// Use when reviewing a diff, a PR, or a series of recent commits. Produces a severity-graded report covering correctness, security, performance, concurrency, maintainability, and Definition of Done compliance. Pairs well with pipe input and with Codex cross-checks.
Use to decide when to invoke the Claude Code CLI and how. Claude specializes in deep reasoning — plans, hypercritical reviews, multi-file impact analysis, and pipe-fed log analysis. Includes invocation patterns and cross-check usage with Codex.
Use when an architectural decision has been made or is about to be made. Decides whether the decision belongs in docs/DESIGN.md, what level of detail to record, and what NOT to record. Operates as a judgment skill, not a fixed procedure — for the procedure see the update-design workflow.
Use when evaluating a library, framework, or external service for adoption. Walks evaluation axes (fit, maintenance, license, footprint, integration cost) and produces a recommendation with explicit trade-offs. Output goes under docs/research/.
Use when a bug is reported, a test is failing, or production is misbehaving. Provides observation patterns and diagnostic moves rather than a fixed sequence — every bug has its own shape. Pairs naturally with pipe-fed log analysis.
Use to decide when to invoke the Codex CLI and how. Codex specializes in tight iterate-loops, small refactors, lint cycles, and test additions. Includes invocation patterns and anti-patterns.
Use before writing any non-trivial code. Produces a written plan that names every file to touch, the order of work, the test strategy, the rollback path, and the open questions. Code is not written during this skill.
| name | team-review |
| description | Use when reviewing a diff, a PR, or a series of recent commits. Produces a severity-graded report covering correctness, security, performance, concurrency, maintainability, and Definition of Done compliance. Pairs well with pipe input and with Codex cross-checks. |
A multi-perspective review skill. The goal is not "find one bug" — it's to walk every angle below and stay honest about uncertainty.
AGENTS.md §3).Group findings by severity:
Each finding includes: file path, line range, what's wrong, why it matters, the smallest viable fix.
git diff main...HEAD | claude "Apply the team-review skill."git show <sha> -- 'src/**' | claude "Apply the team-review skill, focus on security."For high-stakes diffs, pipe the same input to Codex with the same prompt and reconcile differences. Where the two disagree is where hidden assumptions usually live — surface those to the human reviewer.