RA
Receipts Audit
🔵 Stable🕐 updated 2026-07-14
🔷 SkillSpec L3
pm-method
Audit any document against its own sources — every factual claim extracted and graded as evidenced, partially evidenced, unsupported, or contradicted, with the exact source line that supports or fails it. Use when asked to fact-check a document against its sources, check whether a report's claims are backed up, verify a deck against the data, or ask 'does this doc have receipts?'. Produces a claim ledger, unsupported claims ranked by load-bearingness, a fix-or-drop call per claim, and an honesty score with stated method.
What to give it
▸The document — the report, deck text, post, memo, or page under audit
▸The sources — the data, citations, quotes, or evidence the document claims to rest on. If none are supplied, run the extraction anyway, grade everything Unsupported (no sources provided), and say so plainly at the top
▸Audience stakes (optional) — (optional) — who reads this and what they'd decide from it; used for load-bearingness ranking. If absent, infer from the document and label the inference
✅ 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.
✓Every graded claim cites a specific source line or explicitly says none was provided
✓Causal claims and superlatives are extracted, not just numbers
✓Contradicted claims show both lines — the claim and the source — verbatim
✓The load-bearing ranking reflects the document's argument, not claim order
✓Every failing claim ends in Fix (with wording) or Drop — no "verify later" limbo
✓The honesty score shows its arithmetic in the artifact
⚠️ What it refuses to do
Do not grade a claim by plausibility — only by the provided sources
Do not let a true-but-unsourced claim pass as evidenced — Unsupported means unsupported here, not false
Do not invent sources — if you recall external evidence, it does not exist for this audit
Do not average away a Contradicted claim — one contradiction outweighs ten evidenced footnotes
Do not fix a claim by vaguening it — fixes bind wording to a real source line, or the claim drops
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-mcpRelated skills
🔌 Embed this skill
Drop this on your blog, docs, or site — it renders a "Run this skill" card:
<div data-pm-skill="receipts-audit"></div>
<script src="https://mohitagw15856.github.io/pm-claude-skills/embed.js" async></script>💬 Discussion
Receipts Audit is one of 599 open-source professional AI agent skills — all SkillSpec L3.
Try them all in the browser · ⭐ Star on GitHub · Browse the full catalog