AI-agent readiness auditing for project documentation and workflows. Evaluates whether future Claude Code sessions can understand docs, execute workflows literally, and resume work effectively. Use when onboarding AI agents to a project or ensuring context continuity. Includes three specialized agents: context-auditor (AI-readability), workflow-validator (process executability), handoff-checker (session continuity). Use PROACTIVELY before handing off projects to other AI sessions or team members.
View on GitHubskills/project-health/SKILL.md
February 4, 2026
Select agents to install to:
npx add-skill https://github.com/jezweb/claude-skills/blob/main/skills/project-health/SKILL.md -a claude-code --skill project-healthInstallation paths:
.claude/skills/project-health/# Project Health: AI-Agent Readiness Auditing **Status**: Active **Updated**: 2026-01-30 **Focus**: Ensuring documentation and workflows are executable by AI agents ## Overview This skill evaluates project health from an **AI-agent perspective** - not just whether docs are well-written for humans, but whether future Claude Code sessions can: 1. **Understand** the documentation without ambiguity 2. **Execute** workflows by following instructions literally 3. **Resume** work effectively with proper context handoff ## When to Use - Before handing off a project to another AI session - When onboarding AI agents to contribute to a codebase - After major refactors to ensure docs are still AI-executable - When workflows fail because agents "didn't understand" - Periodic health checks for AI-maintained projects ## Agent Selection Guide | Situation | Use Agent | Why | |-----------|-----------|-----| | "Will another Claude session understand this?" | **context-auditor** | Checks for ambiguous references, implicit knowledge, incomplete examples | | "Will this workflow actually execute?" | **workflow-validator** | Verifies steps are discrete, ordered, and include verification | | "Can a new session pick up where I left off?" | **handoff-checker** | Validates SESSION.md, phase tracking, context preservation | | Full project health audit | All three | Comprehensive AI-readiness assessment | ## Key Principles ### 1. Literal Interpretation AI agents follow instructions literally. Documentation that works for humans (who fill in gaps) may fail for agents. **Human-friendly** (ambiguous): > "Update the config file with your settings" **AI-friendly** (explicit): > "Edit `wrangler.jsonc` and set `account_id` to your Cloudflare account ID (find it at dash.cloudflare.com → Overview → Account ID)" ### 2. Explicit Over Implicit Never assume the agent knows: - Which file you mean - What "obvious" next steps are - Environment state or prerequisites - What success looks like ###