agentsclimarketplace
Sign in

Shelves Review & quality

Code review

1,664 rows from 692 repositories

Reviewing a diff or a file for correctness, style and risk.

What Code review skills agree on

681 skill files read, by 668 of the 814 authors on this shelf whose files we hold, 2026-09-06

The middle one of the 78 measured here is ~1.4k tokens long, counted with cl100k_base

Counted by distinct author, so one author publishing three of these counts once. Where a claim sits in fewer files than authors, that is said: a claim held by forty authors across three files is one file people copied, not forty people who agreed. Near-identical wordings are grouped and the other wordings are shown, so the grouping is yours to check.

What they tell the agent to do

  1. Provide technical reasoning when pushing back84 of 668 in 70 filesalso worded as push back with technical reasoning if suggestion is wrong; push back with technical reasoning if suggestion is incorrect
  2. Fix critical issues immediately77 of 668 in 60 filesalso worded as Fix all critical and warning issues; fix critical issues immediately upon review
  3. Dispatch a code reviewer subagent76 of 668 in 59 filesalso worded as Dispatch code-reviewer subagent after each task; Dispatch code-reviewer subagent after major features
  4. Fix important issues before proceeding73 of 668 in 56 filesalso worded as Fix important issues before continuing; Fix critical and important issues before merging
  5. Ask for clarification on unclear items68 of 668 in 56 filesalso worded as Ask for clarification if feedback is unclear; ask questions for clarification
  6. Verify feedback against codebase before implementation66 of 668 in 55 filesalso worded as verify feedback against codebase reality; verify feedback against codebase reality before implementation
  7. Implement fixes one at a time64 of 668 in 53 filesalso worded as implement one item at a time; implement fixes one by one
  8. Test each fix individually62 of 668 in 51 filesalso worded as test each change individually; test every individual fix
  9. Restate technical requirements in own words57 of 668 in 46 filesalso worded as restate requirements in own words; restate technical requirements to ensure understanding
  10. Reply to inline comments in the specific thread51 of 668 in 40 filesalso worded as reply to inline comments in the thread; reply in the specific comment thread
  11. Note minor issues for later49 of 668 in 34 filesalso worded as Log minor issues for later; Document minor issues for later
  12. Group findings by severity48 of 668 in 47 filesalso worded as Categorize findings by severity; Classify findings by severity
  13. Prioritize blocking issues over simple fixes43 of 668 in 34 filesalso worded as prioritize blocking issues then simple then complex fixes; prioritize blocking issues over simple or complex fixes
  14. State corrections factually without apologies37 of 668 in 28 filesalso worded as state corrections factually without apology; state corrections factually without long apologies
  15. Get git SHAs for base and head commits35 of 668 in 25 filesalso worded as Provide base and head commit SHAs; Get git SHAs for base and head

What they tell it not to do

  1. Do not ignore critical issues85 of 668 in 62 filesalso worded as Ignore critical issues; do not ignore critical security vulnerabilities
  2. Do not skip review for simple changes80 of 668 in 63 filesalso worded as Do not skip review for simple tasks; Skip review for simple changes
  3. Do not proceed with unfixed important issues73 of 668 in 56 filesalso worded as Proceed with unfixed important issues; Proceed with unresolved important issues
  4. Do not use performative agreement64 of 668 in 53 filesalso worded as do not use performative agreement or gratitude; do not use performative agreement phrases
  5. Do not implement before verification60 of 668 in 49 filesalso worded as do not implement feedback before verification; do not implement suggestions before verification
  6. Do not argue with valid technical feedback54 of 668 in 37 filesalso worded as Argue with valid technical feedback; Argue against valid technical feedback
  7. Do not express gratitude46 of 668 in 35 filesalso worded as Do not use gratitude expressions; do not express gratitude in responses
  8. Do not share session history with reviewer41 of 668 in 32 filesalso worded as Do not share session history with the reviewer; Do not provide session history to the reviewer
  9. Do not apologize for incorrect pushback40 of 668 in 32 filesalso worded as do not apologize for pushback; do not apologize for pushing back
  10. Do not implement unclear items32 of 668 in 24 filesalso worded as do not implement unclear feedback; do not implement unclear findings

What they expect to be installed

  1. git300 of 668 in 292 files
  2. grep113 of 668 in 102 files
  3. gh93 of 668 in 79 files
  4. gh api45 of 668 in 37 files
  5. bash35 of 668 in 33 files
  6. npm audit18 of 668 in 16 files
  7. jq18 of 668 in 11 files
  8. npm18 of 668 in 17 files
  9. Task tool17 of 668 in 12 files
  10. npx16 of 668 in 9 files

What they ask it to produce

  1. Reasoned pushback57 of 668 in 46 filesalso worded as Reasoned pushback with evidence; Reasoned pushbacks
  2. Technical acknowledgment55 of 668 in 44 filesalso worded as Technical acknowledgement
  3. code review request53 of 668 in 49 filesalso worded as Code review report; Code review score
  4. Code fixes49 of 668 in 44 filesalso worded as Code fix; verified code fixes
  5. Standards review report44 of 668 in 35 filesalso worded as Review report; review reports
  6. Clarification request42 of 668 in 34 filesalso worded as clarification requests; clarifying questions
  7. Code review feedback40 of 668 in 25 filesalso worded as Constructive code review feedback; Review feedback
  8. Structured code review report35 of 668 in 33 filesalso worded as structured review report; Structured review summary

When Code review authors say to reach for one

The situations these authors wrote into their own files, counted out of the same 668 authors, with the skills that name each one

How Code review skills are built

1,503 skill directories by 664 authors, read from their repositories’ own file trees 2026-08-05

The middle bundle among those shipping files is 2 files, 12.8 KB beside SKILL.md

Counted by distinct author, same as above, so one author publishing forty template copies counts once. SKILL.md itself is not counted as a file, so a single-file skill is one where that file is the whole skill.

The shape

  1. SKILL.md is the whole skill312 of 664 authors, 762 of 1,503 skills
  2. files ship beside it352 of 664 authors, 741 of 1,503 skills
  3. executable scripts ship inside63 of 664 authors, 91 of 1,503 skills

The folders they converge on

  1. references/153 of 664 authors, 252 of 1,503 skills
  2. agents/49 of 664 authors, 58 of 1,503 skills
  3. scripts/48 of 664 authors, 75 of 1,503 skills
  4. evals/28 of 664 authors, 43 of 1,503 skills
  5. assets/21 of 664 authors, 29 of 1,503 skills
  6. templates/20 of 664 authors, 25 of 1,503 skills

  • Open code review delegate

    alibaba/open-code-review/plugins/open-code-review/skills/open-code-review-delegate Skill

    20,413★ repo

    Open-source & free — Battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in fine-tuned ruleset (NPE, thread-safety, XSS, SQL injection), OpenAI & Anthropic compatible.

  • Code reviewing

    huangjia2019/claude-code-engineering/04-Skills/projects/00-basic-skill/.claude/skills/code-reviewing Skill

    no license1,067★ repo

    This repository demonstrates how to use Claude Code to do real engineering work, not just writing code. 本项目是极客时间专栏 《Claude Code 工程化实战》 的官方配套示例仓库，目标就是： 👉 把 Claude Code 从“对话式编码工具”，变成 可设计、可复用、可治理的工程系统。

  • Go code review

    cxuu/golang-skills/skills/go-code-review Skill

    140★ repo

    AI Agent Skills for idiomatic, production-ready Go code, distilled from Google, Uber, Community

  • Code reviewer

    a-pavithraa/springboot-skills-marketplace/plugins/springboot-architecture/skills/code-reviewer Skill

    71★ repo

    Spring Boot Skill for Claude Code and Codex

  • Better code review graph

    n24q02m/better-code-review-graph/io.github.n24q02m/better-code-review-graph MCP server

    64★ repo

    Token-efficient code review knowledge graph: semantic search and call-graph resolution.

  • Code review

    next-open-ai/openclawx/presets/workspaces/code-assistant/skills/code-review Skill

    no license56★ repo

    a simple openclaw desktop u

  • Kamae review

    iwasa-kosui/kamae-ts/skills/kamae-review Skill

    53★ repo

  • Skills

    spencermarx/obsidian-ai/.ocr/skills Skill

    46★ repo

    Bring your own AI environment to Obsidian. For note/doc creation, refinement, search, organization, management, you name it!

  • Code review levels

    wigtn/wigtn-plugins/plugins/wigtn-plugins/skills/code-review-levels Skill

    45★ repo

    Claude Code Plugins for AI Native-based Engineer

  • Agentic code review

    DominikTobureto/awesome-grok-build/.grok/skills/agentic-code-review Skill

    42★ repo

    Grok Build resources, reusable .grok/skills, AGENTS.md templates, hooks, prompts, and starter workflows.

  • Code review

    Weaverse/.agents/skills/code-review Skill

    no license37★ repo

    Agents, skills, commands, and rules for AI-powered coding tools — used daily to supercharge development productivity.

  • Code review

    KarmaloopAI/Jiva/examples/personas/code-reviewer/skills/code-review Skill

    35★ repo

    Jiva is a CLI-first, open source autonomous AI agent and open alternative to Claude. Written in TypeScript with native support for Sarvam-105B and gpt-oss-120b, it autonomously plans and executes tasks from your terminal. Supports MCP servers, a built-in Skills system, and Jiva Personas - a plugin framework fully compatible with Claude Plugins.

  • Code review

    stellarlinkco/skills/skills/code-review Skill

    no license25★ repo

    Agent skills for long-running execution, high-recall code review, and measurable self-improvement loops.

  • Skills

    spencermarx/orc/.ocr/skills Skill

    no license22★ repo

    A lightweight orchestration framework that piggybacks your local Agentic CLI setup. Intentionally simple. Yet powerful... like an army of Orcs 👹

  • React senior code review

    the-senior-dev/senior-dev-skills/skills/react-senior-code-review Skill

    19★ repo

    Claude Code skills to help you think like a Senior Engineer.

  • Xreview

    davidleitw/xreview/.agents/skills/xreview Skill

    12★ repo

    Agent-native code review engine for Claude Code — delegates review to Codex for independent three-party consensus

  • Dotnet techne code review

    Metalnib/dotnet-episteme-skills/skills/dotnet-techne-code-review Skill

    12★ repo

    DotNet Episteme Skills - a curated, manual-first .NET AI skills library rooted in systematic knowledge (episteme) and shaped by disciplined craft (techne), designed for engineers who prioritise precision over hype.

  • Code review

    skael-dev/skael/examples/code-review Skill

    10★ repo

  • Active read

    paultyng/skill-issue/skills/active-read Skill

    9★ repo

    Personal Claude Code / Cursor agent skills, rules, and config

  • Deep code review

    agentlogbooks/logbooks/plugins/deep-code-review/skills/deep-code-review Skill

    no license7★ repo

    Structured state for agent skills

  • Code review

    kambleakash0/agent-skills/skills/code-review Skill

    7★ repo

    A curated collection of custom AgentSkills and token-saving MCP servers for extending the capabilities of AI coding assistants like Claude Code.

  • Aif code review

    ainative-build/skills/skills/engineering/aif-code-review Skill

    7★ repo

    Portable, self-contained coding-agent skills

  • Code review

    devrimcavusoglu/skern/tests/manual/scenarios/09-template-skills/templates/code-review Skill

    7★ repo

    Mass Skills Manager for Agents on AI Driven Development

  • Code review

    0xMassi/claude-skills/code-review Skill

    6★ repo

    Twelve Claude Code skills enforcing strict code quality, security, and modern language patterns across TypeScript, Rust, Swift, Go, JavaScript, and PostgreSQL.

  • Gerrit Code Review

    GaijinEntertainment/go-gerrit-mcp/team.gaijin/go-gerrit-mcp MCP server

    6★ repo

    Capability-gated Gerrit code review tools with opt-in review notifications pushed into the session

  • Php code review

    jeeinn/claude-skills/php-code-review Skill

    5★ repo

    claude skills for my work

  • Code review coach

    Far-200/think-before-code/skills/code-review-coach Skill

    5★ repo

    Socratic Agent Skills for learning problem-solving and software-engineering judgment — one question at a time.

  • Code review

    kimon1230/claude_extensions/skills/code-review Skill

    4★ repo

    Custom hooks, skills, and rules for Claude Code: adds automatic Python formatting, context persistence across sessions, parallel subagent workflows, and a status line.

  • Rbsmithy

    gogolumo/rbsmithy-roblox-claude-skill/skills/rbsmithy Skill

    no license3★ repo

    A Claude Skill that turns Claude Code into a Roblox game development assistant for Luau, Rojo, multiplayer systems, 3D assets, optimization, QA, and production-ready Roblox releases.

  • Auto code review

    i-stack/ai-coding-kit/skills-engineering/auto-code-review Skill

    3★ repo

    Sync your MCP servers, Agent Skills, and AI rules across Cursor, Claude Code, Cline & more in one click.

  • Frontend code review

    DNM03/frontend-code-review/skills/frontend-code-review Skill

    3★ repo

    Agent skills for production-ready frontend code reviews across React, Next.js, TypeScript, accessibility, UX, performance, and SEO.

  • Code review

    schalkneethling/claude-toolkit/skills/code-review Skill

    3★ repo

    CLI for managing Agent commands, hooks, and skills across projects.

  • Code review

    wardawgmalvicious/claude-config/skills/code-review Skill

    2★ repo

    Personal Claude Code config — skills, subagents, hooks, and rules for Microsoft Fabric and Power BI workflows on Windows. Cherry-pickable, no semver.

  • Multi code review

    szarkans/multi-code-review/skills/multi-code-review Skill

    2★ repo

    Consensus code review: Claude + OpenAI Codex (+ optional Google Antigravity) review the same diff in parallel, findings reconciled into one report. Claude Code plugin marketplace + Agent Skills format.

  • Code review

    edenfunf/promptc/examples/bloated-demo/.claude/skills/code-review Skill

    2★ repo

    Measure worst-case skill-context exposure in your Claude Code setup.

  • Code review

    d0hx4n2503/Agent-Skills/skills /engineering/code-review Skill

    2★ repo

    Collection of useful skills, prompts, tools and best practices for engineers when building and working with AI Agents

  • Aidress skill find verified code review agent

    Aidress-ai/aidress-skill-find-verified-code-review-agent Skill

    2★

    Find a Verified Code Review Agent. Agent discovery, trust verification, and capability routing powered by Aidress — the coordination registry for autonomous AI agents. Use for software agent discovery, trust verification, and capability routing — via Aidress (https://api.aidress.ai).

  • Code review judgment

    pinkstrokes/self-distillation/skills/code-review-judgment Skill

    2★ repo

    Reusable agent skills for distilling narrow human capabilities into tested behavior

  • Code reviewer

    rumotion/ai-agent-project-template/.agents/skills/code-reviewer Skill

    2★ repo

    Low-context AI agent project template for Gemini, Codex, Claude, Cline, and more. One canonical AGENTS.md, shared Memory Bank, portable skills, workflows, hooks, and deterministic validation.

  • Odoo code review

    omas-odoo/odoo-superpowers/skills/odoo-code-review Skill

    no license1★ repo

    Odoo development skills for AI coding agents — a Claude Code plugin (also Codex & Gemini CLI) packaging PSDU principles for models, views, security, migrations, tests & code review. Principles, not rules.

  • Ai code review

    lennney/gate-all-skills/skills/ai/ai-code-review Skill

    no license1★ repo

    Frontend/Next.js Claude Code Skills — curated + custom

  • Odoo code review

    assoumaaa/odoo-superpowers/skills/odoo-code-review Skill

    no license1★ repo

    Odoo development skills for AI coding agents — a Claude Code plugin (also Codex & Gemini CLI) packaging PSDU principles for models, views, security, migrations, tests & code review. Principles, not rules.

  • Adversarial review

    claude-hangar/claude-hangar/core/skills/adversarial-review Skill

    1★ repo

    Production-grade configuration management for Claude Code. Hooks, agents, skills, multi-project orchestration.

  • Code review

    bjg4/bgskillz/bakeoff/fixtures/v4/code-review/code-review Skill

    1★ repo

    Build high-quality, portable Claude skills that trigger reliably and deliver real value.

  • Code review

    w4xqz/code-review-skill/code-review Skill

    no license1★ repo

    Automate code reviews for general code projects with modular parallel checks, config-driven scope, and clear reports.

  • Claude code review

    thattimc/skills/skills/claude-code-review Skill

    1★ repo

    Claude Code skills marketplace: domain-search + ssr-market-research (also usable as plain skill folders in Codex/Cursor)

  • Code review brief

    gitgitWi/council-flow/skills/code-review-brief Skill

    no license1★ repo

    Multi-LLM Plan and TDD flow

  • Chatgpt pro review

    heyNag/charms/packages/chatgpt-pro-review/skills/chatgpt-pro-review Skill

    1★ repo

    Small, practical powers for coding agents.

  • Code review

    primeline-ai/primeline-skills/skills/code-review Skill

    1★ repo

    5 production-grade workflow skills for Claude Code. Debugging, delegation, planning, code review, configuration architecture.

  • Code review

    eglenn-dev/dt-skills/skills/code-review Skill

    no license1★ repo

    A collection of AI agent skills for DataThink

  • Code review excellence

    b-mendoza/agent-skills/.agents/skills/code-review-excellence Skill

    no license1★ repo

    A collection of reusable skills for AI-assisted development workflows

  • Refactoring audit

    magallon/refactoring-toolkit/refactoring-audit Skill

    1★ repo

    Stack-agnostic refactoring audit & execution skills for AI agents

  • Code reviewer

    zrosenbauer/skills/skills/code-reviewer Skill

    1★ repo

    Personal monorepo of agent skills (SKILL.md format) — agent-agnostic, works with Claude Code, Cursor, Codex, and others.

  • Code review

    coreline-ai/claude-devflow-plugin/skills/code-review Skill

    1★ repo

    Claude Code 개발 라이프사이클 스킬 번들: Plan·Parallelize·Test·Review·Ship | Claude Code dev lifecycle skill bundle: Plan, Parallelize, Test, Review, Ship

  • Code review

    aictrl-dev/skills/skills/code-review Skill

    1★ repo

    Eleven free, vendor-neutral AI engineering skills for common SDLC workflows.

  • Code review

    Alex7develop/my-agent-skills/skills/code-review Skill

    1★ repo

    Практики senior-разработчика для AI-агентов: спека → TDD → отладка → рефакторинг → ревью → PR. 6 skills для Cursor, Claude Code, Codex и 70+ агентов.

  • Code review skill

    41Yr9/vibeplus/skills/code-review-skill Skill

    1★ repo

    コーディング依頼を受け取ってからPull Requestを作成し、得られた知見を次回へ活かすまでを支援するCodexプラグイン

  • Dingdawg code review

    dingdawg/dingdawg-agent-1/io.github.dingdawg/dingdawg-code-review MCP server

    1★ repo

    AI code review — security, quality, performance. Learns your patterns. Receipted.

  • Code review

    claudifytech/claude-code-skills-starter/skills/code-review Skill

    0★ repo

    Free starter skills for Claude Code: conventional commits, code review, test writing, and README generation, plus a starter CLAUDE.md. From the makers of Claudify.

  • Stern code review

    y-a-v-a/stern-code-review Skill

    no license0★

    What I most desire doesn’t exist on the market yet: a coding agent model, but it’s only been trained on code reviews by Eastern Europeans. - vicki on X

All 1,664 in the catalog