claims-audit
Skill2 starsChanged 9 days agoMITView on GitHub
Inventory and verify checkable claims, quotations, dates, statistics, research summaries, causal statements, and citations in docs or prose. Use for factual review, source audits, citation checks, or verification when text relies on external events, scholarship, technical behavior, law, policy, or other verifiable assertions.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- loootai/reverse-engineertheir own version, first seen Nov 1, 2026
- mrveiss/AutoBot-AItheir own version, first seen Oct 15, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- mrveiss/AutoBot-AI★ 39same name
- loootai/reverse-engineer★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository21 other files it gives its agents.
- AGENTS.mdAGENTS.md
- agent-artifactSkill
- agent-discoverySkill
- agent-run-supervisionSkill
- api-contract-migrationSkill
- changelog-updateSkill
- change-reviewSkill
- ci-reviewSkill
- dependency-auditSkill
- derivation-auditSkill
- durable-cacheSkill
- engineering-auditSkill
- infer-conventionsSkill
- operational-signal-intakeSkill
- planned-releaseSkill
- preferred-stackSkill
- pressure-benchmarkingSkill
- public-surface-reconSkill
- rfc-processSkill
- security-auditSkill
- session-reviewSkill
The file
Files
Claims audit
Separate factual verification from prose preference. Testimony and clearly framed interpretation may be unverifiable without being defects. This skill does not score style, readability, lexical diversity, or narrative craft.
Read claims-audit.md in this skill directory for the ledger, verification steps, outcomes, formal-claim scope, freeze rules, contrary-pass procedure, repair rules, and report shape. Read references/evidence-bundle.md when the work needs a reusable source ledger. Read references/external-skill-intake.md when researching a public skill or prompt pack for possible addition to a prayers catalog.
Quick reference
inventory claims -> contrary pass before the constructive ledger -> follow cited sources -> prefer primary evidence -> freeze quantities from artifacts -> assign outcomes -> repair or qualifyOutcomes: supported, partially supported, unsupported, outdated, contested, unverifiable. A citation in the text is not an outcome.
Order the report by publication-blocking errors, then material qualifications, then accepted unverifiable testimony.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.