About evidence-auditor
evidence-auditor turns an existing claim ledger into an evidence-gap report for paper review. It identifies weak or missing support and actionable fixes without rewriting the manuscript or adding claims.
Key features
- 01Audits claims from `output/CLAIMS.md`
- 02Notes present and missing evidence
- 03Assigns severity and minimal fixes
- 04Writes a report and structured JSONL records
- 05Retains claim and gap identifiers
Use cases
- 01Find unsupported claims during paper review
- 02Identify missing baselines or weak evaluation evidence
- 03Track specific evidence gaps for follow-up
Install
Copy the command and run it in a terminal.
$
npx skills add https:/ / github.com/ willoscar/ research-units-pipeline-skills --skill evidence-auditorAfter installing, type/evidence-auditorin Claude Code to confirm it loaded.
Bundled filesscripts/run.py
Details
From the project READMEEvidence Auditor
Triggers & routing
- Trigger: evidence audit, missing evidence, unsupported claims, 审稿证据审计, 证据缺口.
- Use when:
paper-review流程中,需要逐条检查 claim 的证据链、缺 baseline、评测薄弱点。 - Skip if: 缺少 claims 输入(例如还没有
output/CLAIMS.md)。 - Network: none.
- Guardrail: 只写“缺口/风险/下一步验证”,不要替作者补写论述或引入新主张。
Transforms a claim ledger into a gap report for paper-review.
Input
output/CLAIMS.md
Output
output/MISSING_EVIDENCE.mdoutput/EVIDENCE_AUDIT.jsonl(review-evidence-gap.v1)
Contract
Each gap block should include:
- claim reference
- what evidence is already present
- what is missing or weak
- minimal fix
- severity
Each JSONL record must retain claim_id and a stable gap_id so the final
review can cite the exact failure rather than paraphrasing an unlocated concern.
Script boundary
scripts/run.py should:
- iterate existing claims only
- classify the likely evidence risk
- write actionable, bounded gap items
It should not invent new claims or rewrite the manuscript.
Acceptance
- every claim has a corresponding evidence note or gap item
- minimal fixes are actionable and concrete
- structured records join back to every
claim_id
Non-goals
- manuscript rewriting
- novelty assessment
- recommendation writing
Comments
Markdown supported