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.
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
tigu77Skilltigu77/tiguclaw/skills/code-review/SKILL.md
코드 변경(작업 트리 diff·브랜치·PR·경로·커밋 범위)을 **읽기 전용**으로 검토해, 실제로 확인한 발견만 보고한다. '리뷰해줘·검토해줘·이 diff 봐줘·PR 봐줘·머지해도 되나·이 수정 괜찮아?·내가 고친 거 다시 봐줘' 류 요청, 그리고 스스로 수정을 마친 뒤 되짚을 때. 버그 진단('이거 왜 안 돼')에도 같은 검사 축을 쓴다. 리뷰는 독립 매니저가 먼저 혼자 읽고, 파일이 많으면 **겹치지 않는 파일 묶음**으로만 나눈다(관점·발견 수로 나누지 않는다). 발견은 정적 코드·계약 또는 필요한 실행 근거로 확인하고, 고치지 않는다 — 수정은 사용자가 따로 시킬 때 별도 단계다.
Often used withclose-specadd-new-modelcompare-screenshots
wpankSkillwpank/ai/skills/testing/code-review/SKILL.md
Systematic code review patterns covering security, performance, maintainability, correctness, and testing — with severity levels, structured feedback guidance, review process, and anti-patterns to avoid. Use when reviewing PRs, establishing review standards, or improving review quality.
Often used withclose-specadd-new-modelcompare-screenshots
z-ZihanSkillz-Zihan/Evir/skills/builtin/code-review/SKILL.md
Use on Desktop when reviewing a diff, commit, branch, or local code for correctness, regressions, security, performance, and maintainability.
Often used withclose-specadd-new-modelcompare-screenshots
conorbronsdonSkillconorbronsdon/agent-skills/code-review/SKILL.md
Multi-agent deep review for code PRs in any repo. Use when asked to "deep review this PR," "multi-agent review," "review #N with subagents," "thorough review of this branch," or "is this PR ready to merge." Orchestrates Copilot + parallel subagents (adversarial, operational, reference-comparison) with scope-based escalation, stale-finding triage, and a hard iteration cap.
Often used withclose-specadd-new-modelcompare-screenshots
flightctlSkillflightctl/ai-workflows/code-review/SKILL.md
AI-driven code review workflow that reviews uncommitted changes using a discoverable reviewer profile, presents findings for human decision, and iterates until approved. Supports --unattended for automated iteration. Use when reviewing code before commit or PR. Activated by commands: /start, /continue, /clean.
Often used withclose-specadd-new-modelcompare-screenshots
kambleakash0Skillkambleakash0/agent-skills/skills/code-review/SKILL.md
Performs a thorough code review of the current changes or a specified file / pull request. Covers correctness, security, performance, readability, and adherence to project conventions. Outputs prioritised, actionable feedback. TRIGGER when the user writes /code-review or asks for a code review, PR review, or feedback on their code.
Often used withclose-specadd-new-modelcompare-screenshots
onlyoneamanSkillonlyoneaman/agent-skills/skills/code-review/SKILL.md
Reviews code for best practices, bugs, security issues, and provides improvement suggestions
Often used withclose-specadd-new-modelcompare-screenshots
PedroMosqueraSkillPedroMosquera/squadai/.agents/skills/code-review/SKILL.md
Structured code review with severity-based findings
Often used withclose-specadd-new-modelcompare-screenshots
pekralSkillpekral/cursor-rules/skills/code-review/SKILL.md
Use when senior PHP code review focused on architecture, business
Often used withclose-specadd-new-modelcompare-screenshots
botlearn-aiSkillbotlearn-ai/botlearn-skills/skills/code-review/SKILL.md
name: code-review role: Code Review Specialist version: 1.0.0 triggers: - "review code" - "code review" - "check this code" - "find bugs" - "security audit" - "review my code" - "check for vulnerabilities" - "code quality" --- # Role
Often used withclose-specadd-new-modelcompare-screenshots
CodePhobiiaSkillCodePhobiia/claude-roblox-game-studio/.claude/skills/code-review/SKILL.md
Review Luau code for style compliance, type safety, server authority, error handling, and performance. Use for reviewing a file, a PR-sized change, or a whole module.
Often used withclose-specadd-new-modelcompare-screenshots
DregxmoonDeletes or force-pushesSkillDregxmoon/Kaoru-Agent/skills/code-review/SKILL.md
Revisión de código: identificar bugs, problemas de seguridad, performance, mantenibilidad y consistencia con las convenciones del proyecto
Often used withclose-specadd-new-modelcompare-screenshots
E4crypt3dSkillE4crypt3d/oh-my-qwen/skills/code-review/SKILL.md
Systematic code review with structured output and actionable findings. Use when reviewing code, auditing quality, checking for bugs, security vulnerabilities, or performance issues.
Often used withclose-specadd-new-modelcompare-screenshots
emaraschioSkillemaraschio/cursor-commands/.cursor/skill-contracts/code-review/SKILL.md
Thorough PR code review before approval
Often used withclose-specadd-new-modelcompare-screenshots
fusebase-devSkillfusebase-dev/fusebase-flow/.agents/skills/code-review/SKILL.md
Use before commit, deploy, or PR merge, or when operator asks "review this diff" / "is this safe?"; reviews diff vs spec, decisions, maintainability, scope, tests, rollback. Do NOT write or fix code — review only.
Often used withclose-specadd-new-modelcompare-screenshots
jnotsknabSkilljnotsknab/mux-swarm/Skills/bundled/code-review/SKILL.md
Structured diff and PR code review with a prioritized checklist. Use when reviewing staged changes, pull requests, or any code diff before merge.
Often used withclose-specadd-new-modelcompare-screenshots
kings0527Skillkings0527/pi-harness/skills/mattpocock/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".
Often used withclose-specadd-new-modelcompare-screenshots
Lee-DongwookSkillLee-Dongwook/E2E-Self-Heal/.claude/skills/code-review/SKILL.md
name: code-review description: Default target is the current branch diff vs main. -- # code-review - E2E healer team review The team's own review procedure. It layers **things
Often used withclose-specadd-new-modelcompare-screenshots
lhpaulSkilllhpaul/ai-dev-framework-template/.agents/skills/code-review/SKILL.md
Command-style Codex alias for reviewing implementation changes. Use when the user asks for /code-review or wants the repository code review gate.
Often used withclose-specadd-new-modelcompare-screenshots
LuckyLittleMonsterSkillLuckyLittleMonster/cc-skills/code-review/SKILL.md
Code review a pull request or recent changes using git diff and agent teams. Reviews code usage, efficiency, bugs, and comments. Backs up unused files to bk/.
Often used withclose-specadd-new-modelcompare-screenshots
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.
