audit-reproducibility

Verify numeric claims in research manuscripts against analysis outputs with tolerance thresholds.

1|1|Updated Apr 30, 2026
One-click install
npx skills add https://github.com/xashgg/claude-code-my-workflow-codex --skill audit-reproducibility-xashgg
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: audit-reproducibility
Source: https://github.com/xashgg/claude-code-my-workflow-codex/tree/main/.codex/skills/audit-reproducibility
Command: npx skills add https://github.com/xashgg/claude-code-my-workflow-codex --skill audit-reproducibility-xashgg

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires R, Stata, Python, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the verification of numeric claims in research manuscripts, ensuring accuracy and reproducibility before submission.

Core Features & Use Cases

  • Numeric Claim Verification: Cross-checks numeric claims in manuscripts against actual analysis outputs.
  • Tolerance Thresholds: Reports PASS/FAIL based on defined tolerance thresholds.
  • Use Case: Before submission, use this Skill to ensure that all numeric results in a manuscript match the analysis outputs, reducing the risk of errors and enhancing reproducibility.

Quick Start

Run the audit-reproducibility skill on your manuscript by providing the path to the manuscript and the outputs directory. Example: audit-reproducibility path/to/manuscript.tex path/to/outputs

Frequently Asked Questions about audit-reproducibility

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

FAQPage Schema
How do I verify numeric claims in a research manuscript against analysis outputs?

To verify numeric claims in a research manuscript, you can cross-check the manuscript text against analysis outputs. This automated process reports PASS or FAIL based on defined tolerance thresholds to ensure numeric accuracy.

What is manuscript reproducibility checking and when do I need it?

Manuscript reproducibility checking is the automated cross-validation of numeric results against analysis outputs. You need it before manuscript submission to reduce errors and ensure that all reported numbers match your computational outputs.

Does reproducibility checking work with R, Stata, and Python outputs?

Yes, reproducibility checking works with R, Stata, and Python analysis outputs. You provide the manuscript file and the outputs directory, and the tool cross-checks the numeric claims against the generated results.

How do I run a pre-submission numeric cross-check on my manuscript?

To run a pre-submission numeric cross-check, provide the path to your manuscript and the outputs directory. The tool automatically verifies numeric claims and reports PASS or FAIL based on established tolerance thresholds.

What are the limitations of automated numeric claim verification?

Automated numeric claim verification requires analysis outputs from R, Stata, or Python and a manuscript file. It validates numbers strictly based on tolerance thresholds, meaning any missing analysis outputs or unformatted numeric claims will prevent successful verification.

What's the best way to prepare a replication package for numeric validation?

The best way to prepare a replication package for numeric validation is to ensure your R, Stata, or Python analysis outputs are fully generated and accessible. The validation tool then cross-checks manuscript claims against these outputs.