CommunityProductivity & Collaborationgithub.com

tw93/health

Runs a budget-aware agent-assisted engineering health audit for instruction/config drift, hooks/MCP, verifier surfaces, and AI maintainability. Use when users ask 检查claude/检查codex/检查pi/配置检查/健康度 or report agents ignoring instructions, missing validation, or code becoming hard to maintain. Not for debugging code or reviewing PRs.

What is health?

This skill performs a comprehensive, budget-conscious engineering health audit for AI agent projects. It scans for instruction and configuration drift (e.g., outdated or conflicting rules), checks the health of hooks and MCP integrations, verifies surface areas where validation is applied, and assesses overall AI maintainability. The skill is triggered by specific Chinese and English queries like '检查claude' (check Claude), '检查codex' (check Codex), '检查pi' (check Pi), '配置检查' (config check), '健康度' (health status), or when users report issues such as agents ignoring instructions, missing validation, or code becoming hard to maintain. It is designed for tools like Claude Code, Cursor, and Codex, and operates within a budget-aware framework to avoid excessive cost. It is not intended for general debugging or PR reviews.

Works with✓Claude Code✓Codex CLI~Cursor
npx skills add https://github.com/tw93/claude-health/tree/main/skills/health

Installed? Explore more Productivity & Collaboration skills: steipete/gemini, steipete/gh-issues, steipete/skill-creator · View all 6 →

Ask in your favorite AI

Open a new chat with this agent skill pre-loaded.

Documentation

What does health do?

Runs a budget-aware agent-assisted engineering health audit for instruction/config drift, hooks/MCP, verifier surfaces, and AI maintainability. Use when users ask 检查claude/检查codex/检查pi/配置检查/健康度 or report agents ignoring instructions, missing validation, or code becoming hard to maintain. Not for debugging code or reviewing PRs.

Related Skills