explainable-ai
Make AI model decisions interpretable and transparent. Use for: implementing SHAP for feature importance analysis, using LIME for local explanations, creating attention visualizations for deep learning, generating counterfactual explanations, building inherently interpretable models, visualizing decision boundaries and activation maps, explaining predictions to stakeholders, debugging model behavior, ensuring regulatory compliance with explainability requirements, and building trust in AI systems.
npx skills add majiayu000/claude-skill-registry --skill explainable-ai --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Explainable AI (XAI) Make AI model decisions understandable, interpretable, and transparent to humans. ## Overview Explainable AI (XAI) encompasses techniques and processes that provide human-understandable explanations for AI model predictions and behaviors. As AI systems increasingly influence critical decisions, explainability is essential for building trust, ensuring fairness, meeting regulatory requirements, and debugging models. XAI bridges the gap between complex "black-box" models and human understanding. ## Why Explainability Matters **Trust and Adoption**: Users trust systems they understand **Regulatory Compliance**: GDPR, EU AI Act require explainability **Debugging**: Identify model errors and biases **Fairness**: Detect discriminatory patterns **Safety**: Understand failure modes **Scientific Discovery**: Extract insights from learned patterns ## Types of Explainability ### Global Explainability Understanding overall model behavior across all predictions. ### Local Explainability Understanding individual predictions for specific instances. ### Model-Agnostic vs Model-Specific **Model-Agnostic**: Works with any model (SHAP, LIME) **Model-Specific**: Tailored to speci
- Overview
- Why Explainability Matters
- Types of Explainability
- Global Explainability
- Local Explainability
- Model-Agnostic vs Model-Specific
- SHAP (SHapley Additive exPlanations)
- Basic SHAP Usage
- SHAP for Deep Learning
- SHAP Waterfall Plot
- SHAP Interaction Values
- LIME (Local Interpretable Model-agnostic Explanations)
- LIME for Tabular Data
- LIME for Images
What does the explainable-ai skill do?
Make AI model decisions interpretable and transparent. Use for: implementing SHAP for feature importance analysis, using LIME for local explanations, creating attention visualizations for deep learning, generating counterfactual explanations, building inherently interpretable models, visualizing decision boundaries and activation maps, explaining predictions to stakeholders, debugging model behavior, ensuring regulatory compliance with explainability requirements, and building trust in AI systems.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill explainable-ai --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.