Review code changes for concrete behavior, contract, security, test, maintainability, and documentation defects. Use when the user exactly asks you for a "code review" or to "review" code.
89%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The required workflow runs `gh pr view` and `gh pr diff` on a pull request and reads its title and body, which outsiders can author on a monitored GitHub PR, so this is medium under the "ANY GitHub issue/PR reading" rule.
shillem/cc-marketplace
258691a
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.