skills/personal/pitch-deck/SKILL.md
Generate investor-ready pitch decks as branded PPTX files from founder meeting notes, uploaded decks, DD reports, and strategy docs. Use this skill whenever the user mentions building a pitch deck, turning notes into slides, creating an investor deck, preparing for a co-investor presentation, or helping a portfolio company with their deck. Also trigger when the user uploads Granola meeting notes, founder call transcripts, or company materials and asks for a deck, slides, or presentation for investors. Covers co-investor syndication decks and founder coaching decks. Even if the user just says 'build a deck from these notes' or 'make this into a pitch deck' or 'help [company] with their deck', use this skill.
npx skillsauth add The-Utopia-Studio/skills pitch-deckInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security scan pending...
This skill is queued for security scanning. Results will appear when the scan completes.
Build investor-ready pitch decks from raw materials — meeting notes, uploaded decks, DD reports, and strategy docs — and output as branded PPTX.
This skill is built for The Studio (Utopia Capital). The default audience is co-investors and syndicate partners. When helping portfolio founders build their own decks, adapt the branding and voice accordingly.
view /mnt/skills/public/pptx/SKILL.md — then read pptxgenjs.md for from-scratch creationreferences/slide-frameworks.md — Global Context and Growth Flywheel frameworks (the two signature slides)references/slide-best-practices.md — research-backed guidance for every slide in the deckreferences/scoring-rubric.md — the 15-dimension scoring framework (score inputs and outputs)assets/utopia-branding.md — Studio brand defaultsreferences/dd-integration.md for extraction patternsAll reference paths are relative to this skill's directory.
Read and parse everything the user provides. Typical inputs:
markitdown or the pdf-reading skill to extract content; note what's strong and what's missingreferences/dd-integration.md)From these materials, extract and organize:
| Category | What to find | |----------|-------------| | Company basics | Name, stage, what it does, founding date | | Problem | Pain points, market gaps, why now | | Solution | Product, differentiators, technical approach | | Market | TAM/SAM/SOM, growth rates, industry dynamics | | Traction | Users, revenue, partnerships, milestones | | Team | Founders, key hires, relevant domain expertise | | Business model | Revenue streams, pricing, unit economics | | Financials | Burn rate, runway, projections | | The ask | Funding amount, use of funds, milestone targets | | Competitive landscape | Named competitors, positioning, moats |
If critical data is missing, ask specific questions before generating. Never fabricate metrics, financials, or traction numbers. Use [NEEDS INPUT] placeholders for gaps the user must fill.
After ingesting all source materials, score them using the 15-dimension framework in references/scoring-rubric.md. Present the input scores to the user before generating the deck — this sets expectations about what the source materials support and where research or user input is needed to improve the output.
For any dimension scoring 6 or below, flag it immediately and ask for additional information or approval to research.
Supplement the user's materials with current market intelligence using web search:
Cross-reference any numbers from the source materials against public data. Flag discrepancies for the user rather than silently correcting.
The standard co-investor deck follows this sequence. Adapt based on what the materials contain — not every company needs every slide, and some need extras.
| # | Slide | Purpose |
|---|-------|---------|
| 1 | Title | Company name, tagline, round context |
| 2 | Global Context | Three structural forces — see references/slide-frameworks.md |
| 3 | Problem | Pain point with data validation |
| 4 | Solution | Product overview, key differentiators |
| 5 | Product | Features, architecture, demo flow |
| 6 | Market Opportunity | TAM/SAM/SOM with cited sources |
| 7 | Business Model | Revenue streams, pricing, unit economics |
| 8 | Traction | Metrics, growth trajectory, key milestones |
| 9 | Growth Flywheel | How the business scales + defensible moats — see references/slide-frameworks.md |
| 10 | Competition | Positioning matrix, structural advantages |
| 11 | Go-to-Market | Channels, partnerships, CAC/LTV dynamics |
| 12 | Team | Founders, advisors, key hires, domain credibility |
| 13 | Financials | Projections, key assumptions, path to profitability |
| 14 | The Ask | Funding amount, use of funds, milestone targets |
| 15 | Appendix | Supporting data, references, backup slides |
The Global Context (slide 2) and Growth Flywheel (slide 9) are the two signature slides that distinguish a Studio deck from a generic pitch. They are non-negotiable for co-investor decks. Read references/slide-frameworks.md before generating these.
For each slide, consult references/slide-best-practices.md for research-backed guidance on what great looks like, what to avoid, and how investors evaluate that specific slide. Then produce:
Adapt language and metrics by sector:
| Sector | Key Metrics | |--------|------------| | SaaS | ARR, churn, NRR, CAC payback, LTV/CAC | | Biotech/Health | Regulatory pathway, clinical milestones, IP | | Marketplace | GMV, take rate, liquidity, network effects | | Hardware | BOM cost, manufacturing scale, distribution | | AI/ML | Model performance, data moats, compute costs | | Fintech | Regulatory compliance, transaction volume, trust |
Use the pptx skill's pptxgenjs approach (from-scratch creation). Before writing code:
/mnt/skills/public/pptx/pptxgenjs.md for the full API referenceassets/utopia-branding.md (Studio default) or the portfolio company's brand if specifiedDo not repeat the same layout across slides. Rotate through:
Follow the pptx skill's QA process exactly:
python scripts/office/soffice.py --headless --convert-to pdf output.pptx then pdftoppmpython -m markitdown output.pptx — verify no missing content or placeholder textAfter generating the deck, score it again using the same 15-dimension framework from references/scoring-rubric.md. Present a before/after comparison:
PITCH DECK QUALITY SCORECARD
Input Output Delta
1. Narrative Clarity X/10 X/10 +X
2. Problem Definition X/10 X/10 +X
...
TOTAL X/150 X/150 +X
GRADE [A/B/C/D/F]
Then provide:
[NEEDS INPUT] markersTarget a minimum grade of B (90+/150) before sharing a deck with co-investors. Anything below B needs another iteration.
[NEEDS INPUT: specific question]When the user uploads an existing pitch deck and asks to improve it:
When a Technical DD report exists:
references/dd-integration.md for extraction patternsdata-ai
Raw mechanical interfaces fusing Swiss typographic print with military terminal aesthetics. Rigid grids, extreme type scale contrast, utilitarian color, analog degradation effects. For data-heavy dashboards, portfolios, or editorial sites that need to feel like declassified blueprints.
development
Teaches the AI to design like a high-end agency. Defines the exact fonts, spacing, shadows, card structures, and animations that make a website feel expensive. Blocks all the common defaults that make AI designs look cheap or generic.
development
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.
development
Senior UI/UX Engineer. Architect digital interfaces overriding default LLM biases. Enforces metric-based rules, strict component architecture, CSS hardware acceleration, and balanced design engineering.