跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
其他技能

data-validator

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.

MAGA2010 · 已有静态检查记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add MAGA2010/data-master --skill data-validator

技能说明


name: data-validator description: "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." parent: data-master stage: 3c

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