evidence-auditor

Audit research claims against manuscript content and identify evidentiary gaps.

497|38|Updated Jan 7, 2026
One-click install
npx skills add https://github.com/WILLOSCAR/research-units-pipeline-skills --skill evidence-auditor
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: evidence-auditor
Source: https://github.com/WILLOSCAR/research-units-pipeline-skills/tree/main/.codex/skills/evidence-auditor
Command: npx skills add https://github.com/WILLOSCAR/research-units-pipeline-skills --skill evidence-auditor

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill addresses the critical need to rigorously verify the evidence supporting claims made in research papers, particularly during peer review, by identifying and documenting any gaps or weaknesses in the provided support.

Core Features & Use Cases

  • Claim Verification: Systematically checks if empirical or conceptual claims are adequately supported by evidence presented in the manuscript.
  • Gap Identification: Pinpoints specific areas where evidence is missing, weak, or improperly cited.
  • Actionable Recommendations: Suggests minimal, concrete steps to address identified evidence gaps.
  • Use Case: During a peer review process, this skill can be used to ensure that every assertion made by the authors is backed by solid experimental results, theoretical arguments, or appropriate citations, flagging any unsupported statements for revision.

Quick Start

Use the evidence-auditor skill to audit the evidence for claims in output/CLAIMS.md.

Frequently Asked Questions about evidence-auditor

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I verify evidence for claims during academic peer review?

Gap analysis in academic writing identifies evidentiary gaps by cross-referencing assertions against manuscript content. It pinpoints specific areas where evidence is missing, weak, or improperly cited, flagging unsupported statements for revision.

What is the best way to identify unsupported statements in a manuscript?

To perform claim verification on a manuscript, input clear claims and manuscript context to generate a report on missing or weak evidence. This workflow applies to academic peer review and manuscript self-correction by systematically checking if assertions are backed by solid results.

Can I use this evidence audit skill for manuscript self-correction?

Yes, you can use this evidence audit skill for manuscript self-correction. It applies to self-correction workflows by systematically checking if every assertion is backed by solid experimental results, theoretical arguments, or appropriate citations, flagging any unsupported statements.

Does claim verification work without providing manuscript context?

No, claim verification requires clear input of claims and manuscript context to generate a report on missing or weak evidence. Without providing the manuscript content, the skill cannot cross-reference assertions or identify evidentiary gaps.

What are the limitations of evidence audit for research integrity?

The limitation of evidence audit for research integrity is that it only identifies missing or weak evidence based on provided manuscript content. It requires clear input of claims and context, meaning it cannot evaluate external data or sources not present in the input.