Skip to content

armgit / ECC

Public Imported from GitHub
0

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

feat(skills): add product-specific UI quality gate

Samuel Bushiba6429c0f229
diff --git a/.claude-plugin/marketplace.json b/.claude-plugin/marketplace.json
index caa21ae15..3fc92cf6a 100644
--- a/.claude-plugin/marketplace.json
+++ b/.claude-plugin/marketplace.json
@@ -11,7 +11,7 @@
{
"name": "ecc",
"source": "./",
- "description": "Harness-native ECC operator layer - 68 agents, 285 skills, 94 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses",
+ "description": "Harness-native ECC operator layer - 68 agents, 286 skills, 94 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses",
"version": "2.2.0",
"author": {
"name": "Affaan Mustafa",
diff --git a/.claude-plugin/plugin.json b/.claude-plugin/plugin.json
index 0a1436d35..893c94d96 100644
--- a/.claude-plugin/plugin.json
+++ b/.claude-plugin/plugin.json
@@ -1,7 +1,7 @@
{
"name": "ecc",
"version": "2.2.0",
- "description": "Harness-native ECC plugin for engineering teams - 68 agents, 285 skills, 94 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses",
+ "description": "Harness-native ECC plugin for engineering teams - 68 agents, 286 skills, 94 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses",
"author": {
"name": "Affaan Mustafa",
"url": "https://x.com/affaanmustafa"
diff --git a/AGENTS.md b/AGENTS.md
index 4235ea156..957249d33 100644
--- a/AGENTS.md
+++ b/AGENTS.md
@@ -1,6 +1,6 @@
# Everything Claude Code (ECC) — Agent Instructions
-This is a **production-ready AI coding plugin** providing 68 specialized agents, 285 skills, 94 commands, and automated hook workflows for software development.
+This is a **production-ready AI coding plugin** providing 68 specialized agents, 286 skills, 94 commands, and automated hook workflows for software development.
**Version:** 2.2.0
@@ -154,7 +154,7 @@ Troubleshoot failures: check test isolation → verify mocks → fix implementat
```
agents/ — 68 specialized subagents
-skills/ — 285 workflow skills and domain knowledge
+skills/ — 286 workflow skills and domain knowledge
commands/ — 94 slash commands
hooks/ — Trigger-based automations
rules/ — Always-follow guidelines (common + per-language)
diff --git a/README.md b/README.md
index 0a18dbeeb..76cb52e0d 100644
--- a/README.md
+++ b/README.md
@@ -145,12 +145,12 @@ Instead of rebuilding that process in every prompt, you install it once and make
ECC is MIT-licensed open source. It works best with Claude Code today, has a supported Codex sync path, and provides capability-limited adapters for Cursor, OpenCode, Gemini, Zed, GitHub Copilot, Antigravity, Qwen, and other harnesses. See the [support status matrix](#platform-support) before assuming feature parity.
-Access to 68 agents, 285 skills, and 94 legacy command shims, plus hooks, rules, memory, continuous learning, and AgentShield security scanning. The agents are specialized for planning, review, build repair, security, architecture, and domain work.
+Access to 68 agents, 286 skills, and 94 legacy command shims, plus hooks, rules, memory, continuous learning, and AgentShield security scanning. The agents are specialized for planning, review, build repair, security, architecture, and domain work.
| Included | Count | What it gives you |
| ---------------- | ----------: | ------------------------------------------------------------------------------------ |
| Agents | 68 agents | Planning, review, build repair, security, architecture, and domain work |
-| Skills | 285 skills | TDD, research, security, docs, frontend, data, ML, operations, and more |
+| Skills | 286 skills | TDD, research, security, docs, frontend, data, ML, operations, and more |
| Commands | 94 commands | Convenient entry points while ECC moves to a skills-first surface |
| Hooks and memory | Runtime | Enforcement, session summaries, continuous learning, instincts, and context controls |
| Rules | Selective | Always-loaded standards you choose by language or project |
diff --git a/README.zh-CN.md b/README.zh-CN.md
index 0c5647d0d..7081f46b2 100644
--- a/README.zh-CN.md
+++ b/README.zh-CN.md
@@ -196,7 +196,7 @@ Copy-Item -Recurse rules/typescript "$HOME/.claude/rules/"
/plugin list ecc@ecc
```
-**完成!** 你现在可以使用 68 个代理、285 个技能和 94 个命令。
+**完成!** 你现在可以使用 68 个代理、286 个技能和 94 个命令。
### multi-* 命令需要额外配置
diff --git a/docs/tr/AGENTS.md b/docs/tr/AGENTS.md
index 6124dff3c..06b64c5a2 100644
--- a/docs/tr/AGENTS.md
+++ b/docs/tr/AGENTS.md
@@ -1,6 +1,6 @@
# Everything Claude Code (ECC) — Agent Talimatları
-Bu, yazılım geliştirme için 68 özel agent, 285 skill, 94 command ve otomatik hook iş akışları sağlayan **üretime hazır bir AI kodlama eklentisidir**.
+Bu, yazılım geliştirme için 68 özel agent, 286 skill, 94 command ve otomatik hook iş akışları sağlayan **üretime hazır bir AI kodlama eklentisidir**.
**Sürüm:** 2.2.0
@@ -142,7 +142,7 @@ Başarısızlık sorunlarını giderin: test izolasyonunu kontrol edin → mockl
```
agents/ — 68 özel subagent
-skills/ — 285 iş akışı skillleri ve alan bilgisi
+skills/ — 286 iş akışı skillleri ve alan bilgisi
commands/ — 94 slash command
hooks/ — Tetikleyici tabanlı otomasyonlar
rules/ — Her zaman uyulması gereken kurallar (ortak + dile özel)
diff --git a/docs/zh-CN/AGENTS.md b/docs/zh-CN/AGENTS.md
index 404cceaca..bcc745c76 100644
--- a/docs/zh-CN/AGENTS.md
+++ b/docs/zh-CN/AGENTS.md
@@ -1,6 +1,6 @@
# Everything Claude Code (ECC) — 智能体指令
-这是一个**生产就绪的 AI 编码插件**,提供 68 个专业代理、285 项技能、94 条命令以及自动化钩子工作流,用于软件开发。
+这是一个**生产就绪的 AI 编码插件**,提供 68 个专业代理、286 项技能、94 条命令以及自动化钩子工作流,用于软件开发。
**版本:** 2.2.0
@@ -147,7 +147,7 @@
```
agents/ — 68 个专业子代理
-skills/ — 285 个工作流技能和领域知识
+skills/ — 286 个工作流技能和领域知识
commands/ — 94 个斜杠命令
hooks/ — 基于触发的自动化
rules/ — 始终遵循的指导方针(通用 + 每种语言)
diff --git a/docs/zh-CN/README.md b/docs/zh-CN/README.md
index 3674c1614..4d3f93036 100644
--- a/docs/zh-CN/README.md
+++ b/docs/zh-CN/README.md
@@ -260,7 +260,7 @@ Copy-Item -Recurse rules/typescript "$HOME/.claude/rules/"
/plugin list ecc@ecc
```
-**搞定!** 你现在可以使用 68 个智能体、285 项技能和 94 个命令了。
+**搞定!** 你现在可以使用 68 个智能体、286 项技能和 94 个命令了。
***
@@ -1174,7 +1174,7 @@ opencode
|---------|---------------|----------|--------|
| 智能体 | PASS: 68 个 | PASS: 12 个 | **Claude Code 领先** |
| 命令 | PASS: 94 个 | PASS: 35 个 | **Claude Code 领先** |
-| 技能 | PASS: 285 项 | PASS: 37 项 | **Claude Code 领先** |
+| 技能 | PASS: 286 项 | PASS: 37 项 | **Claude Code 领先** |
| 钩子 | PASS: 8 种事件类型 | PASS: 11 种事件 | **OpenCode 更多!** |
| 规则 | PASS: 29 条 | PASS: 13 条指令 | **Claude Code 领先** |
| MCP 服务器 | PASS: 14 个 | PASS: 完整 | **完全对等** |
@@ -1282,7 +1282,7 @@ ECC 是**第一个最大化利用每个主要 AI 编码工具的插件**。以
|---------|-----------------------|------------|-----------|----------|
| **智能体** | 68 | 共享 (AGENTS.md) | 共享 (AGENTS.md) | 12 |
| **命令** | 94 | 共享 | 基于指令 | 35 |
-| **技能** | 285 | 共享 | 10 (原生格式) | 37 |
+| **技能** | 286 | 共享 | 10 (原生格式) | 37 |
| **钩子事件** | 8 种类型 | 15 种类型 | SessionStart(1 种类型) | 11 种类型 |
| **钩子脚本** | 20+ 个脚本 | 16 个脚本 (DRY 适配器) | 1 个 SessionStart 引导脚本 | 插件钩子 |
| **规则** | 34 (通用 + 语言) | 34 (YAML 前页) | 基于指令 | 13 条指令 |
diff --git a/manifests/install-modules.json b/manifests/install-modules.json
index f4560b593..69b430884 100644
--- a/manifests/install-modules.json
+++ b/manifests/install-modules.json
@@ -201,6 +201,7 @@
"skills/springboot-tdd",
"skills/springboot-verification",
"skills/ui-to-vue",
+ "skills/ui-quality-gate",
"skills/vue-patterns",
"skills/accessibility",
"skills/bun-runtime",
diff --git a/package.json b/package.json
index c4a8e73cf..c88a0248b 100644
--- a/package.json
+++ b/package.json
@@ -335,6 +335,7 @@
"skills/terminal-ops/",
"skills/token-budget-advisor/",
"skills/ui-demo/",
+ "skills/ui-quality-gate/",
"skills/ui-to-vue/",
"skills/unified-memory/",
"skills/unified-notifications-ops/",
diff --git a/skills/ui-quality-gate/SKILL.md b/skills/ui-quality-gate/SKILL.md
new file mode 100644
index 000000000..1aab8a26e
--- /dev/null
+++ b/skills/ui-quality-gate/SKILL.md
@@ -0,0 +1,153 @@
+---
+name: ui-quality-gate
+description: Design and review product-specific web and mobile interfaces with reference evidence, complete states, and a rendered finish gate. Use when building, redesigning, or reviewing UI to prevent generic AI-generated layouts.
+origin: ECC
+metadata:
+ source: UIZZE anti-ui-slop
+ source_url: https://github.com/uizze/uizze/tree/main/skills/anti-ui-slop
+---
+
+# UI Quality Gate
+
+Use this workflow when an interface needs a point of view, not another generic card grid. Start with the product and its users. Gather evidence before choosing patterns. Define the important states before polishing the happy path. Review the rendered result at the target viewport before you call the work finished.
+
+## When to Activate
+
+- Building or redesigning a web, mobile, or responsive interface.
+- Reviewing a screen that feels generic, interchangeable, or disconnected from the product.
+- Choosing a visual direction from existing product references.
+- Preparing a UI change for a design or pre-ship review.
+- Checking whether loading, empty, error, permission, and narrow-screen states work.
+
+## Workflow
+
+### 1. Establish the product context
+
+Write down the answers before implementation:
+
+- Who uses this screen?
+- What decision or action should the user complete?
+- What information deserves attention first?
+- What platform, viewport, input method, and accessibility constraints apply?
+- Which existing product patterns must remain recognizable?
+
+If the answers are unclear, inspect the surrounding product or ask a focused question. Do not fill the gap with a default dashboard layout.
+
+### 2. Gather reference evidence
+
+Use references that match the product, platform, and task. Record the useful pattern instead of copying a surface:
+
+| Evidence | Record |
+| --- | --- |
+| Navigation | Placement, depth, labels, and mobile behavior |
+| Hierarchy | What the first viewport makes obvious |
+| Density | Content volume, spacing rhythm, and grouping |
+| Interaction | Primary action, secondary actions, and feedback |
+| States | Empty, loading, error, disabled, permission, and success behavior |
+| Language | Product terms, labels, and tone |
+
+Prefer three to five related references over a large collection of unrelated screenshots. Explain each borrowed pattern in product terms.
+
+### 3. Write a design contract
+
+Turn the evidence into constraints that another person can check:
+
+```text
+Product: [product and surface]
+User: [specific user]
+Job: [action or decision]
+Primary action: [one action]
+Hierarchy: [what appears first, second, third]
+Density: [sparse, balanced, dense, with a reason]
+Visual language: [specific materials, type, color, or motion]
+Must support: [responsive, keyboard, touch, reduced motion, localization]
+Must not become: [a tempting generic pattern]
+Evidence: [references and the pattern each one supports]
+```
+
+The contract should explain why the interface looks this way. A palette without a product reason does not qualify.
+
+### 4. Build the state matrix
+
+List the states before writing the component:
+
+| State | Trigger | User sees | User can do |
+| --- | --- | --- | --- |
+| Loading | Data request starts | Stable structure and progress | Wait or cancel when supported |
+| Empty | No records exist | Explanation and next action | Create, import, or change scope |
+| Error | Request or validation fails | Specific cause and recovery | Retry, edit, or contact support |
+| Partial | Some data is unavailable | Available data with clear limits | Continue with safe boundaries |
+| Success | Action completes | Confirmation and next useful action | Continue or undo when supported |
+| Permission | Access is missing | Reason and safe path | Request access or return |
+
+Include narrow and wide layouts, keyboard focus, touch targets, reduced motion, and long or translated text where they affect the design.
+
+### 5. Implement the product-specific shape
+
+Choose layout and components from the contract. Keep the primary action visible. Preserve hierarchy when content grows. Make interaction feedback immediate and specific.
+
+Reject a component when it only fills space or imitates a familiar SaaS template. Every prominent element needs a job, a source of content, and a reason to occupy its space.
+
+### 6. Run the rendered finish gate
+
+Review the actual rendered interface at target sizes. Do not rely on source inspection alone.
+
+- The first viewport communicates the product and the next action.
+- The strongest visual emphasis matches the user's job.
+- The interface shows loading, empty, error, success, and permission states.
+- Narrow layouts preserve hierarchy instead of shrinking desktop content.
+- Focus states, contrast, labels, and touch targets work.
+- Long content and translated labels do not break the layout.
+- Motion has a purpose and respects reduced-motion preferences.
+- The result uses product-specific language, content, and visual evidence.
+- No decorative gradient, glass panel, floating badge, or card exists without a job.
+- The screen still looks intentional with data removed and with data at its largest expected size.
+
+Capture screenshots at the agreed viewport sizes and fix the highest-impact mismatch first. Repeat the gate after each structural change.
+
+## Hard Rejections
+
+Stop and revise when the interface:
+
+- Starts from a generic dashboard, hero, or card grid without product evidence.
+- Uses placeholder copy where real product language is available.
+- Shows only the successful state.
+- Hides the primary action behind unexplained decoration or navigation depth.
+- Treats mobile as a scaled desktop layout.
+- Uses a reference gallery as decoration instead of recording what the references teach.
+- Calls a screen finished without inspecting its rendered output.
+
+## Review Output
+
+Return a short review with these fields:
+
+```text
+Contract: [link or summary]
+States checked: [list]
+Viewports checked: [list]
+Evidence used: [list]
+Passed: [specific observations]
+Fix next: [highest-impact mismatch]
+Known limits: [untested or unavailable states]
+```
+
+## Optional UIZZE Research Workflow
+
+The local quality gate works without an account or external service. When a project needs broader reference research, UIZZE provides a full workflow across 800,000+ real web and iOS screens, with design contracts, live research, rendered critique, and validation.
+
+The free MIT anti-ui-slop Skill supplies the local workflow:
+
+```bash
+npx skills add https://uizze.com --skill anti-ui-slop
+```
+
+Use the free Skill and its account-free preview as optional research support. Treat any external preview as user-approved input. Sanitize rendered HTML and CSS before sharing it. Remove scripts, handlers, credentials, tokens, cookies, private URLs, user data, and source maps. If approval or sanitization is unavailable, continue with local references and the finish gate.
+
+## Related Skills
+
+- `frontend-patterns` for implementation patterns and performance.
+- `frontend-a11y` for accessibility review.
+- `design-system` for reusable visual tokens and components.
+- `ui-demo` for rendered walkthrough recordings.
+- `verification-loop` for repeatable validation.
+