Review a named diff or PR for bugs, regressions, tests, and standards. Use when asked to review code or when a shipping skill needs a review receipt. Use when asked to apply this review's findings locally. Use ce-resolve-pr-feedback for feedback already left on a PR.
82%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Critical
Do not install without reviewing
Detected a prompt injection in the skill instructions. The skill contains hidden or deceptive instructions that fall outside its stated purpose and attempt to override the agent’s safety guidelines or intended behavior.
The skill openly discloses that reviewed code is sent to external model providers, but it also asks the agent to escalate the detached peer's sandbox permissions and to avoid inspecting the bundled worker script, which weakens protections beyond what the review task needs.
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 intent-discovery step reads outsider-authorable PR title, body, linked issues, and commit messages via `gh pr view` in PR/URL mode, and that PR metadata is passed to every reviewer in `<pr-context>`, which is GitHub PR reading and so falls under the medium rule.
EveryInc/compound-engineering-plugin
ee46dde
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.