Explain model predictions by attributing feature contributions with SHAP values.
npx skills add https://github.com/Hung-3008/agusta --skill shap-hung-3008
Please help me install this Agent Skill. Skill: shap Source: https://github.com/Hung-3008/agusta/tree/main/.agents/skills/shap Command: npx skills add https://github.com/Hung-3008/agusta --skill shap-hung-3008
SHAP provides principled, local- and global-level explanations for any machine learning model by attributing predictions to input features via Shapley values.
Load your trained model and data, create the appropriate SHAP explainer (TreeExplainer for tree models, DeepExplainer for neural nets, LinearExplainer for linear models, or KernelExplainer for black-box cases), compute SHAP values on a representative background, then visualize global and local explanations.
High-intent search queries and answers about installing and using this skill.
Explain model predictions by attributing each feature's contribution using SHAP values. You compute Shapley values on a representative background dataset to decompose individual predictions and quantify global feature importance across classification and regression tasks.
Yes, SHAP explainers support tree-based models, deep learning, linear, and black-box models. You select the appropriate explainer—TreeExplainer, DeepExplainer, LinearExplainer, or KernelExplainer—to compute feature attributions based on your specific model architecture.
Local explanations decompose individual predictions to reveal each feature's contribution for a single instance, while global feature importance summarizes how features drive predictions across the entire dataset using aggregated SHAP values.
Load your trained model and data, create the appropriate SHAP explainer, compute SHAP values on a representative background, then use visualization tools to present global and local explanations for your model predictions.
Use KernelExplainer for black-box models where you lack internal model architecture access, and TreeExplainer specifically for tree-based models to compute exact SHAP values efficiently.
Yes, you must construct an appropriate background dataset to compute SHAP values. This representative data serves as the reference distribution for attributing feature contributions to your model's predictions.
ManfronEnricoCompute SHAP values and visualizations for tree, deep, and linear models.
galeepCompute SHAP values and generate feature attribution visualizations for any model type.
ovachieverCompute SHAP values and generate visual explanations for model predictions.
tondevrelAnalyze scikit-learn model feature importance with SHAP, LIME, and partial dependence plots.
