metrics with >20% change+hackmd_url: "" # HackMD publish link, populated in Phase 3.7+stale_prs: X+review_bottleneck: true/false+missing_followups: X+linear_blocked_issues: X+---+```diff --git a/skills/team-brief/references/publish-templates.md b/skills/team-brief/references/publish-templates.mdnew file mode 100644index 0000000..c3ca9be--- /dev/null+++ b/skills/team-brief/references/publish-templates.md@@ -0,0 +1,99 @@+# Team Brief — Publish Templates++Verbatim implementation snippets for publishing the brief: the HackMD bash pattern (Phase 3.7) and the two Phase 4 Slack message templates (Monday week-start vs. regular day).++## HackMD implementation pattern (Bash)+```bash+# Step 1: Create note+curl -s -X POST 'https://api.hackmd.io/v1/notes' \+ -H "Authorization: Bearer $HACKMD_API_TOKEN" \+ -H 'Content-Type: application/json' \+ -d '{"title":"...","readPermission":"owner","writePermission":"owner","commentPermission":"disabled","content":"placeholder"}'++# Step 2: Prepare payload and update+python3 -c "+import json+with open('[CUSTOMIZE: path/to/briefs/]daily-brief-YYYY-MM-DD.md') as f:+ content = f.read()+with open('/tmp/hackmd-payload.json', 'w') as f:+ json.dump({'content': content}, f)+"+curl -s -X PATCH "https://api.hackmd.io/v1/notes/<id>" \+ -H "Authorization: Bearer $HACKMD_API_TOKEN" \+ -H 'Content-Type: application/json' \+ -d @/tmp/hackmd-payload.json+```++## Slack message format — Monday (Week Start Brief)+```+:calendar: *Week Start Brief — [DATE] (covering Fri–Sun)*++*Weekend recap:* [X] PRs merged since Friday. [Brief summary of what got done.] :rocket:++*What shipped:*+• [Feature/PR 1 with <https://github.com/[CUSTOMIZE: your-org/your-repo]/pull/XXX|#XXX> link] — [1-line description]+• [Feature/PR 2 with link] — [1-line description]+• [Feature/PR 3 with link] — [1-line description]++---++:rotating_light: *Heads up:*+• [Most important alert with PR links and context]+• [Second alert — include who's involved and what's needed]+• [Third alert if relevant]++---++:mag: *Key discussions from Slack:*+• *[Topic 1]:* [2-3 sentence summary of the discussion, decisions made, and any open questions.]+• *[Topic 2]:* [Summary with context]++:clipboard: *Open action items:*+• [Person] — [What they need to do] ([source: meeting/Slack thread])+• [Person] — [What they need to do]++---++:bar_chart: *Product pulse:*+• [X] visitors ([↑/↓X%]), [X] sign-ups, [X] core events ([↑/↓X%]) | [Any notable anomaly]++:chart_with_upwards_trend: *This week's focus:*+• [Key priority or theme for the week]++:zap: *Quick wins:*+• <https://github.com/[CUSTOMIZE: your-org/your-repo]/pull/XXX|#XXX> and <...|#YYY> are approved — just need someone to merge.++:link: *Full brief:* [HACKMD_PUBLISH_LINK]+```++## Slack message format — regular days+```+:newspaper: *Daily Brief — [DATE]*++*What shipped:* [X] PRs merged. :rocket:+• [Feature/PR 1 with <https://github.com/[CUSTOMIZE: your-org/your-repo]/pull/XXX|#XXX> link] — [1-line description]+• [Feature/PR 2 with link] — [1-line description]++---++:rotating_light: *Heads up:*+• [Alert 1 with PR links, context, and who needs to act]+• [Alert 2 with details]++---++:mag: *Key discussions:*+• *[Topic]:* [2-3 sentence summary — what was discussed, any decisions, open questions.]++:clipboard: *Action items:*+• [Person] — [Task] ([from meeting/Slack])++---++:bar_chart: *Product pulse:* [X] visitors ([↑/↓X%]) | [X] core events ([↑/↓X%]) | [Any notable anomaly]++:zap: *Quick wins:*+• <https://github.com/[CUSTOMIZE: your-org/your-repo]/pull/XXX|#XXX> and <...|#YYY> are approved — just need someone to merge.++:link: *Full brief:* [HACKMD_PUBLISH_LINK]+```