xai-check
CommunityConduct a thorough explainability audit for AI products.
Authorhaabe
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill addresses the need for an in-depth explainability audit for AI products, ensuring they meet defensible XAI standards.
Core Features & Use Cases
- Risk Classification: Evaluates AI components based on risk tiers for regulatory compliance.
- Stakeholder Matrix: Assesses answerability of AI systems for various stakeholders.
- Fidelity Audit: Reviews LLM-generated rationales for faithfulness to system outputs.
- System Card Check: Verifies publication of system cards detailing AI features and limitations.
- Recourse Path Test: Ensures a clear human review process for AI decisions.
Quick Start
Run /mycelium:xai-check to initiate the Explainability Audit for your AI product.
Dependency Matrix
Required Modules
mycelium
Components
scriptsreferences
💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: xai-check Download link: https://github.com/haabe/mycelium/archive/main.zip#xai-check Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 620,000+ vetted skills library on demand.