assumption-audit
Use as the mandatory evidence gate before signing off on any strategy, PRD, or business case—audits every key claim against documented sources and assigns calibrated probabilities.
npx skills add majiayu000/claude-skill-registry --skill assumption-audit --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
## Overview Assumption-audit is the "evidence gate" that prevents Resulting (evaluating decisions by outcomes) and Hindsight Bias (feeling something was predictable after it happened). It forces an honest accounting of what is known versus what is guessed. ## Iron Law `NO SIGN-OFF WITHOUT VALIDATION EVIDENCE FOR EVERY KEY CLAIM` Assertions without evidence are vulnerabilities. Unaudited assumptions create fragile strategies that collapse under the first sign of volatility. ## State Machine ```dot digraph assumption_audit_flow { "Start" [shape=doublecircle]; "Step 1: Inventory Key Assumptions" [shape=box]; "Step 2: Evidence Mapping (Knowledge Tracker)" [shape=box]; "Step 3: Stress-Test (Pre-mortem)" [shape=box]; "Step 4: Probability Calibration" [shape=box]; "Gate: Claim-Evidence Match" [shape=diamond]; "Step 5: Fragility Audit (Via Negativa)" [shape=box]; "Done: Audit Passed" [shape=doublecircle]; "Start" -> "Step 1: Inventory Key Assumptions"; "Step 1: Inventory Key Assumptions" -> "Step 2: Evidence Mapping (Knowledge Tracker)"; "Step 2: Evidence Mapping (Knowledge Tracker)" -> "Step 3: Stress-Test (Pre-mortem)"; "Step 3: Stress-Test (Pre-mortem)" -> "Step 4: Probability Calibrati
- Overview
- Iron Law
- State Machine
- When to Use This Skill
- When NOT to Use This Skill
- Core Process
- Step 1: Inventory Key Assumptions
- Step 2: Evidence Mapping (Knowledge Tracker)
- Step 3: Stress-Test (Pre-mortem & Backcasting)
- Step 4: Probability Calibration
- Step 5: Fragility Audit (Via Negativa)
- Cross-Skill Invocations
- Rationalization Table
- Red Flags
What does the assumption-audit skill do?
Use as the mandatory evidence gate before signing off on any strategy, PRD, or business case—audits every key claim against documented sources and assigns calibrated probabilities.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill assumption-audit --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.