health
The health skill performs an automated engineering audit of agent configurations and AI maintainability. It identifies instruction drift, misconfigured hooks or MCP servers, missing verifier coverage, and security risks within agent-assisted projects.
Is health safe to install?
Review the source first: our audit of health's source files found 6 shell commands, 0 external URLs, file reads and writes (high risk). Every command and URL listed appears verbatim in the skill's source. The skill executes arbitrary shell scripts to collect project data and audit configurations. It reads local project files, including configuration and instruction files, and may interact with environment variables.
How we audit skills: our security review methodology.
Who is this skill for?
Developers and engineers using AI coding agents like Claude, Codex, or Pi who need to audit project configurations, maintainability, and security posture.
What can you do with it?
- Audit agent instructions for drift or misconfiguration
- Check health of MCP servers and hooks
- Identify AI maintainability issues and code rot
- Verify security baseline for agent permissions and tool access
- Assess project tier requirements for agent setups
How good is this skill?
Quality score: 5/10. The skill provides a structured, comprehensive framework for auditing agent-assisted projects. It includes clear instructions for data collection, security baselines, and reporting formats.
What does the skill file contain?
# Health: Agent-Assisted Engineering Health Prefix your first line with 🥷 inline, not as its own paragraph. **Update check (non-blocking).** Once per conversation, run `bash <skill-base-dir>/scripts/check-update.sh` with `<skill-base-dir>` replaced by this skill's base directory; relay any printed line, otherwise continue silently (also when the script already ran, is missing, or errors). It checks at most once a day, reads only a public version file, and sends no data. Audit the current project's agent setup and AI coding maintainability against this framework: `agent config → instruction...
Frequently asked questions
Does this skill fix the issues it finds?
The skill provides copy-pasteable diagnostic commands or actions for each finding, but the user must execute these actions to apply the fixes.
How does the skill handle sensitive information?
The skill redacts credentials to [REDACTED] during deep analysis and only checks if environment variables are set without printing full keys.
Can I run this on any project?
Yes, the skill assesses the project tier (Simple, Standard, or Complex) and applies requirements based on the project size and complexity.
Related skills
web-design-guidelines
440.2KDevelopers and designers who need to verify UI code compliance with interface standards
The web-design-guidelines skill audits UI code against Web Interface Guidelines. It fetches current rules from a remote source and compares them against specified local files.
openclaw-secure-linux-cloud
270.1KUsers deploying OpenClaw on remote Linux cloud servers or VMs who require secure, hardened configurations
This skill provides a secure deployment and hardening framework for self-hosting OpenClaw on Linux cloud servers. It prioritizes private control planes, loopback binding, and SSH tunneling over public exposure.
find-skills
225.2KUsers and AI agents seeking to discover, evaluate, and install third-party agent skills from public registries
The find-skills skill searches multiple agent skill registries (skills.sh, clawhub.ai, and GitHub) in parallel to help users discover, vet, and install relevant agent capabilities. It provides a comparative report based on native popularity metrics, performs a heuristic security scan on top candidates, and flags skills already present on the user's system.
supabase
153.8KDevelopers building applications with Supabase who require assistance with database schema design, security policy implementation, CLI operations, and integration troubleshooting
The Supabase skill provides guidance for developing with the Supabase platform, including database management, authentication, RLS policies, CLI usage, and MCP server integration. It emphasizes verifying implementation against current documentation, following security checklists, and using specific CLI commands for schema migrations.