# Skills health check (/meta--health-check)

/meta--health-check is a Claude Code skill in the AI & Agents section. Checks every installed skill for structure, declared permissions and safety, then produces a health report of what passes and what fails.

- Web version: https://skills.sgomez.dev/en/s/meta--health-check
- Section: [AI & Agents](https://skills.sgomez.dev/en/ai.md)
- Author: Santiago Gómez de la Torre
- License: MIT
- Source: https://github.com/sgomez-dev/claude-skills/blob/main/skills/meta/health-check.md
- Updated 26 Mar 2026

## How to ask for it

- `/meta--health-check check all my installed skills`
- `/meta--health-check look for risky permissions in my skills`
- `/meta--health-check validate the structure of my custom commands`

## Install

macOS · Linux:

```
curl -fsSL https://raw.githubusercontent.com/sgomez-dev/claude-skills/main/install.sh | bash
```

Windows:

```
irm https://raw.githubusercontent.com/sgomez-dev/claude-skills/main/install.ps1 | iex
```

Claude Code plugin:

```
/plugin marketplace add sgomez-dev/claude-skills
/plugin install meta-skills@claude-skills-collection
```

## Permissions

- Reads: `skills/**`, `~/.claude/commands/**`, `.claude/commands/**`
- Writes: —
- Runs: `bash scripts/test-runner.sh`, `bash scripts/lint-permissions.sh`
- Network: No
- Destructive: No

## Author's description

Run a health check on all installed skills - validate structure, permissions, and safety

- [How we review this](https://skills.sgomez.dev/en/methodology.md)