agentleFS
Sign inStart free
MAGA2010MAGA2010/data-master/skills/data-validator/SKILL.md

data-validator

Skill78 starsChanged 23 days agoMITView on GitHub

Run the 8 Nature statistical gates and the journal checklist against the finished artifacts. Writes audit/final_audit.md and refuses the label submission-ready on a mandatory FAIL.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. fafa-ai-data-lab/ai-data-analyst-agent★ 44same 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 repository10 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    After the report exists. Also run it on a partially finished run to see which gate is still open -- the audit reads artifacts, so missing …

    line 17
  2. Distinctive:

    do not edit the report to make the audit pass.

    line 64
  3. Distinctive:

    do not turn a FAIL into a WARN because the run is late.

    line 65
  4. Distinctive:

    do not print PASS for registration, funding, consent or data availability -- those are author-supplied and are reported as AUTHOR INPUT …

    line 66

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

data-validator

Stage 3c of the data-master pipeline. The router in ../../SKILL.md owns the end-to-end run; this skill owns one stage and one gate. Read the parent contract before changing anything here: the invariants in ../../SKILL.md (additive-only, types decided once, default-FAIL gates, three-part provenance) are not restated, they are inherited.

When to invoke

After the report exists. Also run it on a partially finished run to see which gate is still open -- the audit reads artifacts, so missing ones surface as FAIL/N/A rather than as an exception.

Inputs

  • outputs/report.md
  • outputs/report_build.json
  • outputs/analysis/*.json
  • outputs/cleaned/cleaning_run.json
  • references/journal-reporting-standards.json

Outputs

  • outputs/audit/final_audit.md
  • outputs/audit/final_audit.json
  • exit code 0 (submission-ready), 1 (mandatory gate failed), 2 (cannot run)

Commands

python scripts/final_audit.py --outdir outputs --journal nature
python scripts/final_audit.py --outdir outputs --journal nejm --design randomized_trial
python scripts/final_audit.py --outdir outputs --template standard --json

Gate (default FAIL)

Gates 1, 2, 7 and 8 are mandatory at every template. Gates 3-6 are mandatory for nature and relax only where the selected template says so -- and the relaxation is printed, never silent.

Gate 1 also requires explicit question provenance for an estimable comparison: --unit-key, --group, and --outcomes must be user-declared. Automatic selections must be labelled exploratory in the report; a missing label or incomplete declaration fails the gate.

Failure modes seen in real runs

  • An audit that trusts the report. Gate 3 must read effect_sizes from inferential.json, not the sentence the report wrote about it.
  • A checklist borrowed from the wrong design. CONSORT applied to a cross-sectional survey produces a page of N/A and a false sense of coverage.
  • n = 1 matching inside n = 158. Token matching is boundary-aware for a reason.

Do not

  • do not edit the report to make the audit pass;
  • do not turn a FAIL into a WARN because the run is late;
  • do not print PASS for registration, funding, consent or data availability -- those are author-supplied and are reported as AUTHOR INPUT NEEDED.

Upstream / downstream

  • checklist: ../../references/nature-statistics-checklist.md
  • journals: ../../references/journal-reporting-standards.md
  • script: ../../scripts/final_audit.py

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free