WindcleaverDev
UserStatistically rigorous regression skills for Claude — Python computes, the model narrates.
Categories
Indexed Skills (3)
linear-regression
Fit a linear regression (OLS) on tabular data and produce a rigorous report — coefficient table with confidence intervals, standardized betas, plain-English interpretation of each coefficient (transform-aware), fit statistics, and a standalone HTML report. Use this skill whenever the user wants to model a continuous outcome from one or more predictors, asks to "fit a regression" or "run OLS" or "model Y from X", or hands over tabular data with a continuous target. Outputs are both a structured JSON (LinearRegressionReport) and a self-contained HTML deliverable. Pair this skill with the diagnostics skill to check assumptions and identify influential observations.
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.
diagnostics
Run the full diagnostic battery on a fitted regression model — assumption tests (linearity, homoscedasticity, normality of residuals, independence, multicollinearity), influence analysis (leverage, Cook's distance, DFFITS), and bias/variance assessment via cross-validation. Produces a structured DiagnosticsReport with status flags and ranked remediation recommendations, plus a standalone HTML report. Use this skill whenever a regression has been fitted and the user wants to know if they can trust it, asks "are the assumptions met?", "is this model overfit?", "is this overfitting or underfitting?", or wants to identify influential outliers. Pair with the linear-regression or regularized-regression skills.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.