菜单
Rigor for descriptive and diagnostic analytics (what happened and why): denominators, grain, and confounded slices, not model leakage.
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.
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.
Final modeling once the baseline and feature set are locked: tune against validation, audit overfitting, touch the test set once, justify the complexity.
| name | lemma-describe |
| description | Rigor for descriptive and diagnostic analytics (what happened and why): denominators, grain, and confounded slices, not model leakage. |
| homepage | https://github.com/tkpratardan/lemma |
| license | MIT |
Use this skill when a descriptive question needs a multi-step decomposition or competing explanations. The root contract covers bounded calculations.
Return the requested number, list, table, or diagnostic with its observation unit or denominator, population, and time boundary. Put the complete result in chat and stop when it and its material caveats are supported.
Use lemma-wrangle only when a reconciliation conflict prevents calculation.
Do not fit a model or imply causality from a slice.
For complex decompositions, read references/deep-guide.md.
