Perform thorough code reviews with security, performance, and maintainability analysis. Use when user asks to review code, check for bugs, or audit a codebase.
Run code review in an independent agent. Automatically used after code implementation or fixes. Triggered by "review this", "code review", "code check", "look at this PR", "check the diff", "is this code OK?".
Performs an architectural and quality code review on a specified file or set of files. Checks for coding standard compliance, architectural pattern adherence, SOLID principles, testability, and performance concerns.
Use when receiving code review feedback (especially if unclear or technically questionable), when completing tasks or major features requiring review before proceeding, or before making any completion/success claims. Covers three practices - receiving feedback with technical rigor over performative agreement, requesting reviews via code-reviewer subagent, and verification gates requiring evidence before any status claims. Essential for subagent-driven development, pull requests, and preventing false completion claims.
Perform thorough code reviews with security, performance, and maintainability analysis. Use when user asks to review code, check for bugs, or audit a codebase.
[UDS] Reference for systematic code review: eight review categories and BLOCKING/IMPORTANT/SUGGESTION comment prefixes. Use when: reviewing a pull request or diff, deciding how to phrase and prioritise review comments, agreeing review scope with a team. Not for: executing a gated review workflow — that moved to the adoption layer (XSPEC-095); pre-commit gate verification — use /checkin. Keywords: code review, pull request review, review checklist, BLOCKING, comment prefix, 程式碼審查, 審查類別, 評論前綴.
The depth half of a review - the dimensions a diff is read against (correctness, boundaries, concurrency, failure paths, secrets, data access, structure, test quality) and the rule that a finding is refuted before it is reported. The verdict stays with the reviewer agent. Use when reviewing a diff or a pull request, or when asked about N+1 queries or wasted round trips.
Use when reviewing a pull request in the deepseek-harness repo — orients the reviewer to this codebase's standards (AGENTS.md conventions, defensive patterns, ADRs, quality gates) and the review-specific checks that code alone can't show
name: code-review
description:
Reviewcode changes using Hyperlane monorepo coding standards. Use when
reviewing PRs, checking your own changes, or doing self-review before committing.
---
# CodeReview Skill
Reviews local changes, an open PR/MR, or a branch diff for bugs, security issues, and violations of the project's own coding guidelines, through review lenses applied inline on a small diff or in parallel agents on a larger one. Excludes style and linter-catchable issues. Read-only: applies fixes or posts PR/MR comments only on explicit approval. For an iterative auto-fix loop, use /optimus:deep review.
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md or AGENTS.md?
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
What is a skill?
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Can I search my own team's files too?
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.