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.
Phelan164SkillPhelan164/codex-howto/skills/review-code/SKILL.md
Review code changes for correctness defects, regressions, security risks, data-integrity problems, concurrency hazards, and missing meaningful tests. Use for pull requests, branches, commits, patches, or working-tree reviews; do not use for implementation unless the user separately requests fixes.
quanruSkillquanru/code-review-skill/SKILL.md
Perform architecture- and maintainability-focused code reviews. Use when the user asks for code review, style review, refactoring feedback, or review of architecture, cohesion, coupling, TypeScript rigor, naming, tests, responsibility boundaries, or unnecessary abstractions.
Reef123SkillReef123/OpenVera/.claude/skills/code-review/SKILL.md
Adversarial code review by a clean-context Claude subagent. Read-only. Returns Critical/High/Medium/Low findings against correctness, security, design, reliability, tests, quality. Standalone (no /build pipeline coupling).
YassimbaSkillYassimba/loom/skills/code-review/SKILL.md
Review changes since a fixed point along separate Standards and Spec axes, plus Code Contracts when the repository defines @cc or CONTRACTS obligations. Runs enabled reviews in parallel sub-agents and reports them side by side. Use for branches, PRs, work-in-progress changes, or "review since X".
bis-codeSkillbis-code/claude-toolkit/.claude/skills/code-review/SKILL.md
Review code changes for correctness, security, test coverage, and style.
hellyguoSkillhellyguo/self-ai-spec/skills/code-review/SKILL.md
代码审查框架：通用审查流程 + 语言特定规则引用，支持多语言代码审查
lilangMaxSkilllilangMax/ClaudeCodeGameStudios/.claude/skills/code-review/SKILL.md
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.
mgiovaniSkillmgiovani/cc-arsenal/skills/review-code/SKILL.md
Runs a comprehensive multi-agent code review of a PR, commit, or the
PanPanFRSkillPanPanFR/oh-my-openkilo/skills/code-review/SKILL.md
Use when reviewing a branch, PR, diff, or work-in-progress changes - two-axis review of coding standards compliance and spec fidelity with concise actionable findings
PedroMosqueraSkillPedroMosquera/squadai/.claude/skills/code-review/SKILL.md
Structured code review
Prat011SkillPrat011/nano-claude-code/skills/code-review/SKILL.md
code-review Use this skill when the task is a code review rather than feature implementation. Focus on: - correctness bugs - regressions - missing tests - risky assumptions Return findings first. Keep
QBall-IncSkillQBall-Inc/the-bulwark/skills/code-review/SKILL.md
Comprehensive code review with distinct aspect based sections. Use when reviewing code, checking for security issues, finding type safety problems, auditing code quality, or when user asks to review code, PRs or changes. Three-phase workflow runs static tools, LLM judgment, and writes diagnostic log.
thechandanbhagatSkillthechandanbhagat/claude-skills/skills/code-review/SKILL.md
Perform automated code reviews with best practices, security checks, and refactoring suggestions. Use when reviewing code, checking for vulnerabilities, or analyzing code quality.
All-The-VibesSkillAll-The-Vibes/ecorp/.github/skills/code-review/SKILL.md
Review any ECorp pull request against its PR-template merge-readiness rubric, ATV security, Ponytail complexity audit, and Santa verification. Use for automatic Copilot PR reviews, explicit open-PR sweeps, and explicitly authorized TDD remediation with issue-scoped subagents.
Kripu77SkillKripu77/software-factory/skills/code-review/SKILL.md
Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a code review, deep code quality audit, or especially harsh maintainability review. Only use when explicitly asked to review; never during implementation.
officialunofficialSkillofficialunofficial/skills/skills/engineering/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".
PusteltoSkillPustelto/code-review-skills/code-review/SKILL.md
Use for a thorough, impact-aware code review of the current branch (or an MR). Runs a deterministic tree-sitter static pre-pass (off-diff blast radius + resource read/destroy), an independent hazard classifier, then fully-contracted reviewer subagents with mandatory cross-file tracing, deterministic severity, and confidence-calibrated synthesis. Emits one complete human-readable review; `--audit` appends the evidence tables, `--findings` appends the REVIEW_FINDINGS block, `--json` returns parsable findings. Triggers on "review my code", "code review", "review this branch", "/code-review".
zanlib0Skillzanlib0/skills/code-review/SKILL.md
Review the code the user might not be immediately familiar with.
bestdeejay-designSkillbestdeejay-design/agent-skills/skills/code-review/SKILL.md
Структурированный code review: читает git diff или путь к репозиторию/файлу, применяет чек-лист категорий (correctness, security, performance, style, tests, edge cases, a11y) и выдаёт замечания вида [severity] файл:строка с предлагаемым исправлением. Скилл только анализирует и комментирует, правки не вносит. Триггеры: 'code review', 'ревью кода', 'review PR', 'проверь код', 'pull request review', 'code quality', 'замечания по коду', 'найти баги', 'review commit', 'проверь изменения', 'review diff', 'ревью пул-реквеста'.
davidmeirlevySkilldavidmeirlevy/obvious-skills/skills/code-review/SKILL.md
Code review my changes
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.
