agentleFS
Sign inStart free
PerryLinkPerryLink/dsh-research-skills/skills/claim-evidence-audit/SKILL.md

claim-evidence-audit

Skill0 starsChanged 5 days agoApache-2.0View on GitHub

Check that each claim is supported by the evidence it cites, then produce a reviewer-facing trail of verdicts.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. ChangChrisLiu/academic-writing-audit★ 4same 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 repository6 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Do not soften contradicted or disproven into "needs review".

    line 31
  2. Distinctive:

    Do not delete a claim to make the report cleaner.

    line 32

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Claim / evidence audit

Rules

  • A claim without a resolvable evidence id is unbound, not "probably fine".
  • Quote support is verbatim; paraphrase support needs semantic checking and must be labelled as such.
  • insufficient means "cannot decide", never "false".

Steps

  1. doc_anchor the source documents (PDF/HTML/LaTeX/Markdown); keep page/section anchors.
  2. claim_check each claim against its evidence id; record the verdict and the quote span.
  3. For numbers, run statcheck on the reported statistics; for pooled effects, meta_analysis.
  4. research_trail to render claim → evidence → verdict and to list unbound/dangling rows.
  5. research_report to seal the corrections; unresolved claims stay visibly marked.

Output

  • Table: claim id, verdict, evidence id, failing check, suggested repair.
  • Counts: verified / unverified / insufficient / contradicted / disproven.
  • Unbound and dangling rows called out separately.

Never

  • Do not soften contradicted or disproven into "needs review".
  • Do not delete a claim to make the report cleaner; mark it.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free