Profile My skills Saved My plugins Edit profile Submit a skill

AI agent skills for code review

A code review skill gives your agent a fixed checklist instead of whatever it happens to notice: correctness first, then security, then style, with a severity it has to justify. The good ones tell the agent what NOT to comment on, which is what separates a useful review from forty nitpicks about naming. Look for one that reads the diff in the context of the surrounding file rather than in isolation — a review that cannot see the caller cannot tell you the change breaks it.

People land here searching for “claude code skill for code review”, “agent skill to review a pull request”, “ai code review skill”.

2,000 code review skills Refine in search →

How to install a code review skill

  1. Compare the skills. Read the code review skills below — each page shows the full SKILL.md, its safety verdict, and the capabilities it declares.
  2. Install it. Run npx skillmds@latest add <owner>/<name>. The CLI writes the skill into every agent directory it detects, or use --agent to pin one.
  3. Use it. Restart your agent. It loads the skill on demand the next time you ask for something that matches — you do not have to name the skill.

What makes a good code review skill?

A code review skill gives your agent a fixed checklist instead of whatever it happens to notice: correctness first, then security, then style, with a severity it has to justify. The good ones tell the agent what NOT to comment on, which is what separates a useful review from forty nitpicks about naming. Look for one that reads the diff in the context of the surrounding file rather than in isolation — a review that cannot see the caller cannot tell you the change breaks it.

Every skill listed here is a plain SKILL.md file in the format Anthropic documents for Agent Skills, read unchanged by Cursor, OpenAI Codex and 60+ agents. Each passes a safety review before it is publicly listed; the verdict and declared capabilities are on every skill's page.

Frequently asked questions

What is an agent skill for code review?

A code review skill gives your agent a fixed checklist instead of whatever it happens to notice: correctness first, then security, then style, with a severity it has to justify. The good ones tell the agent what NOT to comment on, which is what separates a useful review from forty nitpicks about naming. Look for one that reads the diff in the context of the surrounding file rather than in isolation — a review that cannot see the caller cannot tell you the change breaks it.

Can a code review skill run on a real pull request?

Yes, if your agent can reach the repository. In Claude Code the usual shape is `gh pr diff` piped to the agent with the review skill loaded; the skill supplies the checklist and the output format, the agent supplies the reading. Skills that post the review back as comments declare that network capability on their page.

Which agents can use these code review skills?

Any agent that reads SKILL.md files: Claude Code, Claude.ai, Cursor, OpenAI Codex, Windsurf, OpenCode and 60+ others. The format is not vendor-specific, so the same file works everywhere — each agent just keeps its skills in a different directory, listed at /agents.

Are these code review skills free?

Yes. Searching, reading and installing skills on SkillMD is free and needs no account. Individual skills carry their own licence, shown on each skill's page.