メニュー
EDA kickoff for a fresh dataset: fixed opening scaffold (goal, imports, load, sanity), then chapters derived from the data; scan leakage, land a baseline.
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.
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-eda |
| description | EDA kickoff for a fresh dataset: fixed opening scaffold (goal, imports, load, sanity), then chapters derived from the data; scan leakage, land a baseline. |
| homepage | https://github.com/tkpratardan/lemma |
| license | MIT |
Provide a trustworthy dataset orientation, a short ranked set of findings, important limitations, and the next analytical question or baseline suggested by the evidence.
scripts/profile_table.py is available for a deterministic
first pass.Do not generate an indiscriminate chart catalog, silently drop missing rows, infer causality, or turn a bounded question into open-ended EDA.
For visualization and chapter patterns, read references/deep-guide.md.