Star200+

AI Agent Skill Repository

AI Agent Skills Directory

Browse reusable skills for Codex, Claude Code, Cursor, finance, research, web scraping, PPT, football analytics, data, marketing, design, and more.

Finance Stock analysisQuant Trading researchSlides PPT generationDocs PDF parsingExtract Web scraping
16
Shown
10
Tracks
48
Targets
Resolve APITask in, selected skill and install plan out.Skills APIMachine-readable shortlist with trust and safety signals.llms.txtA crawler-friendly entry point for agent surfaces.

Browse by scenario

Real skills, grouped by the work your agent needs to finish.

Each directory entry links to real skill pages with GitHub adoption, trust score, install handoff, risk notes, and agent-readable metadata. Use these as starting points when you want a shortlist before asking an agent to install anything.

Design to deployment

Frontend and UI skills

Design direction, Figma implementation, UI review, React performance, browser QA, and safe preview deployments.

  • Material Ui98K stars

    Material UI: Comprehensive React component library that implements Google's Material Design. Free forever.

    Trust 90Quality 100design-creative
  • Dokploy36K stars

    Open Source Alternative to Vercel, Netlify and Heroku.

    Trust 85Quality 100devops
  • Open Design83K stars

    🎨 Local-first, open-source Claude Design alternative. 🖥️ Native desktop app. ⚡ 259+ Skills · ✨ 142+ Design…

    Trust 91Quality 100agent-skills

Codex, Claude Code, Cursor

Coding agent skills

Code review, repo inspection, testing, planning, shipping, and engineering workflows for coding agents.

  • Agent Skills81K stars

    Production-grade engineering skills for AI coding agents.

    Trust 86Quality 100agent-skills
  • Oh My Openagent63K stars

    omo/lazycodex: The coding agent for tokenmaxxers;the one and only agent harness for complex codebases. For yo…

    Trust 87Quality 100agent-frameworks
  • Ponytail86K stars

    Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.

    Trust 91Quality 100agent-skills

Documents and knowledge

Research and RAG skills

Research, recent-events briefings, PDF parsing, markdown conversion, RAG ingestion, and knowledge workflows.

  • Markitdown156K stars

    Python tool for converting files and office documents to Markdown.

    Trust 87Quality 100document-processing
  • PaddleOCR83K stars

    Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bri…

    Trust 89Quality 100document-processing
  • Docling63K stars

    Get your documents ready for gen AI

    Trust 89Quality 100document-processing

Markets and quant

Finance and trading skills

Stock analysis, market research, quant backtesting, financial data, and investment research skills.

  • Daily Stock Analysis52K stars

    LLM驱动的 A/H/美股智能分析：多数据源行情 + 实时新闻 + LLM决策仪表盘 + 多渠道推送，零成本定时运行，纯白嫖. LLM-powered stock analysis system for A/H/US…

    Trust 90Quality 100finance
  • TradingAgents88K stars

    TradingAgents: Multi-Agents LLM Financial Trading Framework

    Trust 88Quality 100finance
  • Freqtrade52K stars

    Free, open source crypto trading bot

    Trust 88Quality 100finance

Crawlers and extraction

Web scraping skills

Crawling, scraping, extraction, browser automation, structured data capture, and website-to-markdown workflows.

  • Firecrawl139K stars

    The API to search, scrape, and interact with the web at scale. 🔥

    Trust 87Quality 100agent-frameworks
  • Scrapy63K stars

    Scrapy, a fast high-level web crawling & scraping framework for Python.

    Trust 88Quality 100web-automation
  • Prettier52K stars

    Prettier is an opinionated code formatter.

    Trust 88Quality 100document-processing

Slides and decks

PPT and presentation skills

Presentation generation, editable PPTX, slide decks, speaker notes, and visual storytelling workflows.

  • Slidev47K stars

    Presentation Slides for Developers

    Trust 88Quality 100document-processing

Prompts, B-roll, explainers

Video creation skills

Video-generation prompts, B-roll, Vox-style explainers, camera direction, captions, and creative-production workflows.

  • MoneyPrinterTurbo89K stars

    利用AI大模型，一键生成高清短视频 Generate short videos with one click using AI LLM.

    Trust 88Quality 100automation
  • Cs Video Courses82K stars

    List of Computer Science courses with video lectures.

    Trust 85Quality 100ml-automation
  • Last30days Skill54K stars

    Agent-led recent-trends research across social, prediction markets, video, code, and the web.

    Trust 91Quality 100research

Images, video, UI

Design and creative skills

Image, video, creative production, UI design, multimodal generation, and visual workflow skills.

  • Ultralytics58K stars

    Ultralytics YOLO 🚀

    Trust 85Quality 100ml-automation
  • Unsloth67K stars

    Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss loca…

    Trust 90Quality 100media-automation
  • Whisper.Cpp51K stars

    Port of OpenAI's Whisper model in C/C++

    Trust 88Quality 100media-automation

Popular directories

AI agent skills libraryA real library of reusable skills with trust, audit, install, and agent metadata.Open source AI agent skillsOpen-source skill candidates filtered by task fit, GitHub quality, and install safety.Best Codex skillsRepo inspection, code review, testing, web data, and safe install workflows for Codex.Best AI agent skills for stock analysisFinance and market research skills with trust, install, and maintenance signals.Best Codex skills for web scrapingCrawler and extraction skills that agents can shortlist before installing.Best Claude Code skills for PDF parsingDocument conversion, table extraction, OCR, and markdown workflows.Best AI agent skills for football analyticsMatch data, scouting, dashboards, and World Cup analytics workflows.OpenAgentSkill vs skills.shCompare task resolution, trust signals, install handoffs, and registry APIs.OpenAgentSkill vs agentskills.ioCompare directories, agent-readable metadata, audits, and discovery workflows.

Supply tracks

Build the registry by domain, not just by count.

Coding

Coding and developer agents

73

Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills.

73 quality73 maintained

Research

Research and knowledge work

33

Deep research, source comparison, literature review, RAG, knowledge search, and reports.

33 quality33 maintained

Presentation

Presentation and deck workflows

0

PPTX generation, HTML slides, pitch decks, speaker notes, and presentation workflow skills.

0 quality0 maintained

Finance

Finance and quant workflows

8

Market data, SEC filings, portfolio analysis, quant research, backtesting, and risk workflows.

8 quality8 maintained

Marketing

Marketing and growth automation

1

SEO, content operations, lead generation, CRM, email automation, analytics, and growth workflows.

1 quality1 maintained

Design

Design and creative production

26

Design assets, images, video, audio, multimodal media, presentation, and creative production skills.

26 quality26 maintained

Data

Data, BI, and analytics

10

CSV, SQL, notebooks, dashboards, data pipelines, BI, ETL, and spreadsheet analysis.

10 quality10 maintained

Legal

Legal, policy, and compliance

2

Contract analysis, privacy, policy review, compliance checks, governance, and document risk review.

2 quality2 maintained

Education

Education and tutoring

4

Tutoring, course generation, quizzes, learning analytics, classrooms, and teaching workflows.

4 quality4 maintained

World Cup

Football and World Cup analytics

2

Football data, World Cup dashboards, xG, match prediction, scouting, and sports analytics.

2 quality2 maintained

High-intent entry points

Start from the task, not a keyword list.

These shortcuts use the same trust, supply, and relevance signals as the registry API, so humans and agents land on a useful shortlist faster.

Agent-readable index
FinanceStock analysisQuantTrading researchSlidesPPT generationDocsPDF parsingExtractWeb scrapingCreativeDesign workflowSportsFootball analytics

Decision filters

Choose by scenario, quality, and trust signals.

Showing 1-16 of 151 ranked candidates matching "coap-protocol"

Best blend of quality, stars, freshness, and agent usage

1

Crawl4AI

EXCELLENT · 100TRUST · 82SAFE · REVIEWEDRESEARCH

Open-source LLM-friendly web crawler and scraper for agent workflows.

$ npx skills add unclecode/crawl4ai
4 agent calls100% success66.0K stars96 quality82 trustReviewedClaude Code + OpenAI Agents2mo since pushSafe to try79.2K installs
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustGood trust signals with a few areas worth checking before rollout.Review: Documentation summary is thin
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario Research agents

Claude Code + OpenAI Agents · 4 targets

codexclaude-codecursor
by unclecodeDetailsQuick view
2

Agent Skills

VERIFIEDEXCELLENT · 100TRUST · 86SAFE · REVIEWEDCODING

Production-grade engineering skills for AI coding agents.

$ npx skills add addyosmani/agent-skills
9 agent calls88.89% success80.6K stars88 quality86 trustReviewed with permission notesClaude Code + Cursor7d since pushSafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/…Review: Documentation summary is thin
Safety gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario Coding agents

Claude Code + Cursor · 4 targets

shellai-agents
by addyosmaniDetailsQuick view
3

Taste Skill: Anti-Slop Frontend

VERIFIEDEXCELLENT · 100TRUST · 94SAFE · VERIFIEDDESIGN

Design and implementation guidance for distinctive landing pages, portfolios, product demos, and purposeful redesigns.

$ npx skills add Leonxlnx/taste-skill --skill design-taste-frontend
65.8K stars94 quality94 trustVerifiedClaude Code + OpenAI Agents13d since pushSafe to try79.0K installs
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/…
Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.

Scenario Design and creative

Claude Code + OpenAI Agents · 4 targets

codexclaude-codecursor
by LeonxlnxDetailsQuick view
4

Frontend Design

VERIFIEDEXCELLENT · 100TRUST · 91SAFE · REVIEWEDDESIGN

Guidance for distinctive, intentional UI design, typography, visual direction, and non-template-like product interfaces.

$ npx skills add anthropics/skills --skill frontend-design
163.1K stars93 quality91 trustReviewedClaude Code + OpenAI Agents17d since pushSafe to try195.7K installs
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.Check: Use is subject to the upstream source terms; review LICENSE.txt before redistri…
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/…Review: Use is subject to the upstream source terms; review LICENSE.txt before redistri…
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario Design and creative

Claude Code + OpenAI Agents · 4 targets

claude-codecodexcursor
by anthropicsDetailsQuick view
5

Webapp Testing

VERIFIEDEXCELLENT · 100TRUST · 90SAFE · REVIEWEDCODING

Use Playwright to interact with and test local web applications, capture screenshots, debug UI behavior, and inspect browser logs.

$ npx skills add anthropics/skills --skill webapp-testing
163.1K stars93 quality90 trustReviewedClaude Code + OpenAI Agents17d since pushSafe to try195.7K installs
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.Check: Use synthetic or approved test data; do not run destructive browser actions wit…
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/…Review: Use synthetic or approved test data; do not run destructive browser actions wit…
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario Testing and QA

Claude Code + OpenAI Agents · 4 targets

claude-codecodexcursorplaywright
by anthropicsDetailsQuick view
6

Vercel React Best Practices

VERIFIEDEXCELLENT · 100TRUST · 94SAFE · VERIFIEDCODING

React and Next.js performance guidance for writing, reviewing, and refactoring production UI code.

$ npx skills add vercel-labs/agent-skills --skill vercel-react-best-practices
29.3K stars93 quality94 trustVerifiedClaude Code + OpenAI Agents13d since pushSafe to try35.1K installs
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/…
Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.

Scenario Coding agents

Claude Code + OpenAI Agents · 4 targets

codexclaude-codecursorreactnext.js
by vercel-labsDetailsQuick view
7

Figma Implement Design

VERIFIEDEXCELLENT · 100TRUST · 91SAFE · REVIEWEDCODING

Translate Figma designs into production-ready UI code with close visual fidelity and component-level detail.

$ npx skills add openai/skills --skill figma-implement-design
24.0K stars92 quality91 trustReviewedClaude Code + OpenAI Agents19d since pushSafe to try28.8K installs
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.Check: Requires access to the intended Figma design and a human visual QA pass.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/…Review: Requires access to the intended Figma design and a human visual QA pass.
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario Coding agents

Claude Code + OpenAI Agents · 4 targets

codexclaude-codecursor
by openaiDetailsQuick view
8

Web Design Guidelines

VERIFIEDEXCELLENT · 100TRUST · 91SAFE · REVIEWEDRESEARCH

Review UI code for web interface guidelines, UX quality, accessibility, and interaction design best practices.

$ npx skills add vercel-labs/agent-skills --skill web-design-guidelines
29.3K stars91 quality91 trustReviewedClaude Code + OpenAI Agents13d since pushSafe to try35.1K installs
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.Check: Use formal accessibility testing for regulated or high-compliance releases.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/…Review: Use formal accessibility testing for regulated or high-compliance releases.
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario Research agents

Claude Code + OpenAI Agents · 4 targets

codexclaude-codecursor
by vercel-labsDetailsQuick view
9

Playwright Browser Skill

VERIFIEDEXCELLENT · 100TRUST · 86SAFE · REVIEWEDCODING

Automate a real browser from the terminal for navigation, form filling, snapshots, screenshots, extraction, and UI-flow debugging.

$ npx skills add openai/skills --skill playwright
24.0K stars91 quality86 trustReviewed with permission notesClaude Code + OpenAI Agents19d since pushSafe to try28.8K installs
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.Check: Browser automation can submit data; confirm the target environment and review a…
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/…Review: Browser automation can submit data; confirm the target environment and review a…
Safety gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario Testing and QA

Claude Code + OpenAI Agents · 4 targets

codexclaude-codecursorplaywright
by openaiDetailsQuick view
10

Canvas Design

VERIFIEDEXCELLENT · 100TRUST · 91SAFE · REVIEWEDDESIGN

Create original visual art, posters, PNG assets, and PDF documents through a clear design philosophy.

$ npx skills add anthropics/skills --skill canvas-design
163.1K stars90 quality91 trustReviewedClaude Code + OpenAI Agents17d since pushSafe to try195.7K installs
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.Check: Create original work; do not use it to imitate living artists or reproduce copy…
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/…Review: Create original work; do not use it to imitate living artists or reproduce copy…
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario Design and creative

Claude Code + OpenAI Agents · 4 targets

claude-codecodexcursor
by anthropicsDetailsQuick view
11

Deploy to Vercel

VERIFIEDEXCELLENT · 100TRUST · 91SAFE · REVIEWEDCODING

Deploy applications and websites to Vercel, including preview deployments and shareable deployment links.

$ npx skills add vercel-labs/agent-skills --skill deploy-to-vercel
29.3K stars90 quality91 trustReviewedClaude Code + OpenAI Agents13d since pushSafe to try35.1K installs
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.Check: Deployment can publish external changes; review the target project and producti…
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/…Review: Deployment can publish external changes; review the target project and producti…
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario Coding agents

Claude Code + OpenAI Agents · 4 targets

codexclaude-codecursorvercel
by vercel-labsDetailsQuick view
12

Anthropic Brand Guidelines

VERIFIEDEXCELLENT · 100TRUST · 91SAFE · REVIEWEDDESIGN

Apply Anthropic official brand colors, typography, and visual standards to appropriate Anthropic-related artifacts.

$ npx skills add anthropics/skills --skill brand-guidelines
163.1K stars86 quality91 trustReviewedClaude Code + OpenAI Agents17d since pushSafe to try195.7K installs
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.Check: Brand guidance is source-specific; do not apply Anthropic identity to unrelated…
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/…Review: Brand guidance is source-specific; do not apply Anthropic identity to unrelated…
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario Design and creative

Claude Code + OpenAI Agents · 4 targets

claude-codecodexcursor
by anthropicsDetailsQuick view
13

Firecrawl

EXCELLENT · 100TRUST · 82SAFE · REVIEWEDRESEARCH

Turn websites into clean markdown or structured data for retrieval and agents.

$ npx skills add mendableai/firecrawl
34.0K stars94 quality82 trustReviewedClaude Code + OpenAI Agents2mo since pushSafe to try40.8K installs
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustGood trust signals with a few areas worth checking before rollout.Review: Documentation summary is thin
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario RAG and knowledge

Claude Code + OpenAI Agents · 4 targets

codexclaude-codecursor
by mendableaiDetailsQuick view
14

MarkItDown

EXCELLENT · 100TRUST · 81SAFE · REVIEWEDRESEARCH

Convert PDFs, Office documents, and web files into clean markdown for agents.

$ npx skills add microsoft/markitdown
80.0K stars93 quality81 trustReviewedClaude Code + OpenAI Agents2mo since pushSafe to try96.0K installs
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustGood trust signals with a few areas worth checking before rollout.Review: Documentation summary is thin
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario Document processing

Claude Code + OpenAI Agents · 4 targets

codexclaude-codecursor
by microsoftDetailsQuick view
15

n8n

EXCELLENT · 100TRUST · 74SAFE · REVIEWEDCODING

Workflow automation for connecting agents to repeated operational tasks.

$ npx skills add n8n-io/n8n
190.0K stars92 quality74 trustReviewed with permission notes2mo since pushNeeds review228.0K installs
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustGood trust signals with a few areas worth checking before rollout.Review: License is unclear
Safety gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario Coding agents

CLI + Codex · 4 targets

apicliagent-workflow
by n8n-ioDetailsQuick view
16

LlamaIndex

EXCELLENT · 100TRUST · 81SAFE · REVIEWEDRESEARCH

Data framework for building RAG and knowledge workflows around agent tasks.

$ npx skills add run-llama/llama_index
42.0K stars91 quality81 trustReviewedClaude Code + OpenAI Agents2mo since pushSafe to try50.4K installs
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustGood trust signals with a few areas worth checking before rollout.Review: Documentation summary is thin
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario RAG and knowledge

Claude Code + OpenAI Agents · 4 targets

pythoncodexclaude-code
by run-llamaDetailsQuick view

Page 1

Showing the strongest 16 results to keep the registry fast for humans and agents. Refine by use case, platform, stars, or search query for a narrower shortlist.

Try the agent resolve API