Summary
This is the quality gate for the Claude Code skills repository. It runs D1-D11 structural checks and M1-M6 intent reviews on SKILL.md files, plus a separate review mode for .claude/commands. The structural review catches worker independence violations, broken shared paths, stale CLAUDE.md duplicates, and wrong MCP namespaces. Intent review applies only to primary changed skills using git diff context. It also includes a repo-specific suite (R1-R27) with quick, skip, and full runtime modes for release validation. Auto-fixes deterministic issues like path errors and copied boilerplate, but won't guess on ambiguous behavior. Designed to run in Plan Mode so you can review the findings before it applies edits.
Install to Claude Code
npx -y skills add levnikolaevich/claude-code-skills --skill ln-162-skill-reviewer --agent claude-codeInstalls into .claude/skills of the current project.
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
Files
SKILL.md
Select a file.
Featured
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →First SeenJun 3, 2026
