Shap

If you need to explain why your ML model made a prediction, this gets you SHAP values and visualizations fast. Works with XGBoost, LightGBM, neural nets, basically anything. The skill walks you through picking the right explainer (TreeExplainer for tree models, DeepExplainer for neural nets, KernelExplainer for black boxes), computing feature attributions, and generating the standard plots: waterfall for individual predictions, beeswarm for global importance, scatter for relationships. The workflow sections are solid, especially the debugging and fairness analysis bits that show you how to catch data leakage or check for bias across demographic groups. Good reference if you're tired of Googling which SHAP plot does what.

skills.sh installs: 2.1K
GitHub stars: 56.6K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add k-dense-ai/scientific-agent-skills --skill shap --agent claude-code

Installs into .claude/skills of the current project.

Files

SHAP

Use SHAP to describe how a fitted predictive model maps inputs to outputs. Work from the modern shap.Explanation API, make the explained output and background distribution explicit, and validate every explanation before interpreting it.

This skill is aligned with SHAP 0.52.0 (released 2026-05-28). That release requires Python 3.12 or newer.

The maintained examples were checked on Python 3.12.10 with SHAP 0.52.0, NumPy 2.5.3, pandas 3.0.6, scikit-learn 1.9.1, and matplotlib 3.11.2. Native tests cover small tree, exact, permutation, partition, linear, additive, kernel, text, and constant-image games; additional numeric XGBoost 3.4.1 smoke checks cover raw, probability, loss, and interaction outputs. Reference snippets that require a project model, framework, or data are adaptation templates; optional pretrained/deep, GPU, and distributed integrations remain illustrative and require their own runtime validation.