Pre Analysis

Audit tabular data before fitting any regression — target distribution and skewness, feature types and missingness, multicollinearity (pairwise correlation + VIF), suspected nonlinearity, univariate outliers, and concrete modeling recommendations (which transforms to apply, which features to drop or combine, which estimator family to use). Produces a structured PreAnalysisReport and a standalone HTML report. Use this skill whenever the user is about to fit a model and hasn't done EDA yet, asks "what should I do with this data?", "should I transform anything?", "is this data ready to model?", or hands over a CSV with a target in mind but no clear modeling plan. Run this BEFORE linear-regression or logistic-regression to avoid refit cycles.

WindcleaverDev Updated
regkit

File contents

WindcleaverDev/regkit commit c765bf93cd

Frequently asked questions

npx get-skill add windcleaverdev/pre-analysis