From jeremylongshore-claude-code-plugins-plus-skills
Guides model explainability tool tasks for ML training, including data preparation, hyperparameter tuning, and experiment tracking.
How this skill is triggered — by the user, by Claude, or both
Slash command
/jeremylongshore-claude-code-plugins-plus-skills:model-explainability-toolThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
This skill provides automated assistance for model explainability tool tasks within the ML Training domain.
This skill provides automated assistance for model explainability tool tasks within the ML Training domain.
This skill activates automatically when you:
Example: Basic Usage Request: "Help me with model explainability tool" Result: Provides step-by-step guidance and generates appropriate configurations
| Error | Cause | Solution |
|---|---|---|
| Configuration invalid | Missing required fields | Check documentation for required parameters |
| Tool not found | Dependency not installed | Install required tools per prerequisites |
| Permission denied | Insufficient access | Verify credentials and permissions |
Part of the ML Training skill category. Tags: ml, training, pytorch, tensorflow, sklearn
npx claudepluginhub jeremylongshore/claude-code-plugins-plus-skills --plugin ejentum-reasoningExplains ML model predictions using SHAP, LIME, and feature importance analysis. Helps debug model behavior, identify influential features, and communicate insights to stakeholders. Activates when users ask for model interpretability or prediction explanations. Activates when users ask for model interpretability or prediction explanations.
Explains ML model predictions with SHAP — computes feature importance and generates waterfall, beeswarm, bar, scatter, force, and heatmap plots. Works with XGBoost, LightGBM, PyTorch, TensorFlow, and other models.
Explains ML model predictions using SHAP values. Computes feature importance and generates SHAP plots (waterfall, beeswarm, bar, scatter, force, heatmap) for tree-based, deep learning, linear, and black-box models.