evidence-audit
Skill2 starsChanged 59 days agoMITView on GitHub
Adversarial provenance audit of a draft deliverable before it ships — re-derive load-bearing claims at their sources, downgrade what fails. Use before publishing any client- or stakeholder-facing artifact containing numbers, ratings, prices, or "verified" language; or when the operator says "audit this", "check the claims", or "is this actually verified?"
6 other projects use a version of this.
Adopted by
Most recently taken up by
- youyu-code/research-pipeline-skillstheir own version, first seen Nov 8, 2026
- luciferprosun/AIOA-spArkHATtheir own version, first seen Oct 25, 2026
- juanitourquiza/shipframetheir own version, first seen Oct 23, 2026
- Jason-hub-star/model-orchestratortheir own version, first seen Oct 20, 2026
- ersinkoc/evidence-audittheir own version, first seen Oct 4, 2026
- crfldrxyz/AuthorOps-Skillstheir own version, first seen Sep 1, 2026
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 6
- juanitourquiza/shipframe★ 5same name
- ersinkoc/evidence-audit★ 4same name
- luciferprosun/AIOA-spArkHAT★ 2same name
- youyu-code/research-pipeline-skills★ 1same name
- crfldrxyz/AuthorOps-Skills★ 0same name
- Jason-hub-star/model-orchestrator★ 0same 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 repository14 other files it gives its agents.
- adapters/AGENTS.mdAGENTS.md
- adapters/CLAUDE.mdCLAUDE.md
- blast-radiusSkill
- deepenSkill
- diagnoseSkill
- dispatch-waveSkill
- grill-with-docsSkill
- session-closeoutSkill
- shipSkill
- symbol-surgerySkill
- tddSkill
- triageSkill
- write-a-skillSkill
- zoom-outSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 33
Do not fabricate a fetch you didn't make.
“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Evidence Audit
Adversarial audit pass for outbound deliverables. The rule being enforced (working-style.md § Audit discipline): an artifact's claim to have been verified is not verification — and that applies to your own drafts most of all. Search-tool snippets are hearsay; a "verified" label you attached without fetching the source is self-attestation.
Procedure
Honor the request's scope throughout this pass. For an audit-only request, report the exact problem, its consequence, and the smallest remedy; do not rewrite the artifact. Apply corrections when the existing task authorizes editing, without asking again for authorization already given.
- Extract the load-bearing claims. Scan the draft for: prices/fees, ratings and review counts, statistics ("1 in 3...", "N% of..."), superlatives tied to numbers, and every instance of "verified / confirmed / checked directly / pulled directly." Load-bearing = a claim whose failure would change the recommendation or embarrass the sender. List them with locations.
- Trace each to its actual provenance — from the session transcript, not from memory. For each claim, answer: was the source page fetched in-session (WebFetch/browse-tool), or did this number arrive in a search-result summary? Who owns the domain it came from? Vendor self-comparisons and competitor "analyses" are marketing, not evidence — a competitor's stat about its rival is the same failure as the vendor's stat about itself.
- Re-derive what carries "verified" language. Fetch the source directly. Three outcomes:
- Confirms → keep the label, note the fetch.
- Contradicts → fix the claim, not the label.
- Source blocks fetching (G2, Trustpilot 403s) → the claim cannot be labeled verified by anyone; downgrade to "search-corroborated," say the source blocks direct reads, and check whether the recommendation survives without the number. If it doesn't, the recommendation needs different footing.
- Check the deliverable's own confidence taxonomy against itself. If the doc promises "green = read at the source," every green tag must trace to a fetch in this session. A confidence system that lies on one row is worse than no confidence system.
- Hunt the cost/claim gaps. What does the draft imply is free, complete, or settled that isn't priced or checked? (Origin case: a "$0 to start" claim while the plan's only real recurring cost — video hosting — went unpriced.)
- Report findings and authorized corrections. Lead with what the evidence changes and why. In an authorized editing task, apply the corrections and retain conclusions only if the evidence still supports them. In an audit-only task, identify the required corrections and any conclusions that no longer hold.
Notes
- forge-signal has a deterministic version of steps 1–2 as a pipeline role:
src/pipeline/roles/fact-auditor.ts(claim extraction + provenance ledger). This skill is the full pass including re-derivation, which needs live fetches. - For client-facing artifact design provenance (palette/type grounded in the client's real brand), see
forge-signal/scripts/harvest-brand.mjs. - Do not fabricate a fetch you didn't make. "I could not verify X" in the report is a valid, useful finding.
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.

