AI agent skills for startup validation, competitive intelligence, and planning
ai-agentsbattle-cardsclaude-codeclaude-skillscompetitive-analysiscompetitive-intelligencemarket-researchpricing-analysisstartupstartup-validation
docs: add startup-positioning to project documentation
Ferdinando Bonsegna6218c61640b9
diff --git a/.claude-plugin/marketplace.json b/.claude-plugin/marketplace.jsonindex 41c6ac8..451b2ec 100644--- a/.claude-plugin/marketplace.json+++ b/.claude-plugin/marketplace.json@@ -16,7 +16,8 @@"strict": false,"skills": ["./startup-design",- "./startup-competitors"+ "./startup-competitors",+ "./startup-positioning"]}]diff --git a/CLAUDE.md b/CLAUDE.mdindex 82b90b6..b9bf12c 100644--- a/CLAUDE.md+++ b/CLAUDE.md@@ -16,7 +16,7 @@ This repository contains the **startup** plugin for AI agents. The plugin namesp| Category | Purpose | Skills ||----------|---------|--------|| **Design** | Full process, idea to validated plan | `startup-design` |-| **Analyze** | Deep standalone analysis of one area | `startup-competitors`, `startup-positioning` (planned) |+| **Analyze** | Deep standalone analysis of one area | `startup-competitors`, `startup-positioning` || **Build** | Post-validation execution tools | `startup-pitch` (planned) |## Repository Structure@@ -43,6 +43,15 @@ startup-skill/ # Plugin namespace (startup:*)│ ├── research-wave-2-sentiment-mining.md│ ├── research-wave-3-gtm-signals.md│ └── research-synthesis.md+├── startup-positioning/ # Skill: startup:startup-positioning+│ ├── SKILL.md # Main skill file (~218 lines, 2 waves)+│ └── references/+│ ├── research-principles.md+│ ├── research-wave-1-alternatives.md+│ ├── research-wave-2-market-frame.md+│ ├── research-synthesis.md+│ ├── frameworks.md+│ └── honesty-protocol.md├── CLAUDE.md├── CONTRIBUTING.md├── LICENSE@@ -55,8 +64,8 @@ startup-skill/ # Plugin namespace (startup:*)- **Plugin name** (`startup`): defined in `.claude-plugin/marketplace.json` → becomes the namespace prefix- **Skill name** (`startup-design`, `startup-competitors`): defined in `SKILL.md` frontmatter → must match directory name-- **Command**: `/startup:startup-design`, `/startup:startup-competitors` — `plugin-name:skill-name`-- Future skills go in the same repo as separate directories (e.g. `startup-pitch/`, `startup-positioning/`)+- **Command**: `/startup:startup-design`, `/startup:startup-competitors`, `/startup:startup-positioning` — `plugin-name:skill-name`+- Future skills go in the same repo as separate directories (e.g. `startup-pitch/`)### Skill Format@@ -80,7 +89,11 @@ startup-skill/ # Plugin namespace (startup:*)- Wave 2: Customer Sentiment Mining (2 agents)- Wave 3: GTM & Strategic Signals (2 agents)-Each wave must complete before the next starts. Agents use WebSearch for real data. Both skills support Claude.ai (sequential fallback) and Knowledge-Based Mode when WebSearch is unavailable.+**startup-positioning** uses 2 sequential waves of parallel agents:+- Wave 1: Competitive Alternatives + Customer Intelligence (2 agents)+- Wave 2: Market Frame + Trends (2 agents)++Each wave must complete before the next starts. Agents use WebSearch for real data. All skills support Claude.ai (sequential fallback) and Knowledge-Based Mode when WebSearch is unavailable.### Output Structure@@ -101,10 +114,20 @@ Each wave must complete before the next starts. Agents use WebSearch for real da- `battle-cards/{competitor}.md` — Per-competitor one-pagers- `raw/` — Raw research data from each wave+**startup-positioning** generates files in `{project-name}/`:+- `intake.md` — Product and market context+- `positioning-doc.md` — Main deliverable (Dunford 5 components)+- `positioning-statement.md` — Moore + Neumeier statements + elevator pitch+- `competitive-alternatives.md` — JTBD-informed alternatives map+- `market-category-analysis.md` — Category candidates + recommendation+- `raw/` — Raw research data from each wave+### Integration Between Skills`startup-competitors` can detect and leverage prior `startup-design` output. If files like `01-discovery/competitor-landscape.md` exist, it uses them as a starting point instead of re-interviewing.+`startup-positioning` can detect and leverage output from BOTH `startup-design` (intake, discovery, strategy) and `startup-competitors` (battle cards, pricing landscape). It uses prior data as a head start and skips redundant intake questions.+### TestingEval cases are in `{skill}-workspace/evals/evals.json`. To test:diff --git a/CONTRIBUTING.md b/CONTRIBUTING.mdindex 4e89c60..c0b4ecb 100644--- a/CONTRIBUTING.md+++ b/CONTRIBUTING.md@@ -1,6 +1,6 @@# Contributing-Thanks for your interest in contributing to Startup Design Skill! This guide will help you improve the skill or add new capabilities.+Thanks for your interest in contributing to Startup Skills! This guide will help you improve existing skills or add new capabilities.## Ways to Contribute@@ -18,16 +18,20 @@ Thanks for your interest in contributing to Startup Design Skill! This guide wil## Skill Structure+Each skill follows the same directory pattern:+```-startup-design/+{skill-name}/├── SKILL.md # Main skill file (keep under 500 lines)└── references/ # Supporting documents loaded on demand├── research-principles.md├── research-wave-*.md├── research-synthesis.md- └── frameworks.md+ └── frameworks.md (if applicable)```+Current skills: `startup-design/`, `startup-competitors/`, `startup-positioning/`.+### Guidelines- **SKILL.md** should stay under 500 lines. Move detailed content to `references/`@@ -66,12 +70,15 @@ Existing test scenarios are in `startup-design-workspace/evals/evals.json`:When creating a new release:-- [ ] Rebuild `startup-design.zip` from the `startup-design/` directory: `zip -r startup-design.zip startup-design/`+- [ ] Rebuild zip files for each changed skill:+ - `zip -r startup-design.zip startup-design/`+ - `zip -r startup-competitors.zip startup-competitors/`+ - `zip -r startup-positioning.zip startup-positioning/`- [ ] Create a git tag: `git tag -a vX.Y.Z -m "description"`- [ ] Push code and tag: `git push origin main && git push origin vX.Y.Z`-- [ ] Create a GitHub release and attach `startup-design.zip` as an asset (Claude.ai users download this)+- [ ] Create a GitHub release and attach zip files as assets (Claude.ai users download these)-The zip file is used by Claude.ai web app users who install skills via Settings → Skills → Add Skill. It must be updated with every release.+The zip files are used by Claude.ai web app users who install skills via Settings → Skills → Add Skill. They must be updated with every release that changes skill files.## Quality Checklist@@ -81,7 +88,7 @@ The zip file is used by Claude.ai web app users who install skills via Settings- [ ] No sensitive data or credentials- [ ] Tested locally with AI agent- [ ] Changes are focused and minimal-- [ ] `startup-design.zip` rebuilt if skill files changed+- [ ] Zip files rebuilt for any changed skills## Questions?diff --git a/README.md b/README.mdindex f748b01..4db772a 100644--- a/README.md+++ b/README.md@@ -16,8 +16,9 @@ Works with [Claude Code](https://claude.ai/claude-code) and any agent that suppo|-------|-------------|| [startup-design](startup-design/) | A complete startup plan: market research, strategy, brand, product definition, financial projections, and validation experiments. 8 phases, 11 research agents, one command. || [startup-competitors](startup-competitors/) | Battle cards for every competitor, a pricing landscape with reverse-engineered tiers, a feature matrix, and a strategic report — built from real reviews, forums, and web data. |+| [startup-positioning](startup-positioning/) | Market positioning strategy using April Dunford's framework, enriched with JTBD, Moore, and Neumeier. Produces a positioning doc, positioning statements, competitive alternatives map, and market category analysis. 3 phases, 4 research agents. |-Coming soon: `startup-positioning` (April Dunford framework) and `startup-pitch` (investor deck generation).+Coming soon: `startup-pitch` (investor deck generation).## Usage@@ -34,9 +35,13 @@ I need battle cards and a pricing comparison.""Quick validation — fast track mode."→ startup-design runs a compressed go/no-go analysis++"How should we position our product? We're in the project management space+but we're different from Asana and Monday."+→ startup-positioning builds positioning through Dunford's 5+1 components```-Or invoke directly: `/startup:startup-design`, `/startup:startup-competitors`+Or invoke directly: `/startup:startup-design`, `/startup:startup-competitors`, `/startup:startup-positioning`> **Token usage:** These skills run multiple research agents and can consume a large number of tokens. For the best experience, use [Claude Max 5x](https://claude.ai/upgrade). If a session hits the limit, just ask Claude to "resume from where you left off" — it will pick up the process.@@ -63,6 +68,7 @@ npx skills add ferdinandobons/startup-skillgit clone https://github.com/ferdinandobons/startup-skill.gitcp -r startup-skill/startup-design .agents/skills/cp -r startup-skill/startup-competitors .agents/skills/+cp -r startup-skill/startup-positioning .agents/skills/# Git submodulegit submodule add https://github.com/ferdinandobons/startup-skill.git .agents/startup-skill