project-health — an installable skill for AI agents, published by jezweb/claude-skills.
Comprehensive project setup, auditing, and configuration management for Claude Code environments. Detects project type from file indicators (Node.js, Python, Rust, Go, Docker, Cloudflare, etc.) and auto-generates .claude/settings.local.json, CLAUDE.md, and .gitignore with appropriate permission presets Audits existing projects via parallel sub-agents: Permission Auditor scans for leaked secrets, stale MCP servers, permission gaps, and legacy syntax; Context Auditor checks CLAUDE.md quality, detects oversized files, and flags missing documentation Supports six modes: full health check, new project setup, permission tidying, session learnings capture, preset addition, and context restructuring with size targets (root CLAUDE.md 50–150 lines, sub-directory 15–50 lines) Uses sub-agents for heavy analysis to keep main context clean; launches Permission and Context Auditors in parallel for efficiency Project Health One skill for everything about your project's Claude Code configuration. Run it at the start, middle, or end of a project — it figures out what's needed. Goal: Zero permission prompts, well-organised context files, no cruft. When to Use You say... What happens "project health" / "check project" Full audit: permissions + context + docs "setup project" / "kickoff" / "bootstrap" New project setup from scratch "tidy permissions" / "clean settings" Fix permissions file only "capture learnings" / "update CLAUDE.md" Save session discoveries "add python" / "add docker permissions" Add a preset to existing settings "audit context" / "audit memory" Context-focused audit only Architecture: Sub-Agents
don't have the plugin yet? install it then click "run inline in claude" again.