Review code for correctness, design, maintainability, complexity, tests, security, and code health. Use when reviewing a PR, diff, CL, or code change. Prioritize issues that materially affect users or long-term code health over personal preferences and minor style issues
Use when asked to review code, analyze a PR, audit a function or module for quality, security, performance, or maintainability. Provides structured feedback with priority levels.
Use when reviewing code changes in Theseus, especially to find defects, behavioral regressions, missing tests, weak type modeling, stale compatibility leftovers, and agent-generated implementation artifacts.
Reviews code for quality and project conventions using specialized subagents. Triggers:"Review code", "Code review", "Review this", "Check my code". Use when the user asks for a code review, or automatically after TDD cycles in new feature development.
Review code for correctness, naming conventions, style, error handling, security, and scaling concerns. Use when reviewing code, checking a diff, auditing a function, or asking about code quality. Covers Python, PySpark, SQL, KQL, DAX, and data-engineering patterns.
Thorough code review for quality, correctness, performance, and maintainability. Auto-invoke when: "review this code", "check my code", "PR review", "code quality", "any issues with this", "look at this implementation", "is this good", "feedback on code". Checks logic errors, edge cases, performance, readability, test coverage, naming.
Use immediately after writing code, before committing. Check quality, security, performance, and maintainability. Catch bugs and anti-patterns. | 写完代码后立即使用,检查质量/安全/性能/可维护性。
Language-agnostic framework for conducting thorough, respectful, and constructive code reviews on pull requests, merge requests, git diffs, or code snippets. Triggers whenever an agent is asked to "review this PR", "review this diff", "give feedback on this code", "is this ready to merge?", "audit this pull request", or "critique this implementation". Enforces structured review ordering (intent first, architecture second, lines last), objective 3-tier severity triage (Blocker vs Should-Fix vs Nit), actionable feedback phrasing, and clear approval decisions.
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to \"review since X\".
Review a proposed or completed software change against its intent, constraints, supported behavior, evidence, and future change cost without modifying it. Use for working-tree, commit, branch, pull-request, generated-code, migration, or configuration review before merge or release. Route whole-architecture scenarios to architecture-risk-evaluation and portfolio diagnosis to architecture-assessment.
Full review lifecycle — request reviews, handle feedback with technical rigor, and complete branch integration. Use when completing tasks, receiving feedback, or finishing feature branches.
When performing code review on a PR, diff, snippet, or "look at this change" request, first consult the corpus for related ADRs, coding standards, prior patterns, and similar files. Grounds review comments in the team's actual decisions instead of generic best practices. Trigger on any review-style request — "review", "look at", "any issues with", "does this make sense".
Perform comprehensive code reviews using OpenAI Codex CLI. This skill should be used when users request code reviews, want to analyze diffs/PRs, need security audits, performance analysis, or want automated code quality feedback. Supports reviewing staged changes, specific files, entire directories, or git diffs.
Review Business Central AL code using BCQuality's curated rules. Use for an AL app folder, pull request, working-tree diff, branch, or individual AL file when BCQuality is installed as a standalone plugin.
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.