lit-audit

Audit academic manuscript claims against extraction notes with status labels.

37|5|Updated Jun 6, 2026
One-click install
npx skills add https://github.com/bionoob7/nlr-workflow --skill lit-audit
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: lit-audit
Source: https://github.com/bionoob7/nlr-workflow/tree/main/.claude/skills/lit-audit
Command: npx skills add https://github.com/bionoob7/nlr-workflow --skill lit-audit

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires python, python-markdown, python-regex, python-bibTeX, python-zotero, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill addresses the challenge of verifying the factual accuracy of academic literature review manuscripts by meticulously cross-referencing quantitative claims with source extraction notes.

Core Features & Use Cases

  • Factual Accuracy Verification: Cross-checks metric values, dataset names, model names, and sample sizes against source extraction notes.
  • Manuscript Review Support: Useful before any style editing pass to ensure numbers are consistent with their sources.
  • Use Case: For instance, a researcher using this Skill can automatically verify if the number of subjects in a clinical study matches the number stated in the manuscript's text.

Quick Start

Invoke the lit-audit skill to automatically audit the factual fidelity of your manuscript, providing a comprehensive report of matched, mismatched, and uncited claims.

Frequently Asked Questions about lit-audit

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

FAQPage Schema
How do I verify factual accuracy in an academic manuscript against source notes?

Cross-checking quantitative claims like metric values and sample sizes against source extraction notes verifies factual accuracy in academic manuscripts. This process operates on markdown manuscript files and reports matched, mismatched, and uncited claims.

How does fact-checking work for quantitative claims in academic literature reviews?

Fact-checking for academic literature reviews works by cross-referencing dataset names, model names, and metric values stated in the text against source extraction notes. It generates a comprehensive report labeling matched, mismatched, and uncited claims.

Can I use python-bibTeX and python-zotero to audit markdown manuscript files?

Yes, dependencies like python-bibTeX and python-zotero support auditing markdown manuscript files. These tools parse references and extraction notes to verify numerical and qualitative claims within the manuscript.

What is the best way to cross-check dataset names and sample sizes in research papers?

Performing a detailed factual accuracy audit is the best way to cross-check dataset names and sample sizes in research papers. This automatically verifies quantitative claims against source extraction notes and flags inconsistencies before style editing.

When do I need to perform a factual accuracy audit on academic manuscripts?

You need to perform a factual accuracy audit on academic manuscripts before any style editing pass. This ensures numbers, dataset names, and model metrics are consistent with their original extraction notes and sources.