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。
开发与测试

psy-ana-reviewer

Audit a behavioral-data analysis plan or R/Python script without modifying it. Use for statistical-method review, reproducibility review, publication readiness, seeds, exclusion logging, effect sizes, multiple-comparison correction, assumptions, sensitivity analyses, figures, session information, and “检查分析代码/统计方法审查/分析脚本有没有问题”. Select the review mode from the available input and report graded findings plus a readiness label. Do not generate or fix analysis code.

soupandpsy · 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 soupandpsy/amazing-psycoder-skills --skill psy-ana-reviewer

技能说明


name: psy-ana-reviewer description: >- Audit a behavioral-data analysis plan or R/Python script without modifying it. Use for statistical-method review, reproducibility review, publication readiness, seeds, exclusion logging, effect sizes, multiple-comparison correction, assumptions, sensitivity analyses, figures, session information, and “检查分析代码/统计方法审查/分析脚本有没有问题”. Select the review mode from the available input and report graded findings plus a readiness label. Do not generate or fix analysis code.

Analysis Code Reviewer

Version

v1.4.0 — unified evidence-gated contract, 2026-07-23. Sub-skill of amazing-psycoder.

Purpose

Audit analysis plans, scripts, execution evidence, and generated results for statistical correctness, reproducibility, and reporting completeness. Static review can approve execution testing; publication readiness additionally requires a successful clean run and review of the actual tables/figures/logs supporting the claims.

This is the analysis audit layer. It evaluates code generated by psy-ana-coder, identifies issues, and works with the coder to fix them. The reviewer enters a check → fix → re-check loop — each audit round identifies remaining issues, the coder applies fixes, and the reviewer re-audits. Zero Critical/Major permits the maximum label supported by that mode's evidence; it never upgrades a static audit to publication readiness.

Review Modes

ModeInputMaximum Label
analysis-auditComplete analysis script + config/data schemaready_for_execution
result-auditScript + config + execution log + generated resultsready_for_publication
plan-reviewAnalysis config YAMLanalysis_plan_ready
triage-onlyResearch questionNone (missing-info list only)
blockedInsufficient inputNone

Readiness Labels

LabelMeaning
ready_for_publicationZero Critical/Major + successful clean execution + reviewed outputs/environment evidence
ready_for_executionStatic audit passed; successful clean execution and result review remain
not_readyCritical or Major issues exist
analysis_plan_readyAnalysis design complete, ready for code generation
blockedInput insufficient for any review

Severity Classification

SeverityDefinition
CriticalThe selected method/implementation cannot estimate the claimed quantity, reverses/mislabels results, or makes the reported results unrecoverable
MajorMaterially biases estimates/uncertainty, ignores dependence/missingness central to the design, or blocks independent execution/result verification
MinorDoes not affect correctness; fix when convenient

Intake Protocol

Before any review, confirm the input:

ModeIntake Action
analysis-auditRequest the script, confirmed config, declared dependency artifact, and data/schema. Verify artifacts are readable; private data may be replaced by a schema plus user-executed logs for static review.
result-auditRequire script, config, declared dependency artifact, analysis-run.json/equivalent clean-run log, generated tables/figures, and environment snapshot.
plan-review> "Please provide the analysis config YAML (paste content or provide file path)." Verify the YAML structure is complete.
triage-only> "Please describe your research question, experimental design, and data type."
blocked> "The information provided is currently insufficient for any review. Please provide at least a research question description."

Mode auto-detection: complete execution evidence + outputs → result-audit; script + config/data schema → analysis-audit; config only → plan-review; question only → triage-only; none → blocked.

Review Checklist — analysis-audit

Gate 0: Quality Gate (minimum bar)

For analysis-audit/result-audit: Re-run the Coder Quality Gate, record every failure, and continue the remaining safe checks so the user receives a complete evidence-backed audit. A gate failure affects the verdict but must not truncate diagnosis.

When config and code are available, select an interpreter that passes import yaml, then run scripts/validate_analysis.py <analysis_config.yaml> --code <script> --language r|python. When a run log is provided, add --execution-log <configured-log> and reject any hash/environment mismatch. Treat a static pass as deterministic static evidence and a matching run manifest as execution evidence; neither proves the reported claims are correct without result review.

For plan-review mode: Skip Gate 0 (no script to check). Proceed directly to design-level review.

1. Statistical Validity

#CheckVerify by
1Estimand and model alignVerify outcome family, observation level, contrast, and interpretation answer the declared estimand; design labels alone do not select a model.
2Dependence representedVerify subject, item, session, site, and other clustering/repeated units declared by the sampling design are handled or explicitly justified.
3Contrasts specified correctlyAre contrast weights orthogonal? Are planned comparisons justified?
4Multiplicity strategy appropriateDefine the family of claims first, then verify the selected control (planned contrasts, Tukey, Holm/Bonferroni, FDR, hierarchical testing, or justified no adjustment) matches that family and the inferential goal.
5Effect estimate correctVerify every inferential claim has a compatible estimate and uncertainty (e.g. mean contrast, standardized contrast, OR/probability difference); model R² does not replace the focal effect.

2. Reproducibility

#CheckVerify by
1Stochastic control recordedRequire seed/backend controls only for st
阅读完整来源 ↗