Audit Reproducibility

Audit Reproducibility is a Quality skill for Claude Code, published by pedrohcgs in claude-code-my-workflow.

1.5K stars2.9K forkson pedrohcgs/claude-code-my-workflowAdded 2026/08/19+1% in starsRepository updated 2026/06/10

academic-writingcausal-inferenceclaude-codeclaude-code-skillseconometricseconomicslatexquartoreproducible-researchresearch-workflow

Install in seconds

Install Audit Reproducibility

Copy Audit Reproducibility into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/pedrohcgs/claude-code-my-workflow/tree/main/.claude/skills/audit-reproducibility ~/.claude/skills/audit-reproducibility

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/pedrohcgs/claude-code-my-workflow.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: .claude/skills/audit-reproducibility/SKILL.md in pedrohcgs/claude-code-my-workflow
Installs to: ~/.claude/skills/audit-reproducibility
Collection: One of 25 skills cataloged from this repository
Category: Quality — 1354 skills

What Audit Reproducibility does

Audit Reproducibility compares numeric claims in a manuscript against actual analysis outputs and reports PASS/FAIL per claim against tolerance thresholds. Use it before submission, before releasing a replication package, or after a major revision to catch mismatches between the paper and the code.

Audit Reproducibility is cataloged under Quality on DirSkills. Audit Reproducibility comes from a repository tagged academic-writing, causal-inference, claude-code, claude-code-skills and econometrics.

Documentation

README

Excerpt

Audit Reproducibility

Compare numeric claims in a manuscript (point estimates, standard errors, p-values, counts) against the actual outputs produced by the analysis pipeline. Report PASS / FAIL per claim against the tolerance thresholds defined in .claude/rules/replication-protocol.md.

Core principle: If the paper says ATT = -1.632 (0.584) and the code produces -1.628 (0.591), we verify — numerically — that the difference is within the documented tolerance. No more "looks close enough" eyeballing.

When to use

This is the opening of the README. Read the full README on GitHub.

Commands Audit Reproducibility provides

Slash commands named in this skill’s SKILL.md, listed in the order they first appear.

/commit
/stata-replication
/verify-claims
/review-paper
/diagnose
/audit-reproducibility

Frequently asked about Audit Reproducibility

What else does pedrohcgs publish alongside Audit Reproducibility?
Audit Reproducibility is one of 25 skills that DirSkills catalogs from pedrohcgs/claude-code-my-workflow, the repository it ships in. Its siblings there include Capture Environment, Checkpoint and Coauthor Brief. Each one is a separate skill with its own page in this directory, installs the same way Audit Reproducibility does, and is maintained by pedrohcgs in that same repository. The rest of the collection is listed on the pedrohcgs/claude-code-my-workflow page.
How does Audit Reproducibility compare to other Quality skills?
Audit Reproducibility ranks #644 by stars among the 1354 Quality skills in this catalog. The most-starred ones next to it are Benchmark, Benchmark Optimization Loop and API Design Patterns. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Audit Reproducibility against them. Open each page to compare what they document and how they install.