One search for your own team's files and the public ecosystem. See how real projects write their agent instructions, and bring the good ideas home.
WubabalalaSkillWubabalala/claude-skills/skills/code-review/SKILL.md
Pragmatic code review & pre-push quality gate. Use when the user says "review code", "check code quality", "any issues with this code", "ready to push", "prepare commit", "submit code", "push to remote", or any variation requesting code inspection before merging or pushing.
OpenAISkillopenai/codex/.codex/skills/code-review-context/SKILL.md
Model visible context
AaronAbuUsamaSkillAaronAbuUsama/whatsappd/.agents/skills/code-review/SKILL.md
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/PRD 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".
Aias00SkillAias00/agent-skills/code-review/SKILL.md
统一代码评审 skill，三种模式：PR 评审（pr：deep 深审 + follow-up 评论回复）、全仓库缺陷发现（repo-audit）、Java 安全深度审计（security-audit）。 触发：pr deep=「review this code」「code review」「before merge」「深度 review #PR」「审 PR 有什么问题」；pr follow-up=「待处理」「review 修了吗」「英文回复」「处理这个 PR 的 review」「#PR」；repo-audit=「分析项目问题」「全仓库扫描」「audit the repo」「find issues」「建 issue」「不要重复」；security-audit=「安全审计」「审安全」「check security」「audit for vulnerabilities」「审 Controller」「单接口安全」。 安全类只写本地 Markdown 不写缺陷系统；非安全建 issue 前先列清单确认。Critical/High 与全部安全 finding 必过统一核验门（可移植：独立 general-purpose subagent 隔上下文复核；OMX 运行时优先用 code-reviewer+architect 双 lane）。
ailess-labSkillailess-lab/CCFG/.agents/skills/code-review/SKILL.md
对指定文件或文件集执行架构和质量的代码审查。检查编码标准合规性、架构模式遵守情况、可测试性、性能和安全风险。
alemdarlabsSkillalemdarlabs/sage-unreal-mcp/.agents/skills/code-review/SKILL.md
Reviews code for bugs, inefficiencies, and adherence to best practices, providing actionable improvement suggestions. Invoke when reviewing C++ code, plugin source, or server implementation in Sage.
alex-voloshin-devSkillalex-voloshin-dev/ai-skills/.agents/skills/code-review/SKILL.md
Structured code review with security, performance, and architecture checklists. Use when reviewing pull requests, code changes, or conducting architecture reviews. Provides actionable checklists for consistent review quality.
AndrewBrown-USDASkillAndrewBrown-USDA/aigb-skills-usda/skills/code-review-2axis/SKILL.md
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\".
AntJanusSkillAntJanus/skillbox/skills/code-review/SKILL.md
Use this skill to run a multi-agent code review of local changes whenever the user asks to "review my code", "review these changes", "do a code review", "check my changes before I commit", "review the whole repo", "review this in the background", or "review this PR I checked out locally" — even if they never say "review" and only ask whether the work is ready to ship or safe to commit. Reviews any local diff, including a pull request checked out into a worktree (`--branch origin/dev`). Prioritizes correctness over nitpicks and writes REVIEW.md. Do NOT use this skill to fetch and review an open PR by number from GitHub (use /review), for a security-specific pass (use /security-review), for grading a SKILL.md file (see rate-skill), or for a quality-only cleanup that does not hunt for bugs (see simplify).
apinsteinSkillapinstein/skills/skills/code-review/SKILL.md
Guidelines and checklist for performing rigorous AI-based code reviews emphasizing test coverage, naming, DRY principles, and standards alignment.
bchoxSkillbchox/agent-practices/skills/code-review/SKILL.md
Use when reviewing a PR, diff, or proposed patch for merge risk.
BigPapiCBSkillBigPapiCB/Universal-Claude-Skills/code-review/SKILL.md
Systematic code review checklist covering correctness, security, performance, and maintainability. Use when reviewing pull requests, auditing changes, or checking code quality across any language.
cbooneSkillcboone/agent-harness-plugins/.github/skills/code-review/SKILL.md
Style checklists for reviewing this repository's pull requests. Use for every pull request review to match each changed file to its checklist and report findings with the severities defined here.
Citadel-Cloud-ManagementSkillCitadel-Cloud-Management/citadel-saas-factory/.claude/skills/code-review/SKILL.md
Automated code review for pull requests and code changes. Auto-invoked when PR context is detected.
delorenjSkilldelorenj/ssbnk/.agents/skills/code-review/SKILL.md
Comprehensive code review methodology with severity classification and confidence thresholds
DonggangChenSkillDonggangChen/antigravity-agentic-skills/code_review/SKILL.md
PR review, code smell detection, best practice check. ⚠️ Use while reviewing code. For deliverable check → quality-validator, for doc review → peer-review.
DonTiziSkillDonTizi/CodeGeass/.claude/skills/code-review/SKILL.md
Automated code review with focus on security, performance, and maintainability. Use when reviewing code changes, PRs, or performing scheduled audits.
dqtx760Skilldqtx760/skills-manage/code-review/SKILL.md
Thorough code review covering bugs, security, performance, and maintainability. Use when reviewing code, checking for bugs, auditing quality, or getting feedback on implementations.
ElasticSkillelastic/oblt-aw/.github/skills/code-review/SKILL.md
Use this skill when reviewing changes in oblt-aw, especially workflow routing, GitHub Actions configuration, control-plane logic, docs, and E2E safety checks.
encoreshaoSkillencoreshao/encore-skills/skills/review-code/SKILL.md
Pre-MR self-review — first confirm the problem is actually solved, then check for security, correctness, and simplicity
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 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.
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.
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.
