Shap

When you need to explain why your ML model made a specific prediction, this gets you SHAP values and visualizations without digging through documentation. It covers the explainer selection decision tree (TreeExplainer for XGBoost and friends, DeepExplainer for neural nets, KernelExplainer for black boxes), then walks through the standard plots: waterfall for individual predictions, beeswarm for global importance, scatter for feature relationships. The workflow coverage is actually useful, especially the debugging and fairness analysis patterns that go beyond just generating plots. Works with pretty much any model type. The main value is having all the explainer types and plot options laid out clearly so you can pick the right tool without trial and error.

Install to Claude Code

npx -y skills add davila7/claude-code-templates --skill shap --agent claude-code