菜单
Review a notebook or analysis for correctness, reproducibility, leakage, weak validation, unsupported claims, and misleading communication.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Establish a dumb baseline and an honest validation harness before any real model, so every later number means something.
Rigor for causal questions and A/B tests (the effect of acting on X): confounding, post-treatment bias, valid control groups.
Rigor for descriptive and diagnostic analytics (what happened and why): denominators, grain, and confounded slices, not model leakage.
EDA kickoff for a fresh dataset: fixed opening scaffold (goal, imports, load, sanity), then chapters derived from the data; scan leakage, land a baseline.
Rigor for statistical inference (is the difference real): hypothesis tests, power, multiple comparisons, effect size over p-value.
Audit a dataset or pipeline for the five leakages that inflate a metric: target, preprocessing, temporal, group, and sampling.
| name | lemma-review |
| description | Review a notebook or analysis for correctness, reproducibility, leakage, weak validation, unsupported claims, and misleading communication. |
Return findings ranked by severity, with concrete evidence, consequence, and a specific correction. Distinguish correctness defects from optional improvements.
Do not rewrite the analysis merely for style, accept a clean-looking notebook as proof, or report only aggregate metrics when a material group failure is visible.
For detailed review patterns, read references/deep-guide.md.
