Idea Autopsy
Stress-test a business idea — especially one an AI suggested — before anyone builds it. Use when the user says "autopsy this", "is this a business or bullshit", "test this idea", or pastes a startup/side-hustle idea and wants to know if it's real. Returns one of four verdicts: BUSINESS, BUSINESS WRONG OWNER (real idea, wrong constraints — says which), BULLETIN (it's really just content or information), or BULLSHIT, plus the smallest test that would prove it wrong. Built from a four-hour session in which an LLM pitched twelve businesses and eleven died.
Install
npx skills add auracura/idea-autopsy --skill idea-autopsygit clone --depth 1 https://github.com/auracura/idea-autopsy.git /tmp/idea-autopsy
mkdir -p ~/.claude/skills
cp -r /tmp/idea-autopsy/. ~/.claude/skills/idea-autopsyPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Idea Autopsy ## The idea in one line LLMs are very good at generating plausible businesses and very bad at knowing which ones are real. The machine generates; a human decides. This skill is the deciding, written down. It is deliberately hostile: its job is to kill the idea. If the idea survives, build the smallest test, not the product. ## Hard rules 1. **Kill first, praise never.** Lead with what would make this fail. "Strong idea" is banned. 2. **Every claim needs a receipt.** A competitor must be named. A number must have a source. "Commonly" and "typically" are not evidence. 3. **Search before judging.** Run at least three web searches: incumbents, the graveyard (who tried this and died), and the pain (is anyone actually complaining). 4. **The owner's constraints are the law.** Hours per week, money available, audience size, location, and what they refuse to do. An idea that is a business for someone else can be bullshit for this person. 5. **End with a verdict and one test.** Never end with a list of considerations. ## Step 0 — Pin the constraints (ask if missing) - Hours per week the owner actually has (and whether evenings-only). - Revenue target and deadline (e.g. US$1,500/month in 6 months). - Audience or distribution they already own (be honest: "a newsletter nobody reads" = none). - Market they can reach (country, language, payment methods). - What they refuse to do (cold calls, casework, marketing, physical presence).
Details
- Skill name
idea-autopsy- Repository
- auracura/idea-autopsy
- License
- MIT
- Repo updated
- 30 October 2026
FAQ
What does the Idea Autopsy skill do?
Stress-test a business idea — especially one an AI suggested — before anyone builds it. Use when the user says "autopsy this", "is this a business or bullshit", "test this idea", or pastes a startup/side-hustle idea and wants to know if it's real. Returns one of four verdicts: BUSINESS, BUSINESS WRONG OWNER (real idea, wrong constraints — says which), BULLETIN (it's really just content or information), or BULLSHIT, plus the smallest test that would prove it wrong. Built from a four-hour session in which an LLM pitched twelve businesses and eleven died.
How do I install the Idea Autopsy skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add auracura/idea-autopsy --skill idea-autopsy. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Idea Autopsy popular?
It lives in auracura/idea-autopsy, which has 5 GitHub stars and 0 forks.
Related skills
Lead Free Heat Resistant Ceramics
5dungnotnull/lead-free-heat-resistant-ceramics-agent-skill
Lead-Free Heat-Resistant Ceramic Glaze & Body Formulation — Production-grade Ceramic Materials & Lead-Free Glaze Engineering analysis harness. Use this skill whenever analyzing ceramic materials, formulating lead-free glazes, designing clay bodies, evaluating thermal expansion fit, testing food-safety compliance, or recommending firing schedules. This skill provides evidence-backed, risk-disclosed analysis with authoritative sourcing.
Clerk
5wrsmith108/clerk-claude-skill
Clerk authentication integration for Astro/Next.js. Use when implementing authentication, handling Clerk middleware, testing with Playwright, or debugging auth issues. Trigger phrases include "Clerk auth", "sign in", "authentication", "middleware", "E2E testing with Clerk".
River Trash Boom Robot Design
5dungnotnull/river-trash-boom-robot-design-agent-skill
Autonomous River Trash-Boom Design & Testing — Production-grade harness for Autonomous River Debris-Boom Robotics & Hydraulics evidence-backed analysis with real-time data aggregation, recognized domain methods, and self-improving knowledge pipeline.
Bet on It
5Lum1104/bet-on-it
Use when debugging or changing behavior based on an uncertain causal hypothesis that the next action can test.
Never Again
1malaysherasia-ai/claude-never-again
Capture a bug or mistake as a permanent guardrail so it cannot happen twice. Use this skill whenever a bug is fixed, a test fails and is repaired, the user says "you did that again", "don't do that", "remember this", "never do X", or any correction is made that a future session would otherwise forget. Also use when the user asks to review, promote, or clean up existing lessons and hooks.
QA Engineering Suite
5aks-builds/quality-skills
107 production-grade QA engineering skills covering frontend, API, performance, mobile, security, CI, and AI/LLM testing. Use when writing or reviewing Playwright, pytest, Jest, k6, Cypress, Newman, or JUnit tests, auditing test coverage, designing test data strategies, or building quality gates in CI pipelines.
Browse the most popular Claude skills, all testing & qa skills, or write your own with the skills generator.