statsmodels-consistency

statsmodels-consistency

An agent skill that makes generated statsmodels code consistent: one canonical, modern idiom set instead of a mix of legacy and current APIs.

What it does

statsmodels is stable, but generated code mixes the formula and array APIs, forgets that the array API adds no intercept (add_constant), and imports from removed module paths. This skill pins the canonical model→fit→results workflow, the modern import paths, and the prediction and robust-covariance idioms that keep estimates honest.

Install

skills.sh

npx skills add guidogl/statsmodels-consistency

Claude Code plugin marketplace

/plugin marketplace add guidogl/statsmodels-consistency

Contents

• SKILL.md — the skill instructions: canonical idioms, pitfalls, version notes, workflow.
• references/statsmodels-patterns.md — deep reference: legacy→modern migration map and expanded per-topic patterns, gotchas, and code examples.

License

Apache-2.0 — see LICENSE.txt.