pitch-deck-reviewer — Claude Code skill: what it does, how to install
Reviews startup pitch decks, scores narrative and financial clarity, and generates a structured pitch-review.md report with anticipated investor objections.
npx skills add OneWave-AI/claude-skills --skill pitch-deck-reviewer -a claude-codeWhat pitch-deck-reviewer does
The skill evaluates pitch materials across formats including PDF, PPTX, image folders with PNG or JPG files, and public Google Slides links. Multi-page PDFs with 10 or more pages are processed in batches via page parameters. The workflow begins with a slide inventory, recording company stage and industry. Decks exceeding 20 slides get flagged immediately, as typical successful fundraising runs on 10 to 15 slides. Files formatted as .pen cannot be read directly.
Evaluation runs across eight dimensions using an internal scoring guide. Scores range from 1 to 10 with clear evidence, producing a weighted total and grade. Stated figures for market size and revenue growth undergo verification via WebSearch. The tool refuses to accept unverified metrics.
Output is written directly to pitch-review.md in the working directory. It details slide-by-slide feedback, highlights five high-impact fixes, and lists any missing sections for the startup's stage. It also predicts at least five investor pushbacks with actionable verbal responses and deck revisions.
What it helps with
- review pitch deck slides and build a structured narrative inventory
- calculate a weighted score across eight investor-focused evaluation criteria
- predict five or more investor objections with verbal answers and deck fixes
- verify market size claims and revenue figures through web search
- compare the presentation against established benchmark decks
Example prompts for the agent
- Review the startup presentation in
deck.pdfand write the feedback topitch-review.md - Evaluate our slide deck folder
slides/across all eight scoring dimensions - Analyze the public Google Slides link, predict investor objections, and identify missing sections
How to install pitch-deck-reviewer
1Skills CLI (Vercel)
npx skills add OneWave-AI/claude-skills --skill pitch-deck-reviewer -a claude-code2Manually: put the files in place
~/.claude/skills/pitch-deck-reviewer/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/pitch-deck-reviewer/
1Skills CLI (Vercel)
npx skills add OneWave-AI/claude-skills --skill pitch-deck-reviewer -a codex2Manually: put the files in place
.agents/skills/pitch-deck-reviewer/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add OneWave-AI/claude-skills --skill pitch-deck-reviewer -a cursor2Manually: put the files in place
.cursor/skills/pitch-deck-reviewer/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install OneWave-AI/claude-skills pitch-deck-reviewer2Manually: put the files in place
.github/skills/pitch-deck-reviewer/SKILL.md1Skills CLI (Vercel)
npx skills add OneWave-AI/claude-skills --skill pitch-deck-reviewer -a gemini-cli2Platform CLI
gemini skills install https://github.com/OneWave-AI/claude-skills --path pitch-deck-reviewerManually: put the files in place
.devin/skills/pitch-deck-reviewer/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add OneWave-AI/claude-skills --skill pitch-deck-reviewer -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about pitch-deck-reviewer
How to install pitch-deck-reviewer in Claude Code?
Run npx skills add OneWave-AI/claude-skills --skill pitch-deck-reviewer -a claude-code. The skill definition will be placed in ~/.claude/skills/pitch-deck-reviewer/SKILL.md.
What file formats are supported?
The skill processes PDF documents, PPTX decks, PNG and JPG images, markdown notes, and public Google Slides links. Files with the .pen extension cannot be read directly.
What does the pitch-review.md report include?
The report contains an overall weighted score, slide-by-slide critiques, and the top five improvements ranked by impact. It also includes at least five predicted investor objections with suggested verbal answers and comparisons to two benchmark decks.
Source text
SKILL.md · MIT
---
name: pitch-deck-reviewer
description: Reviews pitch decks and investor presentations. Reads slide content, evaluates narrative flow, problem/solution clarity, market sizing, competitive positioning, financial projections, team credibility, and ask clarity. Generates a scored pitch-review.md with slide-by-slide feedback, overall score, top improvements, investor objection predictions, and comparisons to successful decks. Use when reviewing fundraising materials, investor decks, or pitch presentations.
tools: Read, Glob, Grep, Bash, Write, Edit, WebSearch, WebFetch
model: inherit
---
# Pitch Deck Reviewer
Review a pitch deck with VC-grade rigor and produce a scored, actionable `pitch-review.md`.
## Contents
- `references/evaluation-framework.md` -- The 8 scored dimensions, weights, red flags, scoring guides, design notes, and overall-score calculation.
- `references/objections-and-benchmarks.md` -- Investor objection categories and the canonical successful-deck benchmarks.
- `references/output-template.md` -- The exact `pitch-review.md` structure to generate.
## Workflow
1. Ingest the deck. Determine file type and location, then read every slide. Supported inputs: PDF (Read directly; for 10+ pages read in batches via the `pages` parameter), PowerPoint .pptx (invoke the pptx skill or Read), Google Slides links (WebFetch if public), images PNG/JPG (Read to inspect visually), markdown/text descriptions, and directories of slide images (Glob to enumerate, then Read each). For .pen files, state that they cannot be read directly.
2. Build a slide inventory. Catalog each slide by number and primary content before any analysis. Identify company name, stage, and industry. Flag any deck over 20 slides as a concern itself; most successful decks run 10-15.
3. Score the 8 dimensions. Apply `references/evaluation-framework.md`. Score each 1-10 with specific evidence from the deck, then compute the weighted overall score and assign the grade label.
4. Write slide-by-slide feedback. Cover every slide with content summary, purpose, effectiveness, strengths, weaknesses, and recommendations.
5. Predict investor objections. Generate at least 5 using the categories in `references/objections-and-benchmarks.md`, each with severity, trigger, suggested verbal response, and deck fix.
6. Compare to benchmark decks. Reference at least 2 relevant decks from `references/objections-and-benchmarks.md`; name where this deck is stronger, weaker, and what to borrow.
7. Rank the top 5 improvements by impact and list any missing slides or sections for this stage and industry.
8. Assemble `pitch-review.md` per `references/output-template.md`. Write the executive summary last. Save it beside the source deck (or the working directory). Show the overall-score math.
## Calibration
- Verify any market-size, revenue, or growth claim with WebSearch before accepting it. Never fabricate metrics, comparisons, or statistics.
- Reserve 9-10 on a dimension for work that sets a new standard. Give an overall below 3.0 only when the deck has almost no usable content.
- Adjust for stage: weight pre-product decks toward problem/solution clarity, team, and market; relax traction and financials expectations and note the calibration.
- Score absent major sections (e.g., missing financials or team) 1-2 and flag them in the executive summary and the missing-sections list. Review works in progress rather than refusing.
- Evaluate intentionally unconventional decks (memo-style, demo-first, single-page) on their own terms while noting the divergence from convention.
- For multiple versions, review the latest and note which changes improved the deck and which regressed.
## Voice
- Be direct and specific. Replace vague praise with concrete observations.
- Pair every critique with a concrete fix.
- Use investor framing ("This raises a question about...") over verdicts ("This is bad").
- Acknowledge what works before identifying gaps. Define any jargon used.
- Write for the founder, to help them improve.
© OneWave-AI · MIT · OneWave-AI/claude-skills