What do I need to use Assumption Audit?

The plan, belief, or conclusion; Your reasoning; What's at stake; What you're treating as certain.

Is Assumption Audit free to use?

Yes — run it free in the browser playground (no API key needed for the sponsored trial, or bring any provider key), or install it into Claude Code, Cursor, ChatGPT and more via npx pm-claude-skills. MIT-licensed and open source.

Assumption Audit

Q: How do I know the Assumption Audit output is good?

The skill verifies itself against its own quality checks: Assumptions are actually surfaced, including invisible ones; Each is ranked by how load-bearing it is; The critical assumptions are flipped to show consequences; The riskiest (wrong × load-bearing) is identified.

🔵 Stable🕐 updated 2026-08-06 🔷 SkillSpec L3 pm-thinking

Surface the hidden assumptions a plan or belief rests on, then test what happens when each one is wrong. Use when asked what am I assuming here, check my assumptions, what if I'm wrong about, or stress-test my thinking. Produces the unstated assumptions your conclusion depends on (ranked by how load-bearing they are), a flip of each to see which one breaking would change everything, and the cheapest way to check the riskiest ones — because the assumption you didn't know you were making is what sinks plans.

▶ Run it free — no key needed 📝 Grade your existing draft View SKILL.md ↗

🗣 Say this to your agent

“What am I assuming in this plan?”“Check my assumptions about this business idea.”“Stress-test my thinking here — what if I'm wrong?”“I'm sure this will work — what am I not questioning?”“What hidden assumption could sink this?”

What to give it

▸The plan, belief, or conclusion — what you want audited

▸Your reasoning — how you got there (reveals the assumptions)

▸What's at stake — so we know how hard to test

▸What you're treating as certain — the beliefs you're most confident in (often the riskiest)

✅ The bar it holds itself to

Every skill in this library self-verifies — these are this skill's own quality checks, straight from its definition.

✓Assumptions are actually surfaced, including invisible ones

✓Each is ranked by how load-bearing it is

✓The critical assumptions are flipped to show consequences

✓The riskiest (wrong × load-bearing) is identified

✓A cheap, concrete check is proposed for it

⚠️ What it refuses to do

**Only listing obvious assumptions** and missing the buried ones.

**Treating all assumptions as equally important.**

**Naming risks without flipping** to see what breaking them does.

**No cheap test** — leaving the person to just bet on it.

Install

npx pm-claude-skills add --agent claude   # or codex · cursor · gemini · hermes
# or one-line MCP (every skill, any client):
claude mcp add pm-skills -- npx -y pm-claude-skills-mcp

Related skills

🔌 Embed this skill

Drop this on your blog, docs, or site — it renders a "Run this skill" card:

<div data-pm-skill="assumption-audit"></div>
<script src="https://mohitagw15856.github.io/pm-claude-skills/embed.js" async></script>

💬 Discussion

Assumption Audit is one of 1078 open-source professional AI agent skills — all SkillSpec L3. Try them all in the browser · ⭐ Star on GitHub · Browse the full catalog