メニュー
Estimate the effect of an intervention for experiments and defensible quasi-experimental or observational designs; do not substitute prediction for identification.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
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-causal |
| description | Estimate the effect of an intervention for experiments and defensible quasi-experimental or observational designs; do not substitute prediction for identification. |
State the design, target population, estimand, effect with uncertainty, diagnostic evidence, identifying assumptions, and an action-limited conclusion. If the assignment story is unknown, report association only.
Do not call correlation causal, control for mediators or colliders, choose groups after seeing outcomes, or bury failed overlap or pre-trends.
For design diagnostics and sensitivity methods, read references/deep-guide.md.
