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.
Arize-aiSkillArize-ai/coding-harness-tracing/.agents/skills/code-review/SKILL.md
Use before opening a pull request to this repo. Reviews the working diff for correctness bugs and repo conventions, runs the test/lint gates, and can post findings directly on the PR. Triggers on "review my changes", "review this PR", "pre-PR review".
dzhngSkilldzhng/duet-agent/.agents/skills/code-review/SKILL.md
Review changed code for naming, stale references, unnecessary complexity, and comment quality. Use after completing implementation work, before committing, or when the user asks to review or audit code.
zhao-wuyanSkillzhao-wuyan/ccw-command-explorer/.claude/skills/review-code/SKILL.md
Multi-dimensional code review with structured reports. Analyzes correctness, readability, performance, security, testing, and architecture. Triggers on "review code", "code review", "审查代码", "代码审查".
addxaiSkilladdxai/enterprise-harness-engineering/skills/code-review/SKILL.md
Use when reviewing code changes — MR/PR review, local commits, or uncommitted changes. Reviews document compliance, content quality (architecture soundness, test completeness, observability coverage), and end-to-end consistency (User Story ↔ design ↔ code ↔ tests ↔ observability). Triggers on "review MR", "review this commit", "review my changes", "code review", "help me review".
FTShare-LabSkillFTShare-Lab/agent-claim-network/.agents/skills/code-review/SKILL.md
Multi-pass code review. Review changes locally, then run `codex exec --json` as an independent read-only reviewer and merge the findings. Use before merging or after significant refactoring.
FTShare-LabSkillFTShare-Lab/agent-claim-network/.claude/skills/code-review/SKILL.md
Run ACN's canonical local-plus-external code-review workflow before merging or after significant refactoring.
iliaalSkilliliaal/ai-skills/skills/code-review/SKILL.md
Structured code reviews with severity-ranked findings and deep multi-agent mode. Use when performing a code review, auditing code quality, or critiquing PRs, MRs, or diffs, including a diff or patch pasted inline. For the full multi-agent workflow, use the ia-review command (/ia-review in Claude Code).
NVIDIASkillNVIDIA/NeMo-Fabric/examples/code_review_agent/skills/code-review/SKILL.md
Review Python changes for correctness risks and missing test coverage.
vuralserhat86Skillvuralserhat86/antigravity-agentic-skills/skills/code_review/SKILL.md
PR review, code smell detection, best practice kontrolü. ⚠️ Kod incelerken kullan. Deliverable kontrolü için → quality-validator, doküman review için → peer-review.
anthroosSkillanthroos/claude-code-review-skill/SKILL.md
AI code review for PR or local changes. 280+ checks across security, architecture, performance, testing, and code quality. Posts findings as GitHub PR comments with confidence scores.
cenconq25Skillcenconq25/claude-code-app-studio/.claude/skills/code-review/SKILL.md
Architectural and quality review of one or more files. Verifies coding standards, SOLID, testability, mobile anti-patterns, and ADR compliance. Use after /dev-story and before /story-done.
padmarajnidagundiSkillpadmarajnidagundi/Playwright-AI-Agent-POM-MCP-Server/.github/skills/code-review/SKILL.md
Reviews Playwright test code for POM compliance, best practices, security, and coverage completeness. Auto-loaded when the user asks to review, audit, or inspect test files.
scibly-devSkillscibly-dev/scibly/.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".
fagemxSkillfagemx/edda/.claude/skills/code-review/SKILL.md
Review merged code, commit ranges, or codebase paths for correctness, security, architecture, and test risk; use pr-review for open PRs
flc1125Skillflc1125/skills/skills/code-review/SKILL.md
Request or perform a git-backed code review for a defined diff or SHA range using implementation context and requirements. Use when finishing a task, completing a major feature, preparing to merge, or when you need a fresh review before proceeding.
muyenSkillmuyen/vibe-to-prod/.claude/skills/code-review/SKILL.md
Proactive code quality review. Triggers on significant code changes to check security, performance, architecture, and project patterns.
ptsilivisSkillptsilivis/autonomousguy/skills/code-quality/code-review/SKILL.md
Senior embedded-engineer code review. Defaults to Classic AUTOSAR embedded C and covers two concerns: (1) Correctness review — integer overflow, volatile correctness, ISR/task race conditions, stack usage, dynamic memory, control flow, AUTOSAR/ISO 26262 readiness, with findings rated Critical/Major/Minor; (2) Naming review — AUTOSAR Classic conventions for modules, SWC types, port names, runnables, C identifiers, typedefs, macros, and enumerations, aligned with MISRA Rule 5.x identifier uniqueness. Audits existing code and generates correctly-named identifiers for new work. Handles Adaptive AUTOSAR C++14+ when the input is C++ or names ara::, reviewing RAII, exceptions vs ara::core::Result, smart pointers, and AUTOSAR C++14 / MISRA C++:2023 naming. A third focus, legacy modernization assessment, proposes the smallest safe steps toward a MISRA-conformant, MCAL-abstracted, unit-tested state. Returns decision-ready findings with a built-in self-check and can emit a self-contained HTML report under analysis/.
felipereisdevSkillfelipereisdev/code-review-skill/SKILL.md
Performs a structured, comprehensive code review of git changes. Detects stack and architecture automatically, applies relevant stack/pattern-specific rules, and reports findings by severity. Use when: user runs /code-review, /review-pr, or asks to "review my changes".
galandoSkillgalando/piv-speckit/.claude/skills/code-review/SKILL.md
Auto-activates during code reviews
lezli01Skilllezli01/vincent/.claude/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/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".
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.
