reproducibility-audit
Skill0 starsChanged 5 days agoApache-2.0View on GitHub
Record what would be needed to reproduce an analysis, then check whether the artifacts have drifted.
4 other projects use a version of this.
Adopted by
Most recently taken up by
- mcfrank/claude-skillstheir own version, first seen Nov 15, 2026
- poldracklab/scientific-audit-skillstheir own version, first seen Nov 8, 2026
- cellrishi-code/claude-skills-atlastheir own version, first seen Nov 1, 2026
- jurgendn/agent-skillstheir own version, first seen Sep 17, 2026
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 4
- mcfrank/claude-skills★ 12same name
- jurgendn/agent-skills★ 10same name
- cellrishi-code/claude-skills-atlas★ 6same name
- poldracklab/scientific-audit-skills★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository6 other files it gives its agents.
- citation-auditSkill
- claim-evidence-auditSkill
- data-management-planSkill
- literature-reviewSkill
- manuscript-preflightSkill
- reviewer-responseSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 4 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 32
Do not execute the notebook to "make it reproducible".
- Distinctive: line 33
Do not overwrite the recorded baseline.
“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Reproducibility audit
Rules
- Record facts, not intentions: commit, lockfiles, environment, data hashes, seeds, run commands.
- A missing artifact is reported as missing, never filled in from memory.
- Drift is a comparison against a recorded baseline, not a guess.
Steps
repro_auditon the project root; capture the artifact manifest.notebook_capturefor.ipynbfiles; report execution order, hidden state, absolute paths and runtime installs.dataset_cardfor each dataset; flag PII-like columns and missing sections.- Bind the manifest to
research_reportevidence. - Re-run
repro_auditafter changes to show drift; do not edit the baseline.
Output
- Manifest summary: commit, lockfile, environment, data hashes, figures, seeds.
- Drift report with changed/missing artifacts.
- Notebook risks (out-of-order execution, unpinned installs).
- A three-level verdict: reproducible / partially / not reproducible.
Never
- Do not execute the notebook to "make it reproducible".
- Do not overwrite the recorded baseline.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.