agentsclimarketplace
Sign in

Shelves Review & quality

Quality gates

7,902 rows from 2,334 repositories

Checks that block a change rather than commenting on it.

What Quality gates skills agree on

2,127 skill files read, by 1,524 of the 2,830 authors on this shelf whose files we hold, 2026-09-06

The middle one of the 271 measured here is ~1.5k 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. Read full output and check exit code45 of 1524 in 40 filesalso worded as read full output and check exit codes; read the full output and check exit codes
  2. Verify output confirms the claim44 of 1524 in 39 filesalso worded as Output verification results; confirm the output supports your claim
  3. Identify the command that proves the claim43 of 1524 in 39 filesalso worded as identify the command proving the claim; identify the command that derives each claim
  4. Execute the full verification command36 of 1524 in 30 filesalso worded as provide full output of verification commands; execute full verification commands fresh
  5. Produce a verification report34 of 1524 in 18 filesalso worded as generate verification report; Produce verification report
  6. Review git diff changes30 of 1524 in 16 filesalso worded as review git diff for unintended changes; Review git diff
  7. Fix build failures immediately29 of 1524 in 9 filesalso worded as Fix compilation errors immediately; stop and fix build failures immediately
  8. Group findings by severity28 of 1524also worded as Categorize findings by severity; rank findings by severity
  9. State claim only with evidence27 of 1524 in 22 filesalso worded as State claims only with evidence; make the claim only with evidence
  10. Verify regression tests with red-green cycle26 of 1524 in 22 filesalso worded as perform red-green cycle for regression tests; run regression tests through red-green cycle
  11. Run the full test suite26 of 1524 in 25 filesalso worded as Run test suite; Run the test suite
  12. Run test suite with coverage25 of 1524 in 10 filesalso worded as Execute test suite with coverage; run test suite with coverage collection
  13. Fix critical type errors22 of 1524 in 7 filesalso worded as fix critical type errors before continuing; Fix critical type errors before proceeding
  14. Verify every fifteen minutes22 of 1524 in 7 filesalso worded as run verification every fifteen minutes during long sessions; Verify every 15 minutes in long sessions
  15. Run build verification22 of 1524 in 7 filesalso worded as Run build verify before PRs; run verification against production builds

What they tell it not to do

  1. Do not claim completion without fresh verification72 of 1524 in 69 filesalso worded as do not claim success without fresh verification; Do not claim completion without fresh verification evidence
  2. Do not skip verification steps41 of 1524also worded as do not skip any verification steps; do not skip full verification for efficiency
  3. Do not use hedging words like should or probably40 of 1524 in 34 filesalso worded as do not use hedging language like should or probably; Do not use hedging language like should or seems
  4. Do not express satisfaction before verification39 of 1524 in 34 filesalso worded as Expressing satisfaction before verification; do not express satisfaction before verifying
  5. Do not rely on partial verification37 of 1524 in 33 filesalso worded as Relying on partial verification; Do not rely on partial test runs
  6. Do not trust agent success reports blindly30 of 1524 in 26 filesalso worded as do not trust agent success reports; Trusting agent reports without checking
  7. Do not modify any files28 of 1524 in 26 filesalso worded as Do not modify files; never modify the source file
  8. Do not claim work is done without evidence28 of 1524 in 27 filesalso worded as do not report findings without evidence; Do not claim completion without evidence
  9. Do not continue if build fails26 of 1524 in 11 filesalso worded as do not continue if build fails; Do not continue after a failed gate
  10. Do not commit secrets to source code20 of 1524 in 13 filesalso worded as Do not commit secrets or API keys; do not commit production secrets

What they expect to be installed

  1. git335 of 1524
  2. grep193 of 1524
  3. bash136 of 1524
  4. npm133 of 1524 in 121 files
  5. python3133 of 1524
  6. curl104 of 1524
  7. gh91 of 1524 in 89 files
  8. node88 of 1524
  9. ruff86 of 1524 in 74 files
  10. python83 of 1524

What they ask it to produce

  1. Verification report111 of 1524 in 93 filesalso worded as verification status report; verification-report.md
  2. Validation report68 of 1524 in 58 filesalso worded as JSON validation report; validation reports
  3. Verification results40 of 1524also worded as Validation results; verification results report
  4. Verification command output37 of 1524 in 32 filesalso worded as Command output; fresh verification command output
  5. Screenshots29 of 1524also worded as screenshot; screenshot files
  6. Evidence-backed status report29 of 1524 in 25 filesalso worded as status report with evidence; evidence-based status report
  7. Verification evidence28 of 1524 in 27 filesalso worded as evidence of verification; Verification report with evidence
  8. Summary report28 of 1524also worded as summary table; Summary

When Quality gates authors say to reach for one

The situations these authors wrote into their own files, counted out of the same 1,524 authors, with the skills that name each one

How Quality gates skills are built

7,290 skill directories by 2,067 authors, read from their repositories’ own file trees 2026-08-05

The middle bundle among those shipping files is 3 files, 14.4 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 skill822 of 2,067 authors, 3,905 of 7,290 skills
  2. files ship beside it1,245 of 2,067 authors, 3,385 of 7,290 skills
  3. executable scripts ship inside531 of 2,067 authors, 1,272 of 7,290 skills

The folders they converge on

  1. references/705 of 2,067 authors, 1,762 of 7,290 skills
  2. scripts/438 of 2,067 authors, 948 of 7,290 skills
  3. agents/237 of 2,067 authors, 458 of 7,290 skills
  4. assets/149 of 2,067 authors, 248 of 7,290 skills
  5. evals/122 of 2,067 authors, 279 of 7,290 skills
  6. examples/94 of 2,067 authors, 274 of 7,290 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.

  • 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

  • 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.

  • 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.

  • 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.

  • 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.

  • 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.

  • 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.

  • 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

  • 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。

  • 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

  • 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.

  • 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

  • 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

  • Docs claim check

    kyungseo/skillstead/skills/docs-claim-check Skill

    71★ repo

    Practical, portable skills for agentic coding workflows — clearer diagrams, checked claims, safer GitHub releases, natural EN↔KO writing.

  • Ai output validation

    DevelopersGlobal/ai-agent-skills/skills/ai-output-validation Skill

    65★ repo

    AI agent skills for production grade applications

  • Anti wechat ai check

    lovstudio/skills/skills/anti-wechat-ai-check Skill

    65★ repo

    Top-level index for the Lovstudio skills ecosystem

  • Mcp slim guard

    lennney/mcp-slim-guard/io.github.lennney/mcp-slim-guard MCP server

    59★ repo

    Schema compression (83%+ savings) + security proxy for MCP servers — SSRF, injection, rate limit

  • Artifact consistency checker

    GulajavaMinistudio/awesome-copilot-id/.agents/skills/artifact-consistency-checker Skill

    58★ repo

    A curated collection of custom agents, skills, rules, and prompts for GitHub Copilot, Google Antigravity, OpenCode, ChatGPT Codex, and Oh My Pi. Tailored for Indonesian developers to streamline SDLC workflows with AI.

  • Citecheck

    color4-alt/CiteCheck/skills/citecheck Skill

    56★ repo

    Agent Skill: Check academic paper citations for format, queryability, thematic relevance, and semantic accuracy.

  • Kamae review

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

    53★ repo

  • Speq audit

    marconae/speq-skill/.claude/skills/speq-audit Skill

    48★ repo

    A light-weight and straightforward system for spec-driven development with Claude Code or OpenAI Codex. Written in Rust 🦀

  • Work with design systems

    natdexterra/work-with-design-systems Skill

    48★

    Inspect, build, or extend Figma design systems from Claude Code. Read-only audits with WCAG checks and component scoring, build mode with variable bindings and slots, optional Phase 6 sync to tokens.css + AI rules.

  • Maintenance rules

    motiful/skill-forge/.claude/skills/maintenance-rules Skill

    46★ repo

    Skill engineering methodology and publishing pipeline for AI agent skills. Validates structure, scans for security, audits entire projects, and publishes to GitHub. Skills are code — engineer them like it.

  • Media publish check

    XshuiAi/media-publish-check Skill

    46★

    自媒体发布审核 Skill｜Pre-publish audit for Douyin, Xiaohongshu, Weixin Video Accounts & Kuaishou.

  • Claude code eyes

    fcavalcantirj/claude-code-eyes Skill

    43★

    Give Claude Code eyes 👁️ — a camera skill so it can SEE real hardware, displays and wiring: verify a rendered panel, check wiring before power-on, and catch bugs that live on the glass, not the logs.

  • Verification

    Aurite-ai/agent-verifier/skills/verification Skill

    43★ repo

    Agent Verifier is a coding agent skill that verifies code against organizational policies, code quality patterns, security requirements, and framework best practices — before code ships. Works with Claude Code, Cursor, Windsurf, and 30+ agents.

  • A11y check

    haabe/mycelium/plugins/mycelium/skills/a11y-check Skill

    42★ repo

    AI made building cheap. It didn't make deciding cheap. Mycelium is a Claude Code harness that makes your agent run discovery and weigh evidence before it writes code. It earns the right to start. Built for software, courses, AI tools, and services.

  • 46 orchestrate

    scdenney/open-science-skills/codex/46-orchestrate Skill

    no license42★ repo

    Agentic skills for Claude Code and Codex, built from published social-science methods sources. Covers experimental design, computational text analysis, manuscript QA, and transparent reporting.

  • Grammar checker vi

    longhang2004/vietnamese-humanizer/skills/grammar-checker-vi Skill

    42★ repo

    Agent Skills and lightweight tools for clearer, more natural Vietnamese writing, translation cleanup, grammar checks, and style consistency.

  • Research collaborator

    saidwivedi/research-skills/plugins/research-collaborator/skills/research-collaborator Skill

    40★ repo

    Claude Code skills for AI/ML researchers

  • Content creator

    IJONIS/geo-lint/skills/content-creator Skill

    38★ repo

    The first open-source GEO linter. 92 rules for SEO, GEO, and content quality — built for AI agents to run, read, fix, and re-lint automatically.

  • Git workflow

    netresearch/git-workflow-skill/skills/git-workflow Skill

    no license38★ repo

    Agent Skill for Git workflow best practices - branching, commits, PR workflows | Claude Code compatible

  • Check ticket implementation

    eai-org/agent-toolkit/skills/check-ticket-implementation Skill

    37★ repo

    Minimalistic, project-agnostic skills and rules for AI coding agents

  • Skill check

    olgasafonova/SkillCheck-Free/skills/skill-check Skill

    36★ repo

    Validate Claude Code skills against the agentskills specification (Free tier)

  • X impact checker

    tonkotsuboy/x-impact-checker/skills/x-impact-checker Skill

    35★ repo

    AI agent skill to analyze X (Twitter) posts for viral potential using the actual recommendation algorithm

  • Autonomous common

    zxkane/autonomous-dev-team/skills/autonomous-common Skill

    no license33★ repo

    Turns issues into merged PRs/MRs with zero human intervention — supports GitHub and GitLab, and Claude Code, Codex CLI, Kiro CLI, Antigravitiy CLI, opencode, and other agent CLIs.

  • Audio quality check

    tenequm/skills/skills/audio-quality-check Skill

    32★ repo

    Agent skills for building, shipping, and growing software products

  • Specstory guard

    specstoryai/agent-skills/skills/specstory-guard Skill

    32★ repo

    SpecStory's official collection of agent skills. Summarize, organize and create with `.specstory/history`

  • Ai quality gate

    mustafacagri/ai-quality-gate/io.github.mustafacagri/ai-quality-gate MCP server

    32★ repo

    🚀 Kill the Junior AI Era. 🤖 Level up AI code to automatically Principal standards. 🛡️ Quality Gate ✨

  • Tdd

    Shelpuk-AI-Technology-Consulting/agent-skill-tdd/skills/tdd Skill

    30★ repo

    TDD + requirements workflow skill for AI coding agents (Claude Code, Codex, Antigravity, Cursor, Windsurf, etc.). Part of the Shelpuk agentic suite alongside Serena, Kindly Web Search, and Lad.

  • Ios accessibility validator

    gygantskiyMatilyock/ios-developer-agents/.claude/skills/ios-accessibility-validator Skill

    30★ repo

    AI Agents and Skills for iOS Developers

  • Claude code project

    zebbern/skills/claude-code-project Skill

    no license29★ repo

    High-quality Agent Skills made to perform reliably in real workflows

  • Delegate and verify

    benjaminard/fable-skills/skills/delegate-and-verify Skill

    29★ repo

    A skill library that teaches Claude Opus the working disciplines of Claude Fable 5. Move the checkpoints, not the capacity.

  • Wp admin browser

    mralaminahamed/wp-dev-skills/skills/wp-admin-browser Skill

    27★ repo

    WordPress plugin development skills for AI coding agents — Claude Code, Gemini CLI, Cursor, Windsurf, Cline, Codex, Copilot, opencode, and more

  • Handoff

    arimet/handoff/skills/handoff Skill

    27★ repo

    Claude Code skill that quizzes you on the code Claude wrote — verify you understood it before shipping.

  • DocGuard

    raccioly/docguard/io.github.raccioly/docguard MCP server

    25★ repo

    Deterministic doc-drift detection: guard, score, explain, verify-claims and diagnose MCP tools.

  • Agent acceptance gate

    WenyuChiou/agent-collab-skills/skills/agent-acceptance-gate Skill

    23★ repo

    Claude Code marketplace for multi-agent collaboration — task splitter, output reconciler, adversarial debate, shared memory, acceptance gate. Composes with codex-delegate / gemini-delegate.

  • Flight check

    analystacademy/flight-check Skill

    23★

    Final check for AI-generated slide decks — catches fake sources, AI tells, and other mistakes you don't want in your presentation.

All 7,902 in the catalog