Agent skill
review-ai
Review changes made by AI editors (Codex, Claude, etc.). Run git diff, lint, security scan, tests, and provide a code review.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/review-ai
SKILL.md
Review changes made by an AI editor. Follow these steps:
- Run
git diffandgit status -sto see all uncommitted changes (staged, unstaged, and untracked files) - For any new untracked files, read them fully
- Analyze every change for:
- Bugs or logic errors
- Security issues (SQL injection, XSS, etc.)
- Style consistency with the rest of the codebase
- Missing edge cases
- Unnecessary or over-engineered code
- Run CI checks on changed files:
bin/brakeman --no-pager(scan_ruby: security vulnerabilities)bin/importmap audit(scan_js: JS dependency vulnerabilities)bin/rubocop(lint: code style)PARALLEL_WORKERS=0 bin/rails db:test:prepare test test:system(test: unit/integration/system tests)- For reviews, always run the exact command above to include system tests.
- Provide a structured review:
- Summary of what changed
- CI results (pass/fail for each check)
- File-by-file comments (only where there are issues)
- Overall verdict: approve / needs fixes
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?