agentsclimarketplace
Sign in

Shelves

Review & quality

19,471 rows from 4,065 repositories

Reading code and calling out what is wrong with it.

What Review & quality skills agree on

1,766 skill files read, by 1,273 of the 2,403 authors on this shelf whose files we hold, 2026-09-06

The middle one of the 173 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. Ask one question at a time63 of 1273 in 62 filesalso worded as Ask questions one at a time; ask only one question at a time
  2. Provide a recommended answer for each question47 of 1273 in 45 filesalso worded as Provide a recommended answer with each question; provide a recommended answer for every question
  3. Rank findings by severity44 of 1273also worded as Report findings ordered by severity; Group findings by severity
  4. Use parameterized queries for database access38 of 1273 in 20 filesalso worded as use parameterized queries for all database operations; use parameterized queries for SQL
  5. Validate all user input with schemas33 of 1273 in 15 filesalso worded as Validate all user inputs; validate all user inputs before processing
  6. Store secrets in environment variables32 of 1273 in 14 filesalso worded as store all secrets in environment variables; use environment variables for secrets
  7. Explore the codebase to answer questions31 of 1273 in 29 filesalso worded as explore codebase to answer questions; explore the codebase before asking questions
  8. Store tokens in httpOnly cookies30 of 1273 in 12 filesalso worded as store authentication tokens in httpOnly cookies; store authentication tokens in httpOnly cookies or secure storage
  9. Implement rate limiting on API endpoints30 of 1273 in 12 filesalso worded as implement rate limiting on all endpoints; apply rate limiting to all API endpoints
  10. Sanitize user-provided HTML29 of 1273 in 11 filesalso worded as sanitize user-provided HTML content; sanitize all user-provided HTML content
  11. Return generic error messages to users28 of 1273 in 10 filesalso worded as use generic error messages for users; return generic error messages to prevent account enumeration
  12. Cite file and line for every finding28 of 1273 in 25 filesalso worded as Cite specific file and line numbers in findings; cite file and line for all findings
  13. Configure content security policy headers27 of 1273 in 9 filesalso worded as configure strict content security policy headers
  14. Redact sensitive data from logs27 of 1273 in 9 filesalso worded as redact sensitive data from all logs; redact sensitive data from application logs
  15. Verify authorization before sensitive operations27 of 1273 in 9 filesalso worded as perform authorization checks before sensitive operations

What they tell it not to do

  1. Do not hardcode secrets in source code38 of 1273 in 21 filesalso worded as never hardcode secrets in source code; do not hardcode secrets
  2. Never concatenate strings in SQL queries33 of 1273 in 15 filesalso worded as do not concatenate SQL queries; do not concatenate strings in SQL queries
  3. Do not store tokens in localStorage32 of 1273 in 14 filesalso worded as never store tokens in localStorage; Do not store tokens in localStorage or sessionStorage
  4. Do not expose stack traces to users26 of 1273 in 14 filesalso worded as do not expose stack traces in production; never expose stack traces to users
  5. Do not ask multiple questions at once26 of 1273also worded as Do not batch multiple issues into one question; Do not fix multiple issues at once
  6. Do not log sensitive data22 of 1273 in 11 filesalso worded as do not log sensitive data like passwords or cards; do not store sensitive data in URLs or logs
  7. Do not modify source code22 of 1273also worded as Do not modify code; Do not modify code during review
  8. Do not commit changes22 of 1273also worded as do not auto-commit changes; do not make commits
  9. Do not modify any files21 of 1273also worded as Do not modify files; Never modify files
  10. Do not proceed without user approval21 of 1273also worded as Do not proceed without architecture data; Do not proceed without user response to persona interrogation

What they expect to be installed

  1. git346 of 1273
  2. gh130 of 1273
  3. grep117 of 1273
  4. bash61 of 1273
  5. codex58 of 1273
  6. Read52 of 1273
  7. AskUserQuestion47 of 1273
  8. npm47 of 1273 in 29 files
  9. Agent45 of 1273
  10. python344 of 1273

What they ask it to produce

  1. Review report87 of 1273also worded as Review findings; security review report
  2. Structured review report57 of 1273 in 56 filesalso worded as Structured PR review document; Structured critique report
  3. Review summary50 of 1273 in 44 filesalso worded as Code review summary; Summary report
  4. review.md45 of 1273also worded as report.md; review-report.md
  5. Markdown report38 of 1273also worded as Markdown review report; Review report in markdown format
  6. Verdict33 of 1273also worded as verdict.json; Final verdict
  7. Security checklist31 of 1273 in 12 filesalso worded as markdown security checklist; Verification checklist
  8. Automated security tests27 of 1273 in 9 filesalso worded as automated security test suite

When Review & quality authors say to reach for one

The situations these authors wrote into their own files, counted out of the same 1,273 authors, with the skills that name each one

How Review & quality skills are built

18,105 skill directories by 3,571 authors, read from their repositories’ own file trees 2026-08-05

The middle bundle among those shipping files is 2 files, 11.9 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 skill1,289 of 3,571 authors, 9,708 of 18,105 skills
  2. files ship beside it2,282 of 3,571 authors, 8,397 of 18,105 skills
  3. executable scripts ship inside973 of 3,571 authors, 2,482 of 18,105 skills

The folders they converge on

  1. references/1,305 of 3,571 authors, 4,053 of 18,105 skills
  2. scripts/806 of 3,571 authors, 1,994 of 18,105 skills
  3. agents/534 of 3,571 authors, 1,362 of 18,105 skills
  4. assets/297 of 3,571 authors, 566 of 18,105 skills
  5. evals/229 of 3,571 authors, 605 of 18,105 skills
  6. examples/156 of 3,571 authors, 422 of 18,105 skills

  • Codex qa

    code-yeongyu/oh-my-openagent/.agents/skills/codex-qa Skill

    no license67,917★ repo

    omo/lazycodex: The coding agent for tokenmaxxers;the one and only agent harness for complex codebases. For your Codex, for your OpenCode

  • Oh My Posh Validator

    JanDeDobbeleer/oh-my-posh/dev.ohmyposh/validator MCP server

    23,285★ repo

    Validate oh-my-posh configurations and segment snippets against the official schema.

  • 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.

  • Academic paper reviewer

    zebbern/claude-code-guide/skills/academic-paper-reviewer Skill

    4,568★ repo

    Claude Code Guide - Setup, Commands, workflows, agents, skills & tips-n-tricks go from beginner to power user!

  • Gemini

    nowork-studio/NotFair/gemini Skill

    3,336★ repo

    Goal-driven, loop-powered marketing agents that crush your business goals 24/7

  • Document review

    open-gitagent/opengap/examples/full/skills/document-review Skill

    2,907★ repo

    A framework-agnostic, git-native standard for defining AI agents

  • Impeccable

    silverstein/minutes/.agents/skills/impeccable Skill

    1,426★ repo

    Every meeting, every idea, every voice note — searchable by your AI. Open-source, privacy-first conversation memory layer.

  • Clean code guard

    amElnagdy/guard-skills/skills/clean-code-guard Skill

    1,154★ repo

    Guard skills for coding agents, quality gates that catch AI-generated failure modes in code, tests, and docs

  • 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。

  • Mariadb operator comment

    mariadb-operator/mariadb-operator/.agents/skills/mariadb-operator-comment Skill

    998★ repo

    🦭 Run and operate MariaDB in a cloud native way

  • Check accessibility

    AgnosticUI/agnosticui/.claude/skills/check-accessibility Skill

    823★ repo

    AgnosticUI Local (v2) is a CLI-based UI component library that copies components directly into your project. Works with AI tools, agent-driven UIs, and prompt-ready workflows.

  • Agy delegate

    amElnagdy/delegate-skills/skills/agy-delegate Skill

    724★ repo

    Drive Codex, OpenCode, Antigravity, Grok, or Kimi as a background implementer — brief it, review its diff, land the commit yourself.

  • Api contract review

    decebals/claude-code-java/.claude/skills/api-contract-review Skill

    703★ repo

    Reusable AI development infrastructure for Java projects, optimized for Claude Code

  • Ai governance reviewer carl ditzler

    lawve-ai/awesome-legal-skills/skills/ai-governance-reviewer-carl-ditzler Skill

    no license641★ repo

    A curated list of awesome Agent Skills for automating legal work

  • Affiliate skills

    Affitor/affiliate-skills Skill

    595★

    50 AI agent skills for affiliate marketing. Research trending content, write data-backed posts, generate infographics, build landing pages, deploy — full flywheel with social intelligence. Works with Claude Code, Pi, ChatGPT, Gemini, Cursor, Windsurf, any AI.

  • Nw ab critique dimensions

    nWave-ai/nWave/nWave/skills/nw-ab-critique-dimensions Skill

    591★ repo

    AI agents that guide you from idea to working code, with you in control at every step.

  • App store review arbitrage

    Varnan-Tech/opendirectory/skills/app-store-review-arbitrage Skill

    576★ repo

    AI Agent Skills built for Founders who hate Marketing

  • Vibe check mcp server

    PV-Bhat/vibe-check-mcp-server/io.github.PV-Bhat/vibe-check-mcp-server MCP server

    503★ repo

    Metacognitive AI agent oversight: adaptive CPI interrupts for alignment, reflection and safety

  • A11y audit

    plugin87/ux-ui-agent-skills/.claude/skills/a11y-audit Skill

    no license493★ repo

    Turn Claude into a Senior Design Architect — DTCG design tokens, 42 components, WCAG 2.2 accessibility, any-framework code, 138 design systems, and runnable skills.

  • Agent judge criteria

    alibaba/skill-up/e2e/testdata/agent-judge-criteria Skill

    434★ repo

    An evaluation and evolution tool for Agent Skills.

  • Git branch cleanup

    gotalab/skillport/.skills/experimental/git-branch-cleanup Skill

    407★ repo

    Bring Agent Skills to Any AI Agent and Coding Agent — via CLI or MCP. Manage once, serve anywhere.

  • Answer reviewer questions

    tobihagemann/turbo/claude/skills/answer-reviewer-questions Skill

    399★ repo

    A composable dev process for agentic coding harnesses, packaged as modular skills. Turbo has sibling editions for Claude Code and Codex.

  • Pr review

    microsoft/win-dev-skills/.github/skills/pr-review Skill

    377★ repo

    Agents and skills for building Windows apps with WinUI 3 and the Windows App SDK

  • Git release

    wesammustafa/opencode-primer/.opencode/skills/git-release Skill

    364★ repo

    Master OpenCode, the open-source AI coding agent — setup, agents, skills, plugins, MCP, Zen & headless CI.

  • Humanities writing companion

    tizzy916/humanities-writing-companion Skill

    no license357★

    End-to-end humanities writing assistant — an Agent Skill (open SKILL.md format). 11 modes from Socratic research-question sharpening through AI-use disclosure. Bilingual (EN/中文), discipline-aware (literature/history/philosophy/art/religion/linguistics + cross-disciplinary). Four-layer critique, calibratable devils advocate, voice preservation.

  • Ai check

    harshaneel/humanize/ai-check Skill

    350★ repo

    Best static AI text humanizer. Two research-grounded LLM-agnostic skills that make AI writing sound human and relatable. Nine levers, 50+ peer-reviewed sources, 2024-2026 detection literature.

  • Genshijin commit

    InterfaceX-co-jp/genshijin/skills/genshijin-commit Skill

    307★ repo

    genshijin 原始人 🗿| Claude Code / Codex等AIエージェント 向け超圧縮コミュニケーションスキル。caveman の日本語版をベースに、日本語特有の冗長表現に最適化。

  • Domain check

    saidutt46/domain-check/io.github.saidutt46/domain-check MCP server

    no license299★ repo

    Fast domain availability checker with RDAP/WHOIS — batch checks, TLD presets, and name generation.

  • Address pr comments cecil

    Cecilapp/Cecil/.github/skills/address-pr-comments-cecil Skill

    294★ repo

    A simple and powerful content-driven static site generator.

  • Accessibility audit

    billy-enrizky/openbrowser-ai/plugin/skills/accessibility-audit Skill

    238★ repo

    OpenBrowser is a framework for intelligent browser automation. It combines direct CDP communication with a CodeAgent architecture, where the LLM writes Python code executed in a persistent namespace, to navigate, interact with, and extract information from web pages autonomously.

  • Cli review

    alvinunreal/lazyskills/.agents/skills/cli-review Skill

    231★ repo

    mission control for agent skills

  • Git mcp server

    cyanheads/git-mcp-server/io.github.cyanheads/git-mcp-server MCP server

    231★ repo

    Comprehensive Git MCP server enabling native git tools including clone, commit, worktree, & more.

  • Wp performance review

    elvismdev/claude-wordpress-skills/skills/wp-performance-review Skill

    222★ repo

    Professional WordPress engineering skills for Claude Code - performance optimization, security auditing, Gutenberg block development, and theme/plugin best practices.

  • Commit assisted by

    fluxcd/agent-skills/internal/skills/commit-assisted-by Skill

    205★ repo

    Skills to transform AI Agents into GitOps Engineers

  • Grill me

    secondsky/claude-skills/.agents/skills/grill-me Skill

    204★ repo

    Production-ready skills for Claude Code CLI - Cloudflare, React, Tailwind v4, and AI integrations

  • Han release

    testdouble/han/.claude/skills/han-release Skill

    195★ repo

    Han: AI skills and agents for "Solo" product engineers and small teams

  • melta UI

    tsubotax/melta-ui/io.github.tsubotax/melta-ui MCP server

    194★ repo

    AI-Ready design system MCP: melta UI tokens, component contracts, 99 rules, check_html self-verify

  • Bkt

    avivsinai/bitbucket-cli/skills/bkt Skill

    183★ repo

    Bitbucket CLI with gh-like ergonomics

  • Commit

    kklimuk/docx-cli/.claude/skills/commit Skill

    178★ repo

    CLI for AI agents (Claude, Codex) to read, edit, and comment on .docx files with full format fidelity.

  • Ultracode

    PabloNAX/ultracode-skill/ultracode Skill

    174★ repo

    Codex-first Ultracode skill for dynamic coding workflows

  • Zach feature demand validator

    zach22-1999/amazon-skills/skills/zach-feature-demand-validator Skill

    151★ repo

    Open-source Agent Skills for Amazon sellers: product research, feature validation, listing audits, ads search-term analysis, and CVR diagnostics. 亚马逊跨境电商 Skills。

  • Contextual commit

    berserkdisruptors/contextual-commits/skills/contextual-commit Skill

    146★ repo

    An open standard for capturing the WHY in git history

  • 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

  • Compliance check

    guangshu100/BidMaster-Pro/skills/check/compliance_check Skill

    140★ repo

    全流程 智能招投标 Agent：标书生成 · 招投标解读 · 标书检查 · 标书文档ai排版 · 商机发现 一键完成。 21 项合规检查 · 多模型切换 · RAG 知识库 · OCR 抽取。 从招标公告到可交付 docx 文档，全流程 AI 自动化。

  • Orangeo ai visibility skill

    PixelOrange7/orangeo-ai-visibility-skill Skill

    130★

    Open-source GEO / AEO skill for AI visibility readiness: check robots.txt, llms.txt, schema, citation signals, competitor gaps, and buyer prompts

  • Gdpr compliance checker

    goSprinto/compliance-skills/gdpr-compliance-checker Skill

    130★ repo

  • Grammar checker

    DaleSeo/korean-skills/skills/grammar-checker Skill

    129★ repo

    🇰🇷 Korean language skills for AI agents

  • Adversarial case builder

    wanshuiyin/Anti-Autoresearch/skills/adversarial-case-builder Skill

    123★ repo

    Don't trust an autoresearch paper at face value. Reviewer-side integrity forensics (self-consistency + fabrication), deterministic verdict. 61 signals: 46 integrity hack-patterns (families A–H, verdict-bearing) + 13 zero-weight AI writing-style impressions (AIS) + 2 advisory. Not an opaque AI-text classifier. The dual of ARIS.

  • Fable5 mode

    cozytab/fable5-mode Skill

    118★

    Make Opus 4.8 (or any Claude model) work like Claude Fable 5 — a Claude Code skill + guard hooks (plan gate, model ceiling, per-task enforcement) for Fable-5-grade discipline: plan, self-verify, and route sub-agents, without Fable 5.

  • Altimate code

    AltimateAI/data-engineering-skills/skills/altimate-code Skill

    118★ repo

    Skills related to Data Engineering Work for Claude Code

  • Video explainer

    runesleo/claude-video-kit/skills/video-explainer Skill

    113★ repo

    Agent Skill + Remotion pipeline: brief/script → review receipt → narrated 9:16 explainer. RC: video-explainer skill.

  • Fallow review

    fallow-rs/fallow-skills/fallow/skills/fallow-review Skill

    113★ repo

    Agent skills for fallow, codebase intelligence for TypeScript and JavaScript. Teaches AI agents how to find unused code, duplication, circular deps, complexity hotspots, architecture drift, design-system drift, and (with Fallow Runtime) hot-path and cold-path evidence. Works with Claude Code, Cursor, Codex, Gemini CLI, and 30+ agents.

  • Academic citation

    joshua-zyy/academic-paper-writer/skills/academic-citation Skill

    104★ repo

    面向 CS / AI / ML 领域的证据驱动、分节推进的论文写作 Agent Skill。

  • Verify

    rengwu/wayfinder-maps/.claude/skills/verify Skill

    96★ repo

    Planetary visualization tool for /wayfinder maps

  • Architecture review

    omergocmen/vibe-coder-kit/.agent/skills/architecture-review Skill

    89★ repo

  • Git pr description

    deancourse/git-worktree-demo/.agent/skills/git-pr-description Skill

    no license86★ repo

    一站式業務管理平台，助你掌控銷售線、提升成交率。

  • Paper format agent

    zxyasfas/paper_format_agent/io.github.zxyasfas/paper-format-agent MCP server

    83★ repo

    Local-first DOCX formatter for academic papers with a content-fingerprint integrity guard.

  • Adyen webhooks

    hookdeck/webhook-skills/skills/adyen-webhooks Skill

    80★ repo

    Webhook integration skills for AI coding agents (Claude Code, Cursor, Copilot). Step-by-step guidance for setting up webhook receivers, signature verification, and event handling for Stripe, Shopify, GitHub, and more. Built on the Agent Skills specification.

  • Chinese reference formatter skill

    Zechang-Xiong/chinese-reference-formatter-skill Skill

    73★

    Codex skill for formatting Chinese academic references and BibTeX

  • Code reviewer

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

    71★ repo

    Spring Boot Skill for Claude Code and Codex

All 19,471 in the catalog