Skip to content

AI agent skills for startup validation, competitive intelligence, and planning

fix: consistency pass across all skills

Ferdinando Bonsegnae23de316f5fa
diff --git a/AGENTS.md b/AGENTS.md
index e9e9501..d5cbc93 100644
--- a/AGENTS.md
+++ b/AGENTS.md
@@ -26,7 +26,7 @@ startup-skill/ # Plugin namespace (startup:*)
├── .claude-plugin/
│ └── marketplace.json # Plugin definition (name must be "startup")
├── startup-design/ # Skill: startup:startup-design
-│ ├── SKILL.md # Main skill file (~522 lines, 8 phases)
+│ ├── SKILL.md # Main skill file (~568 lines, 8 phases)
│ └── references/ # Supporting documents loaded on demand
│ ├── research-principles.md
│ ├── research-scaling.md
@@ -36,9 +36,12 @@ startup-skill/ # Plugin namespace (startup:*)
│ ├── research-wave-4-distribution.md
│ ├── research-synthesis.md
│ ├── verification-agent.md
-│ └── frameworks.md
+│ ├── frameworks.md
+│ ├── industry-benchmarks.md
+│ ├── honesty-protocol.md
+│ └── output-guidelines.md
├── startup-competitors/ # Skill: startup:startup-competitors
-│ ├── SKILL.md # Main skill file (~220 lines, 3 waves)
+│ ├── SKILL.md # Main skill file (~268 lines, 3 waves)
│ └── references/
│ ├── research-principles.md
│ ├── research-scaling.md
@@ -49,7 +52,7 @@ startup-skill/ # Plugin namespace (startup:*)
│ ├── verification-agent.md
│ └── honesty-protocol.md
├── startup-positioning/ # Skill: startup:startup-positioning
-│ ├── SKILL.md # Main skill file (~240 lines, 2 waves)
+│ ├── SKILL.md # Main skill file (~302 lines, 2 waves)
│ └── references/
│ ├── research-principles.md
│ ├── research-scaling.md
@@ -60,7 +63,7 @@ startup-skill/ # Plugin namespace (startup:*)
│ ├── frameworks.md
│ └── honesty-protocol.md
├── startup-pitch/ # Skill: startup:startup-pitch
-│ ├── SKILL.md # Main skill file (~370 lines, 2 waves)
+│ ├── SKILL.md # Main skill file (~418 lines, 2 waves)
│ └── references/
│ ├── research-principles.md
│ ├── research-scaling.md
@@ -157,6 +160,7 @@ All skills run a **V1: Verification** agent after synthesis. It audits deliverab
- `positioning-statement.md` — Moore + Neumeier statements + elevator pitch
- `competitive-alternatives.md` — JTBD-informed alternatives map
- `market-category-analysis.md` — Category candidates + recommendation
+- `messaging-implications.md` — Bridge from positioning to copy
- `raw/` — Raw research data from each wave
**startup-pitch** generates files in `{project-name}/`:
diff --git a/CLAUDE.md b/CLAUDE.md
index 471d4e7..e7a2379 100644
--- a/CLAUDE.md
+++ b/CLAUDE.md
@@ -26,7 +26,7 @@ startup-skill/ # Plugin namespace (startup:*)
├── .claude-plugin/
│ └── marketplace.json # Plugin definition (name must be "startup")
├── startup-design/ # Skill: startup:startup-design
-│ ├── SKILL.md # Main skill file (~522 lines, 8 phases)
+│ ├── SKILL.md # Main skill file (~568 lines, 8 phases)
│ └── references/ # Supporting documents loaded on demand
│ ├── research-principles.md
│ ├── research-scaling.md
@@ -36,9 +36,12 @@ startup-skill/ # Plugin namespace (startup:*)
│ ├── research-wave-4-distribution.md
│ ├── research-synthesis.md
│ ├── verification-agent.md
-│ └── frameworks.md
+│ ├── frameworks.md
+│ ├── industry-benchmarks.md
+│ ├── honesty-protocol.md
+│ └── output-guidelines.md
├── startup-competitors/ # Skill: startup:startup-competitors
-│ ├── SKILL.md # Main skill file (~220 lines, 3 waves)
+│ ├── SKILL.md # Main skill file (~268 lines, 3 waves)
│ └── references/
│ ├── research-principles.md
│ ├── research-scaling.md
@@ -49,7 +52,7 @@ startup-skill/ # Plugin namespace (startup:*)
│ ├── verification-agent.md
│ └── honesty-protocol.md
├── startup-positioning/ # Skill: startup:startup-positioning
-│ ├── SKILL.md # Main skill file (~240 lines, 2 waves)
+│ ├── SKILL.md # Main skill file (~302 lines, 2 waves)
│ └── references/
│ ├── research-principles.md
│ ├── research-scaling.md
@@ -60,7 +63,7 @@ startup-skill/ # Plugin namespace (startup:*)
│ ├── frameworks.md
│ └── honesty-protocol.md
├── startup-pitch/ # Skill: startup:startup-pitch
-│ ├── SKILL.md # Main skill file (~370 lines, 2 waves)
+│ ├── SKILL.md # Main skill file (~418 lines, 2 waves)
│ └── references/
│ ├── research-principles.md
│ ├── research-scaling.md
@@ -146,6 +149,7 @@ Each wave must complete before the next starts. Agents use WebSearch for real da
- `positioning-statement.md` — Moore + Neumeier statements + elevator pitch
- `competitive-alternatives.md` — JTBD-informed alternatives map
- `market-category-analysis.md` — Category candidates + recommendation
+- `messaging-implications.md` — Bridge from positioning to copy
- `raw/` — Raw research data from each wave
**startup-pitch** generates files in `{project-name}/`:
diff --git a/startup-competitors/SKILL.md b/startup-competitors/SKILL.md
index dc77387..d5a0903 100644
--- a/startup-competitors/SKILL.md
+++ b/startup-competitors/SKILL.md
@@ -10,7 +10,7 @@ Deep competitive intelligence that goes beyond surface-level profiles. Produces
## How It Works
```
-INTAKE → RESEARCH (3 parallel waves) → SYNTHESIS → BATTLE CARDS
+INTAKE → RESEARCH (3 sequential waves) → SYNTHESIS → BATTLE CARDS
```
The process is focused: understand the product, research competitors deeply across 3 dimensions, synthesize findings, and produce actionable output. Typical runtime: 15-25 minutes in Claude Code (parallel agents), 30-45 minutes in Claude.ai (sequential).
@@ -21,6 +21,14 @@ Default output language is **English**. If the user writes in another language o
---
+## Phase 0: Resume Check
+
+Before anything else, check if a `PROGRESS.md` created by this skill exists in the working directory or a project subdirectory (the skill name field says `startup-competitors`). If it does, read it and resume from the last incomplete phase. Tell the user: "I found progress from a previous session. You completed [phases]. Picking up from [next phase]."
+
+If no progress file exists — or the one found belongs to a different skill — start from Phase 1.
+
+---
+
## Phase 1: Intake
Short and focused — 1-2 rounds of questions, not an extended interview. The goal is just enough context to run targeted research.
@@ -87,7 +95,7 @@ The selected tier determines the number of agents per wave and search rounds per
## Phase 2: Research
-Three parallel research waves, each attacking the competitive landscape from a different angle. Together they produce a 360-degree view.
+Three sequential research waves, each attacking the competitive landscape from a different angle — agents within a wave run in parallel. Together they produce a 360-degree view.
### Environment Detection
@@ -256,5 +264,5 @@ Read only what you need for the current phase.
| `research-wave-2-sentiment-mining.md` | When running Wave 2 | ~189 | Agent templates for review + forum mining |
| `research-wave-3-gtm-signals.md` | When running Wave 3 | ~192 | Agent templates for GTM + strategic signals |
| `research-synthesis.md` | After all waves complete | ~231 | How to synthesize + battle card template |
-| `research-scaling.md` | After intake, before Phase 2 | ~80 | Complexity scoring, tier definitions, wave configurations |
-| `verification-agent.md` | After synthesis | ~85 | Verification protocol, universal + skill-specific checks |
+| `research-scaling.md` | After intake, before Phase 2 | ~106 | Complexity scoring, tier definitions, wave configurations |
+| `verification-agent.md` | After synthesis | ~126 | Verification protocol, universal + skill-specific checks |
diff --git a/startup-design/SKILL.md b/startup-design/SKILL.md
index ef7bc3e..b70c4c1 100644
--- a/startup-design/SKILL.md
+++ b/startup-design/SKILL.md
@@ -552,17 +552,17 @@ This skill helps founders make good decisions, not feel good. Honesty is non-neg
The `references/` directory contains supporting documentation. Read only what you need for the current phase.
-| File | When to Read | Lines |
-|------|-------------|-------|
-| `output-guidelines.md` | At the start of every session (once) | ~78 |
-| `honesty-protocol.md` | At the start of every session (once) | ~69 |
-| `research-principles.md` | Before starting Phase 3 (once) | ~54 |
-| `research-wave-1-market.md` | When spawning Wave 1 agents | ~206 |
-| `research-wave-2-competitors.md` | When spawning Wave 2 agents | ~220 |
-| `research-wave-3-customers.md` | When spawning Wave 3 agents | ~233 |
-| `research-wave-4-distribution.md` | When spawning Wave 4 agents | ~132 |
-| `research-synthesis.md` | After all waves complete, before writing final files | ~104 |
-| `research-scaling.md` | After intake, before Phase 3 | ~95 | Complexity scoring, tier definitions, wave configurations |
-| `verification-agent.md` | After synthesis, before Phase 3.5 | ~100 | Verification protocol, universal + skill-specific checks |
-| `frameworks.md` | During Phase 4 (Strategy), Phase 6 (Product), and Phase 8 (Validation) | ~110 |
-| `industry-benchmarks.md` | During Phase 7 (Financial) | ~80 |
+| File | When to Read | ~Lines | Purpose |
+|------|-------------|--------|---------|
+| `output-guidelines.md` | At the start of every session (once) | ~124 | File headers/footers, cross-references, quality examples, pivot handling |
+| `honesty-protocol.md` | At the start of every session (once) | ~69 | Honesty rules, data labels, anti-patterns |
+| `research-principles.md` | Before starting Phase 3 (once) | ~54 | Source quality, cross-referencing, data gaps |
+| `research-wave-1-market.md` | When spawning Wave 1 agents | ~206 | Agent templates for market sizing, trends, regulatory |
+| `research-wave-2-competitors.md` | When spawning Wave 2 agents | ~220 | Agent templates for direct, indirect, GTM analysis |
+| `research-wave-3-customers.md` | When spawning Wave 3 agents | ~233 | Agent templates for customer voice, demand, audience |
+| `research-wave-4-distribution.md` | When spawning Wave 4 agents | ~132 | Agent templates for channels, geographic entry |
+| `research-synthesis.md` | After all waves complete, before writing final files | ~110 | How to synthesize raw findings into deliverables |
+| `research-scaling.md` | After intake, before Phase 3 | ~122 | Complexity scoring, tier definitions, wave configurations |
+| `verification-agent.md` | After synthesis, before Phase 3.5 | ~117 | Verification protocol, universal + skill-specific checks |
+| `frameworks.md` | During Phase 4 (Strategy), Phase 6 (Product), and Phase 8 (Validation) | ~107 | Lean Canvas, Dunford, VPC, RICE/MoSCoW definitions |
+| `industry-benchmarks.md` | During Phase 7 (Financial) | ~66 | Standard metrics by business model type |
diff --git a/startup-pitch/SKILL.md b/startup-pitch/SKILL.md
index 6d21fb8..3be3477 100644
--- a/startup-pitch/SKILL.md
+++ b/startup-pitch/SKILL.md
@@ -10,7 +10,7 @@ Build investor-ready pitch content in multiple formats. Uses a structured 7-elem
## How It Works
```
-INTAKE → RESEARCH (2 parallel waves) → PITCH CONSTRUCTION → REVIEW & PRACTICE
+INTAKE → RESEARCH (2 sequential waves) → PITCH CONSTRUCTION → REVIEW & PRACTICE
```
The process: understand the company deeply, research the investor audience and competitive framing, then construct the pitch. Typical runtime: 15-20 minutes in Claude Code (parallel agents), 30-40 minutes in Claude.ai (sequential).
@@ -29,6 +29,14 @@ Default output language is **English**. If the user writes in another language o
---
+## Phase 0: Resume Check
+
+Before anything else, check if a `PROGRESS.md` created by this skill exists in the working directory or a project subdirectory (the skill name field says `startup-pitch`). If it does, read it and resume from the last incomplete phase. Tell the user: "I found progress from a previous session. You completed [phases]. Picking up from [next phase]."
+
+If no progress file exists — or the one found belongs to a different skill — start from Phase 1.
+
+---
+
## Phase 1: Intake
Short and focused — 1-2 rounds of questions. The goal is enough context to build a compelling pitch.
@@ -127,7 +135,7 @@ The selected tier determines the number of agents per wave and search rounds per
## Phase 2: Research
-Two parallel research waves exploring investor audience and competitive/market framing. Together they provide the raw material for a pitch that resonates with the target audience.
+Two sequential research waves exploring investor audience and competitive/market framing — agents within a wave run in parallel, and Wave 2 builds on Wave 1's findings. Together they provide the raw material for a pitch that resonates with the target audience.
### Environment Detection
@@ -405,6 +413,6 @@ Read only what you need for the current phase.
| `research-wave-1-audience-narrative.md` | When running Wave 1 | ~164 | Agent templates for investor + narrative research |
| `research-wave-2-competitive-framing.md` | When running Wave 2 | ~159 | Agent templates for competitive framing + why now |
| `pitch-frameworks.md` | During Phase 3 | ~261 | Complete pitch framework with integration matrix |
-| `research-synthesis.md` | After waves complete | ~417 | Synthesis protocol and output templates |
-| `research-scaling.md` | After intake, before Phase 2 | ~75 | Complexity scoring, tier definitions, wave configurations |
-| `verification-agent.md` | After pitch construction | ~80 | Verification protocol, universal + skill-specific checks |
+| `research-synthesis.md` | After waves complete | ~423 | Synthesis protocol and output templates |
+| `research-scaling.md` | After intake, before Phase 2 | ~96 | Complexity scoring, tier definitions, wave configurations |
+| `verification-agent.md` | After pitch construction | ~129 | Verification protocol, universal + skill-specific checks |
diff --git a/startup-pitch/references/research-synthesis.md b/startup-pitch/references/research-synthesis.md
index 1e80953..61770d6 100644
--- a/startup-pitch/references/research-synthesis.md
+++ b/startup-pitch/references/research-synthesis.md
@@ -1,5 +1,7 @@
# Pitch Research Synthesis Protocol
+**Contents:** Before Writing · Cross-Source Connections to Look For · Confidence Rating · Pitch Construction Process · Output File Templates (pitch-full, pitch-5min, pitch-2min, pitch-1min, pitch-email, pitch-appendix, pitch-scorecard) · Post-Synthesis Verification
+
## Before Writing
1. Read ALL raw files in `{project-name}/raw/` before writing anything
diff --git a/startup-positioning/SKILL.md b/startup-positioning/SKILL.md
index 9205128..1aa046e 100644
--- a/startup-positioning/SKILL.md
+++ b/startup-positioning/SKILL.md
@@ -10,7 +10,7 @@ Market positioning strategy that produces a complete positioning document, Moore
## How It Works
```
-INTAKE → RESEARCH (2 parallel waves) → POSITIONING SYNTHESIS
+INTAKE → RESEARCH (2 sequential waves) → POSITIONING SYNTHESIS
```
The process: understand the product and its customers, research competitive alternatives and market context, then build positioning through Dunford's 5+1 components. Typical runtime: 10-15 minutes in Claude Code (parallel agents), 20-30 minutes in Claude.ai (sequential).
@@ -21,6 +21,14 @@ Default output language is **English**. If the user writes in another language o
---
+## Phase 0: Resume Check
+
+Before anything else, check if a `PROGRESS.md` created by this skill exists in the working directory or a project subdirectory (the skill name field says `startup-positioning`). If it does, read it and resume from the last incomplete phase. Tell the user: "I found progress from a previous session. You completed [phases]. Picking up from [next phase]."
+
+If no progress file exists — or the one found belongs to a different skill — start from Phase 1.
+
+---
+
## Phase 1: Intake
Short and focused — 1-2 rounds of questions. The goal is enough context to research alternatives and build positioning.
@@ -94,7 +102,7 @@ The selected tier determines the number of agents per wave and search rounds per
## Phase 2: Research
-Two parallel research waves exploring competitive alternatives and market context. Together they provide the raw material for Dunford's 5+1 positioning components.
+Two sequential research waves exploring competitive alternatives and market context — agents within a wave run in parallel, and Wave 2 builds on Wave 1's findings. Together they provide the raw material for Dunford's 5+1 positioning components.
### Environment Detection
@@ -288,7 +296,7 @@ Read only what you need for the current phase.
| `research-principles.md` | Before starting Phase 2 | ~65 | Source quality, cross-referencing, data gaps |
| `research-wave-1-alternatives.md` | When running Wave 1 | ~235 | Agent templates for alternatives + customer intel |
| `research-wave-2-market-frame.md` | When running Wave 2 | ~210 | Agent templates for categories + trends |
-| `research-synthesis.md` | After both waves complete | ~380 | Synthesis protocol, Dunford process, validation tests, messaging implications |
-| `frameworks.md` | During Phase 3 | ~133 | Dunford/Moore/Neumeier/JTBD/Ries reference |
-| `research-scaling.md` | After intake, before Phase 2 | ~75 | Complexity scoring, tier definitions, wave configurations |
-| `verification-agent.md` | After synthesis | ~80 | Verification protocol, universal + skill-specific checks |
+| `research-synthesis.md` | After both waves complete | ~419 | Synthesis protocol, Dunford process, validation tests, messaging implications |
+| `frameworks.md` | During Phase 3 | ~132 | Dunford/Moore/Neumeier/JTBD/Ries reference |
+| `research-scaling.md` | After intake, before Phase 2 | ~96 | Complexity scoring, tier definitions, wave configurations |
+| `verification-agent.md` | After synthesis | ~128 | Verification protocol, universal + skill-specific checks |
diff --git a/startup-positioning/references/research-synthesis.md b/startup-positioning/references/research-synthesis.md
index 7dd9eea..29a183f 100644
--- a/startup-positioning/references/research-synthesis.md
+++ b/startup-positioning/references/research-synthesis.md
@@ -1,5 +1,7 @@
# Positioning Research Synthesis Protocol
+**Contents:** Before Writing · Cross-Wave Connections to Look For · Confidence Rating · Dunford's 5+1 Components — Detailed Synthesis Process · Validation Tests · Output File Templates (positioning-doc, positioning-statement, competitive-alternatives, market-category-analysis, messaging-implications) · Post-Synthesis Verification
+
## Before Writing
1. Read ALL raw files in `{project-name}/raw/` before writing anything