Explainability
See the main Model Explainability skill for comprehensive XAI coverage.
npx skills add majiayu000/claude-skill-registry --skill model-explainability --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.
# Explainability This skill is covered in detail in the main **Model Explainability** skill. Please refer to: `44-ai-governance/model-explainability/SKILL.md` That skill covers: - What is explainability and why it matters - Types of explanations (global, local, counterfactual) - SHAP (SHapley Additive exPlanations) - LIME (Local Interpretable Model-agnostic Explanations) - LLM explainability (attention weights, chain-of-thought) - Presenting explanations to users - Explainability for different audiences - Trade-offs (accuracy vs explainability) - Tools (SHAP, LIME, InterpretML, Captum, Alibi) - Explainability in production - Regulatory requirements (GDPR, AI Act) - Implementation examples --- ## Related Skills - `44-ai-governance/model-explainability` (Main skill) - `44-ai-governance/auditability` - `44-ai-governance/human-approval-flows`
- Related Skills
What does the Explainability skill do?
See the main Model Explainability skill for comprehensive XAI coverage.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill model-explainability --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.