Menu
Establish a dumb baseline and an honest validation harness before any real model, so every later number means something.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
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.
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-baseline |
| description | Establish a dumb baseline and an honest validation harness before any real model, so every later number means something. |
| homepage | https://github.com/tkpratardan/lemma |
| license | MIT |
Provide a reproducible validation design, a no-information or rule baseline, the simplest credible model, and the precise score later models must beat.
Do not tune complex models, repeatedly inspect a final test set, preprocess before splitting, or celebrate a score without the dumb baseline.
For feature iteration and metric guidance, read references/deep-guide.md.
