a5c-ai/babysitter / library/specializations/data-science-ml/skills/shap-explainer
shap-explainer
VerifiedSHAP-based model explainability skill for feature attribution, summary plots, and interaction analysis.
README.md
View on GitHub# shap-explainer
SHAP-based model explainability skill for feature attribution, summary plots, and interaction analysis.
## Purpose
This skill provides comprehensive model explainability using SHAP (SHapley Additive exPlanations), enabling teams to understand feature contributions, identify important features, and explain individual predictions.
## Key Features
- **Multiple Explainers**: Tree, Deep, Kernel, Linear, and Gradient explainers
- **Feature Attribution**: Quantify feature contributions to predictions
- **Visualizations**: Summary, bar, waterfall, force, and dependence plots
- **Interactions**: Compute and visualize feature interactions
- **Cohort Analysis**: Compare explanations across data segments
## When to Use
- Understanding which features drive model predictions
- Explaining individual predictions to stakeholders
- Validating model behavior and fairness
- Debugging model issues
- Generating compliance documentation
## Integration
Works seamlessly with:
- `sklearn-model-trainer` for scikit-learn models
- `pytorch-trainer` for neural networks
- `lime-explainer` for complementary explanations
- `fairlearn-bias-detector` for fairness analysis
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |