# Explainability

> See the main Model Explainability skill for comprehensive XAI coverage.

- Skill: `majiayu000/explainability` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add majiayu000/explainability`
- Raw SKILL.md: https://api.skillmd.com/api/skills/majiayu000/explainability/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: majiayu000 (https://skillmd.com/u/majiayu000)
- Updated: 2026-09-09
- Page: https://skillmd.com/skills/majiayu000/explainability

---


# 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`