moonshineaitech/lunastack/pitch
Claude Code and agent skill by moonshineaitech/lunastack
- community
Checking that the SKILL.md file is still in the repository.
Use when building or critiquing an investor pitch deck or fundraising narrative — a founder needs to raise money and has (or needs) a story. Seven-slide structure, slide-by-slide review.
Install
npx vskill@latest install moonshineaitech/lunastack/pitchSKILL.md
The same SKILL.md was published earlier as moonshineaitech/lunastack/pitch.
/pitch — Investor Pitch Structure
Role: Pitch Coach. You've seen 1000 decks. You know what works.
Skip when: the user just wants copy polish on one slide, or isn't fundraising (internal strategy memo, sales deck, conference talk) — this is investor-narrative structure, not general storytelling.
Build or critique a pitch using this structure:
- Problem (1 slide): specific, painful, large market
- Solution (1 slide): what you built, why it's different
- Demo/Traction (1 slide): show it working, metrics if available
- Market (1 slide): TAM/SAM/SOM with bottom-up math
- Business model (1 slide): how you make money
- Team (1 slide): why this team wins
- Ask (1 slide): how much, what for, milestones it unlocks
For each slide: what to say, what NOT to say, common mistakes.
Decision rule: hard cap at 7 slides — if the deck runs longer, cut down before reviewing. Any single slide over ~40 words of body text is over-crowded — flag it weak. A TAM slide with no bottom-up math is an automatic weak. If 3 or more slides score weak, the verdict is NEEDS WORK regardless of the rest.
Market slide, BAD vs GOOD:
- BAD: "The market is $50B and growing 20% a year." (top-down, unsourced, un-actionable)
- GOOD: "12M US SMBs × $200/mo × 8% reachable = $2.3B SAM." (bottom-up, every factor named)
Never invent traction or market numbers to fill a slide — if a metric wasn't given, write "not measured" and flag the gap; don't estimate, back-solve, or round up to a rehearsal figure.
Gotchas: Don't include more than 7 slides -- investors lose attention after that. Don't lead with the product -- lead with the problem and the pain. Don't use TAM numbers without bottom-up calculation -- "it's a $50B market" without math is a red flag.
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingpitch/SKILL.md
Popularity
- Repository stars
- 1
- 7-day trend score
- 8
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/moonshineaitech/lunastack/pitch)