Agent skill

Analyze Pitch Deck

by davepoon in davepoon/buildwithclaude

Activate for ANY pitch deck analysis, feedback, or review request.

MITAuto-check passedBusiness, Finance & HR

Install Analyze Pitch Deck

skills CLI
$ npx skills add davepoon/buildwithclaude --skill analyze-pitch-deck -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install davepoon/buildwithclaude analyze-pitch-deck --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/davepoon/buildwithclaude.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/venture-capital-intelligence/skills/analyze-pitch-deck .claude/skills/analyze-pitch-deck && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
analyze-pitch-deck
GitHub stars
3.6k
Token cost
~2.4k tokens
SKILL.md length
931 words
Files
1
Skills in repo
247
Repo updated
First seen
Licence
MIT

At a glance

Activate for ANY pitch deck analysis, feedback, or review request.

  • Works in 5 steps: EXTRACT DECK CONTENT → SCORE EACH SLIDE (1–10) → DETECT RED FLAGS → …
  • Include: analyze this deck
  • SKILL.md covers STEP 1 — EXTRACT DECK CONTENT, STEP 2 — SCORE EACH SLIDE (1–10), STEP 3 — DETECT RED FLAGS and STEP 4 — BENCHMARK AGAINST…, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Analyze Pitch Deck is an agent skill from davepoon/buildwithclaude. Activate for ANY pitch deck analysis, feedback, or review request. Triggers include: "analyze this deck", "review my pitch deck", "critique my pitch", "feedback on my slides", "is my deck investor ready", "what's wrong with my pitch", "how would a VC react to this deck", "score my pitch deck", "rate my slides", "improve my deck", "what slides am I missing", "is this pitch compelling". Also triggers when a user pastes slide content, describes their deck structure, or shares a company narrative and asks for…

Its SKILL.md is about 2.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Business, Finance & HR, covering Fundraising and pitch decks and Slides and decks. It works with React. The repository describes itself as: A single hub to find Claude Skills, Agents, Commands, Hooks, Plugins, and Marketplace collections to extend Claude Code, Claude Desktop, Agent SDK and OpenClaw. The licence is MIT.

When your agent uses it

  • Include: analyze this deck
  • Review my pitch deck
  • Critique my pitch
  • Feedback on my slides

Example prompts

  • “analyze this deck”
  • “review my pitch deck”
  • “critique my pitch”
  • “/analyze-pitch-deck”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. EXTRACT DECK CONTENT
  2. SCORE EACH SLIDE (1–10)
  3. DETECT RED FLAGS
  4. BENCHMARK AGAINST FAMOUS DECKS
  5. GENERATE SPECIFIC IMPROVEMENTS

What it can do on your machine

Read from SKILL.md and the folder at commit 616deb5. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Analyze Pitch Deck loads about 2.4k tokens when it runs. Until then it costs about 146 tokens; SKILL.md has 931 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~146
When it runs · the whole SKILL.md, loaded when a task matches
~2.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from davepoon/buildwithclaude at commit 616deb5, republished under its MIT licence (© davepoon). 931 words, ~2,442 tokens.

Download SKILL.mdSave it as .claude/skills/analyze-pitch-deck/SKILL.md (or your agent's skills folder).
name
analyze-pitch-deck
description
Activate for ANY pitch deck analysis, feedback, or review request. Triggers include: "analyze this deck", "review my pitch deck", "critique my pitch", "feedback on my slides", "is my deck investor ready", "what's wrong with my pitch", "how would a VC react to this deck", "score my pitch deck", "rate my slides", "improve my deck", "what slides am I missing", "is this pitch compelling". Also triggers when a user pastes slide content, describes their deck structure, or shares a company narrative and asks for investor feedback. Works on claude.ai and Claude Code.

Venture Capital Intelligence — Pitch Deck Analyzer

You are a partner at a top-tier VC firm who has reviewed over 5,000 pitch decks. You've seen what separates the Airbnb deck (raised at $1.5M valuation, simple and visual) from the Uber deck (led with market size), the LinkedIn deck (network effects front and center), and the hundreds of decks that never got a second meeting.

Your job: evaluate a pitch deck slide-by-slide against the proven winning structure, identify red flags, benchmark against famous successful decks, and give specific actionable feedback.


STEP 1 — EXTRACT DECK CONTENT

Map the user's deck against the 11-slide winning structure. If a slide is missing, note it as MISSING. If multiple slides cover one topic, note the overlap.

The 11-slide winning structure (seed stage, joelparkerhenderson/pitch-deck):

01  TITLE          Company name, tagline, contact — 5-second clarity test
02  PROBLEM        Big, painful, frequent problem — with data to prove it
03  SOLUTION       Your product — show don't tell (screenshot > description)
04  WHY NOW        Timing tailwind: tech shift, regulation, behavior change
05  MARKET SIZE    TAM > $1B, SAM, SOM with bottom-up math
06  BUSINESS MODEL How you make money, pricing, ACV, path to scale
07  TRACTION       Revenue, users, growth rate, key customers, retention
08  COMPETITION    2×2 matrix — positioning vs alternatives, why you win
09  TEAM           Founder backgrounds — why THIS team wins THIS market
10  FINANCIALS     3-year projections, burn rate, runway post-raise
11  THE ASK        How much, what you'll do with it, milestones to next round

STEP 2 — SCORE EACH SLIDE (1–10)

Scoring rubric:

  • 9–10: Exceptional. This slide would make a VC lean forward.
  • 7–8: Good. Gets the job done. Minor improvements possible.
  • 5–6: Adequate but forgettable. Won't open or close doors.
  • 3–4: Weak. Raises concerns or leaves key questions unanswered.
  • 1–2: Problematic. This slide could kill the deal on its own.
  • 0: Missing entirely.

Slide-specific criteria:

01 TITLE: Is the tagline memorable in one sentence? Does it pass the "explain to a 10-year-old" test? Does it make someone want to see the next slide?

02 PROBLEM: Is the problem big enough? Is it painful (frequent and costly)? Is there data or a story that makes the pain visceral? Avoid: "The market is inefficient" (too vague). Aim for: "Accountants spend 12 hours per month on X, costing firms $48K/year."

03 SOLUTION: Is there a clear product demo or screenshot? Does the solution directly address the stated problem? Is the "aha moment" visible in the first 10 seconds? Avoid feature lists — show the product working.

04 WHY NOW: This is the most underrated slide. VCs invest in timing as much as companies. Is there a specific catalyst: a new API, regulation, shift in infrastructure, or change in user behavior that makes now the right moment? Vague answers ("AI is transforming everything") score low.

05 MARKET SIZE: Is TAM > $1B (required for venture scale)? Are SAM and SOM calculated with bottom-up math (units × price), not just cited from industry reports? Does the math add up? Is the market growing?

06 BUSINESS MODEL: Is it clear how money is made? Is pricing shown (not just "SaaS")? Are unit economics mentioned (LTV:CAC if known)? Is the path to $100M ARR believable given the model?

07 TRACTION: Revenue, MRR, or users with growth rate — not just totals but growth trajectories. Are customer names shown (even 1-2 logos)? Is there a retention signal? Benchmarks: Seed = 15–20% MoM MRR growth.

08 COMPETITION: Does the 2×2 matrix show real differentiation vs real competitors (not "no one does what we do")? Are the axes meaningful and honest? Is the competitive moat clear?

09 TEAM: Does each founder have a clear "unfair advantage" for this specific market? Credentials matter less than founder-market fit. Prior startup experience is a plus. Is there a clear CEO?

10 FINANCIALS: Are the projections credible (not hockey-stick with no basis)? Are key assumptions stated? Is the burn rate reasonable? Is there 18+ months of runway post-raise?

11 THE ASK: Is the raise amount specific? Is the use of funds broken down? Are the milestones achievable with this capital and timed for the next funding event?


Show full SKILL.md (370 more words)Show less

STEP 3 — DETECT RED FLAGS

Scan for the 10 most common pitch deck killers (from julep-ai/pitch-deck-analyzer patterns):

  1. No clear problem: Solution in search of a problem
  2. TAM abuse: Top-down market sizing only ("$500B market, we need 1%")
  3. Missing Why Now: Why this exists today vs 5 years ago is unclear
  4. Feature, not product: Slides describe features, not user outcomes
  5. Vanity traction: Total downloads/signups without retention or revenue
  6. Fake 2×2: Competition matrix where the founder occupies a corner no one else does
  7. Superhero team: All credentials, no founder-market fit story
  8. Hockey stick financials: $0 to $100M ARR in 3 years with no stated basis
  9. Unclear ask: Raise amount doesn't match stated milestones
  10. Missing unit economics: No mention of LTV/CAC, gross margin, or payback period

STEP 4 — BENCHMARK AGAINST FAMOUS DECKS

Compare the deck to the most relevant reference from successful real decks (rafaecheve/Awesome-Decks):

  • Airbnb (2009): Clean, visual, simple problem/solution framing, TAM cited as $2B
  • Uber (2008): Led with market size, timing (smartphone + GPS), clear business model
  • LinkedIn (2004): Network effects as core thesis, viral coefficient shown
  • Dropbox (2008): Demo-driven, solved a universal pain, minimal text
  • Facebook (2004): Traction-first (1M users in 10 months), simple model
  • Buffer (2011): Transparent metrics, clear MRR growth, honest about stage
  • YouTube (2005): Usage data front and center, platform play articulated

Identify which famous deck this most resembles in structure, where it falls short, and what it should borrow.


STEP 5 — GENERATE SPECIFIC IMPROVEMENTS

For the 3 lowest-scoring slides, write specific rewrite suggestions — not "improve this slide" but "replace [current text] with [specific better version]."


OUTPUT FORMAT

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
DECK ANALYSIS  ·  [Company Name]  ·  [Stage]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

SLIDE SCORES
  01  Title          [X]/10  [████████░░]  [1-line comment]
  02  Problem        [X]/10  [████████░░]  [1-line comment]
  03  Solution       [X]/10  [████████░░]  [1-line comment]
  04  Why Now        [X]/10  [████████░░]  [1-line comment]
  05  Market Size    [X]/10  [████████░░]  [1-line comment]
  06  Business Model [X]/10  [████████░░]  [1-line comment]
  07  Traction       [X]/10  [████████░░]  [1-line comment]
  08  Competition    [X]/10  [████████░░]  [1-line comment]
  09  Team           [X]/10  [████████░░]  [1-line comment]
  10  Financials     [X]/10  [████████░░]  [1-line comment]
  11  The Ask        [X]/10  [████████░░]  [1-line comment]

  OVERALL DECK STRENGTH   [X.X]/10

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

RED FLAGS DETECTED
  🚩 [flag] — [specific issue and why it matters to investors]
  🚩 [flag] — [specific issue]
  [list all detected, minimum 0 maximum 5]

MISSING SLIDES
  ⬜ [slide name] — [why this slide matters and what it should contain]

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

BENCHMARK
  Closest to: [Famous Deck Name] — [why the comparison applies]
  Where it falls short: [specific gap]
  What to borrow: [specific technique from that deck]

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

TOP 3 IMPROVEMENTS (ranked by impact)

  1. [SLIDE NAME] (currently [X]/10 → target [Y]/10)
     Current: "[what the slide currently says or does]"
     Replace with: "[specific rewrite or restructure]"
     Why: [why this change moves the needle with investors]

  2. [SLIDE NAME] (currently [X]/10 → target [Y]/10)
     Current: "[current approach]"
     Replace with: "[specific rewrite]"
     Why: [investor logic]

  3. [SLIDE NAME] (currently [X]/10 → target [Y]/10)
     Current: "[current approach]"
     Replace with: "[specific rewrite]"
     Why: [investor logic]

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
INVESTOR READINESS:  [NOT READY / NEEDS WORK / CLOSE / READY TO SEND]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Investor Readiness thresholds:

  • READY TO SEND: Overall ≥ 8.0, no red flags, no missing slides
  • CLOSE: Overall 7.0–7.9, max 1 red flag, max 1 missing slide
  • NEEDS WORK: Overall 5.5–6.9, or 2–3 red flags
  • NOT READY: Overall < 5.5, or critical slides missing (Problem, Solution, Team, Ask)

TONE GUIDANCE

Be honest. A deck that is "not ready" with specific fixes is 10x more valuable than vague encouragement. Founders can handle truth — what they can't handle is going into investor meetings with a broken deck and not knowing why they're getting rejected. Be the partner who tells them before the meeting, not after.

© davepoon, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in plugins/venture-capital-intelligence/skills/analyze-pitch-deck of davepoon/buildwithclaude.

Open the folder on GitHubat commit 616deb5

Compare with similar skills

Analyze Pitch Deck next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Analyze Pitch Deck compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Analyze Pitch Deck this skilldavepoon/buildwithclaude3.6k—~2.4kAutomated safety check: PassMIT
Storyline Buildersruthir28/enterprise-ai-skills1481 repos~1.9kAutomated safety check: PassMIT
Replit Decksanqiufong/slides-from-anything1321 repos~2.9kAutomated safety check: PassApache-2.0
Deckleewayworks/guochuang-gps106—~546Automated safety check: PassMIT
HTML Ppt Creatorcigery-useio/useio-skills104—~2.4kAutomated safety check: PassNone
Pitch Deckemotixco/claude-skills-founder540—~1.1kAutomated safety check: PassMIT

Similar skills

  • Storyline Builder

    sruthir28/enterprise-ai-skills

    McKinsey-style storyline framework for building presentation decks.

    148 GitHub starsUsed in 1 repo~1.9k tokens
    Business, Finance & HRAuto-check passed
  • Replit Deck

    sanqiufong/slides-from-anything

    Single-file horizontal-swipe HTML deck in the style of Replit Slides's landing-page template gallery.

    132 GitHub starsUsed in 1 repo~2.9k tokens
    Business, Finance & HRAuto-check passed
  • Deck

    leewayworks/guochuang-gps

    A skill your agent uses when outlining, reviewing, or rehearsing a Guochuang pitch deck, project-book presentation, slide narrative, or visual evidence sequence.

    106 GitHub stars~546 tokensUpdated 1 mo ago
    Business, Finance & HRAuto-check passed
  • HTML Ppt Creator

    cigery-useio/useio-skills

    HTML 幻灯片制作技能,生成专业级静态 HTML 演示文稿。内置 36 套主题、15 套完整 deck 模板、31 种页面布局、47 个动效,以及演讲者模式(逐字稿提词器+计时器)。最终通过 bundle.js 打包为单 HTML 文件,可拷贝发送给他人。当用户要求做 PPT、幻灯片、演讲稿、分享 slides、pitch deck、小红书图文等时触发。

    104 GitHub stars~2.4k tokensUpdated 16 days ago
    Business, Finance & HRAuto-check passed
  • Pitch Deck

    emotixco/claude-skills-founder

    Outline a 12-slide investor pitch deck with a takeaway headline, content, visual, and speaker notes for every slide, plus appendix slides for Q&A.

    540 GitHub stars~1.1k tokensUpdated 2 days ago
    Business, Finance & HRAuto-check passed
  • Pitch Deck

    ailabs-393/ai-labs-claude-skills

    Generate professional PowerPoint pitch decks for startups and businesses.

    455 GitHub stars~2.3k tokensUpdated 11 mo ago
    Business, Finance & HRAuto-check passed

More from davepoon/buildwithclaude

All 247 skills in this repo
  • iOS Hig Design Guide

    davepoon/buildwithclaude

    Build, update, and apply iOS design specifications using Apple Human Interface Guidelines (HIG) source data.

    3.6k GitHub stars~735 tokensUpdated yesterday
    Auto-check passed
  • Video Downloader

    davepoon/buildwithclaude

    Download YouTube videos with customizable quality and format options.

    3.6k GitHub starsUsed in 1 repo~871 tokens
    Auto-check passed
  • Qwen Vision

    davepoon/buildwithclaude

    A skill your agent uses when the user asks to "analyze video", "watch this video", "what happens in this video", "describe this clip", "review this footage", "classify these videos", "compare…

    3.6k GitHub stars~1.2k tokensUpdated yesterday
    Auto-check passed
  • Atlas Cloud Media

    davepoon/buildwithclaude

    Discover Atlas Cloud image and video models, inspect their live schemas, and submit one confirmed media generation request with bounded GET polling.

    3.6k GitHub stars~852 tokensUpdated yesterday
    Auto-check passed
  • Browser Extension Launch

    davepoon/buildwithclaude

    面向没有编程经验的用户,把想法做成可试用的浏览器插件,并完成检查、商店材料、审核提交和上线验证;也用于继续已有插件、排错和发布新版。用户说“帮我做个插件”“把插件上架”“继续我的插件”时使用。普通网站开发、仅查询插件知识不触发。

    3.6k GitHub stars~1.5k tokensUpdated yesterday
    Auto-check passed
  • Slack Gif Creator

    davepoon/buildwithclaude

    Toolkit for creating animated GIFs optimized for Slack, with validators for size constraints and composable animation primitives.

    3.6k GitHub starsUsed in 12 repos~4.3k tokens
    Auto-check passed

Works with

Questions about Analyze Pitch Deck

What does Analyze Pitch Deck do?

Activate for ANY pitch deck analysis, feedback, or review request. Analyze Pitch Deck is an agent skill from davepoon/buildwithclaude. Activate for ANY pitch deck analysis, feedback, or review request.

When should I use Analyze Pitch Deck?

Analyze Pitch Deck fits situations like: include: analyze this deck; review my pitch deck; critique my pitch; feedback on my slides.

How do I install Analyze Pitch Deck in Claude Code?

Run `npx skills add davepoon/buildwithclaude --skill analyze-pitch-deck -a claude-code`. Or copy the skill folder (plugins/venture-capital-intelligence/skills/analyze-pitch-deck in davepoon/buildwithclaude) into .claude/skills/analyze-pitch-deck in your project. Claude Code loads it when a task matches its description.

How do I install Analyze Pitch Deck in Codex?

Run `npx skills add davepoon/buildwithclaude --skill analyze-pitch-deck -a codex`. Or copy the skill folder (plugins/venture-capital-intelligence/skills/analyze-pitch-deck in davepoon/buildwithclaude) into .agents/skills/analyze-pitch-deck in your project. Codex loads it when a task matches its description.

Can I use Analyze Pitch Deck in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add davepoon/buildwithclaude --skill analyze-pitch-deck -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/analyze-pitch-deck, .gemini/skills/analyze-pitch-deck, .github/skills/analyze-pitch-deck and .opencode/skills/analyze-pitch-deck in your project.

What does Analyze Pitch Deck need to run?

SKILL.md names no scripts, command-line tools or credentials: Analyze Pitch Deck is instructions for the agent only.

Does Analyze Pitch Deck access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Analyze Pitch Deck safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Analyze Pitch Deck use?

Analyze Pitch Deck is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Analyze Pitch Deck use?

About 2.4k tokens (SKILL.md is roughly 9.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Analyze Pitch Deck?

Skills that share tags, products or a category with Analyze Pitch Deck: Storyline Builder (sruthir28/enterprise-ai-skills, 148 stars), Replit Deck (sanqiufong/slides-from-anything, 132 stars), Deck (leewayworks/guochuang-gps, 106 stars) and HTML Ppt Creator (cigery-useio/useio-skills, 104 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Analyze Pitch Deck?

davepoon (a GitHub user) maintains it in davepoon/buildwithclaude, which has 3,610 GitHub stars. The repository holds 247 skills in this directory. The repository was last updated on October 9, 2026.

Source: davepoon/buildwithclaude on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.