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.

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.

  • Onlook26K stars

    The Cursor for Designers • An Open-Source AI-First Design tool • Visually build, style, and edit your React A…

    Trust 90Quality 100design-creative
  • Taste Skill65K stars

    Taste-Skill - gives your AI good taste. stops the AI from generating boring, generic slop

    Trust 91Quality 100development
  • Skills Manage2.1K stars

    Desktop app to manage AI coding agent skills across Claude Code, Cursor, Gemini CLI, Codex, and 20+ platforms…

    Trust 82Quality 93agent-skills

Codex, Claude Code, Cursor

Coding agent skills

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

  • Cc Sdd3.6K stars

    Turn approved specs into long-running autonomous implementation. A minimal, adaptable SDD harness with Agent…

    Trust 84Quality 95agent-skills
  • Persistent file-based planning for AI coding agents and long-running agentic tasks. Crash-proof markdown plan…

    Trust 89Quality 100agent-skills
  • Agent Skills-compatible LLM wiki for Claude Code, Cursor, and Codex. Build a Karpathy-style knowledge base fr…

    Trust 89Quality 97agent-skills

Documents and knowledge

Research and RAG skills

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

  • Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, s…

    Trust 88Quality 100rag-knowledge
  • Graphify91K stars

    AI coding assistant skill (Claude Code, Codex, OpenCode, Cursor, Gemini CLI, and more). Turn any folder of co…

    Trust 87Quality 100rag-knowledge
  • NeverWrite698 stars

    The bastard son between Cursor and Obsidian

    Trust 79Quality 77document-processing

Markets and quant

Finance and trading skills

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

  • Zhengxi Views1.3K stars

    可溯源的郑希(易方达基金经理)投研 Agent Skill——基于他全部公开观点原文 + 有原话佐证的投资方法 + 全市场基金真实数据,能溯源问答、按他框架给基金打分,绝不杜撰。⚠️仅研究学习辅助,不构成投资建议‼️w…

    Trust 84Quality 90data
  • Cookiy AI Skill for AI agents (Claude, Codex, Cursor, OpenClaw) — end-to-end user research: AI interviews, sy…

    Trust 77Quality 78agent-frameworks
  • A set of ready to use Agent Skills for research, science, engineering, analysis, finance and writing.

    Trust 87Quality 100utility

Crawlers and extraction

Web scraping skills

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

  • Html Anything6.7K stars

    ✨ The agentic HTML editor — your local AI agent writes the HTML, you ship it. 🚀 75 Skills × 9 Surfaces (maga…

    Trust 84Quality 100agent-skills
  • Ir Search185 stars

    🇰🇷 한국 정부 지원사업 전수조사 에이전트 스킬 [Claude Code·Codex·agy(Antigravity)·Cursor·Gemini CLI·Grok Build 지원] K-Startup·기…

    Trust 81Quality 89research
  • Ok Skills456 stars

    Curated AI coding agent skills and AGENTS.md playbooks for Codex, Claude Code, Cursor, OpenClaw, and other SK…

    Trust 81Quality 78agent-skills

Slides and decks

PPT and presentation skills

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

  • Open Design83K stars

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

    Trust 91Quality 100agent-skills
  • Skills3.9K stars

    Agent skills for designers and builders using Codex, Claude, Cursor, and other AI coding agents

    Trust 89Quality 100design-creative
  • Baoyu Design2.7K stars

    Run Claude Design locally as an Agent Skill — Cursor, Claude Code & more. Produce polished UI mockups, protot…

    Trust 89Quality 100agent-skills

Images, video, UI

Design and creative skills

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

  • Ru Text171 stars

    Russian text quality plugin for Claude Code, Cowork, Codex CLI, Gemini CLI, Cursor, OpenClaw, and Notion — ty…

    Trust 81Quality 88productivity
  • Styleseed799 stars

    Design engine for Claude Code, Codex & Cursor — teaches design judgment, not just data. 74 rules, 48 componen…

    Trust 82Quality 86development
  • Typeui1.1K stars

    Build better UI with Codex, Claude, Cursor and other AI tools

    Trust 79Quality 88agent-skills

Analysis and pipelines

Data and analytics skills

Data analysis, analytics, ETL, notebooks, databases, tables, charts, and reporting workflows.

  • Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 160,000+ scientists…

    Trust 91Quality 100data-analysis
  • Agent Skills493 stars

    The official Agent Skills for ClickHouse and ClickHouse Cloud

    Trust 84Quality 94data
  • Graphify92K stars

    AI coding assistant skill (Claude Code, Codex, OpenCode, Cursor, Gemini CLI, and more). Turn any folder of co…

    Trust 87Quality 100development

Supply tracks

Build the registry by domain, not just by count.

Coding

Coding and developer agents

246

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

246 quality246 maintained

Research

Research and knowledge work

86

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

86 quality86 maintained

Presentation

Presentation and deck workflows

1

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

1 quality1 maintained

Finance

Finance and quant workflows

13

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

13 quality13 maintained

Marketing

Marketing and growth automation

11

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

11 quality11 maintained

Design

Design and creative production

49

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

49 quality49 maintained

Data

Data, BI, and analytics

31

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

31 quality31 maintained

Legal

Legal, policy, and compliance

11

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

11 quality11 maintained

Education

Education and tutoring

5

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

5 quality5 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

Decision filters

Choose by scenario, quality, and trust signals.

Showing 1-16 of 435 ranked candidates matching "cursor-skills"

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

1

Cursor Rules

VERIFIEDEXCELLENT · 100TRUST · 88SAFE · REVIEWEDRESEARCH

Better AI coding with cursor rules

$ npx skills add PatrickJS/awesome-cursorrules
40.4K stars70 quality88 trustReviewedCursor2mo since pushSafe to try12.5K installs
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 gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario RAG and knowledge

Cursor + CLI · 4 targets

cursor
by PatrickJSDetailsQuick view
2

Awesome Agent Skills

VERIFIEDEXCELLENT · 94TRUST · 84SAFE · REVIEWEDCODING

🤖 精选的 AI Agent Skills 列表,适用于 Cursor、Claude Code、GitHub Copilot 等 AI 编程工具

$ npx skills add JackyST0/awesome-agent-skills
605 stars62 quality84 trustReviewed with permission notesClaude Code + Cursor7d since pushSafe to try
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 gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario Coding agents

Claude Code + Cursor · 4 targets

shell
by JackyST0DetailsQuick view
3

Skills

VERIFIEDEXCELLENT · 88TRUST · 84SAFE · REVIEWEDCODING

Official AMD catalog of AI agent skills. Empower your AI agents with AMD's optimized SW stack.

$ npx skills add amd/skills
162 stars58 quality84 trustReviewedClaude Code + OpenAI Agents7d since pushSafe to try
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 Coding agents

Claude Code + OpenAI Agents · 4 targets

python
by amdDetailsQuick view
4

Goose Skills

STRONG · 76TRUST · 78SAFE · REVIEWEDCODING

Library of GTM skills for Claude Code, Codex, Cursor

$ npx skills add gooseworks-ai/goose-skills
1.0K stars55 quality78 trustReviewed with permission notesClaude Code + OpenAI Agents16d since pushNeeds review
QualitySolid option that is likely worth shortlisting for production workflows.
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

Claude Code + OpenAI Agents · 4 targets

pythonclaude-code
by gooseworks-aiDetailsQuick view
5

Antigravity Awesome Skills

VERIFIEDEXCELLENT · 100TRUST · 86SAFE · REVIEWEDCODING

Installable GitHub library of 1,273+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, an…

$ npx skills add sickn33/antigravity-awesome-skills
43.5K stars77 quality86 trustReviewed with permission notesClaude Code15d 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: License is unclear
Safety gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario Coding agents

Claude Code + CLI · 4 targets

by sickn33DetailsQuick view
6

Marketingskills

VERIFIEDEXCELLENT · 100TRUST · 92SAFE · REVIEWEDCODING

Marketing skills for Claude Code and AI agents. CRO, copywriting, SEO, analytics, and growth engineering.

$ npx skills add coreyhaines31/marketingskills
40.6K stars75 quality92 trustReviewedClaude Code + OpenAI Agents17d 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 gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario Coding agents

Claude Code + OpenAI Agents · 4 targets

javascriptclaude-code
by coreyhaines31DetailsQuick view
7

Andrej Karpathy Skills

VERIFIEDEXCELLENT · 100TRUST · 85SAFE · REVIEWEDCODING

A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

$ npx skills add multica-ai/andrej-karpathy-skills
175.2K stars75 quality85 trustReviewedClaude Code3mo since pushSafe to try
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 gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario Coding agents

Claude Code + CLI · 4 targets

claude-code
by multica-aiDetailsQuick view
8

Awesome Gamedev Agent Skills

VERIFIEDEXCELLENT · 92TRUST · 82SAFE · REVIEWEDCODING

Game-development Agent Skills for AI coding agents: install once and a master router loads the right skill for your engine and task. 66 original, version-pinned skills (…

$ npx skills add gamedev-skills/awesome-gamedev-agent-skills
349 stars61 quality82 trustReviewed with permission notesClaude Code8d since pushSafe to try
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 gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario Coding agents

Claude Code + CLI · 4 targets

python
by gamedev-skillsDetailsQuick view
9

Context Engineering Kit

VERIFIEDEXCELLENT · 96TRUST · 85SAFE · REVIEWEDCODING

Hand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others.

$ npx skills add NeoLabHQ/context-engineering-kit
1.3K stars63 quality85 trustReviewed with permission notesClaude Code + Cursor20d since pushSafe to try
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 gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario Coding agents

Claude Code + Cursor · 4 targets

typescriptclaude-code
by NeoLabHQDetailsQuick view
10

Fallow Skills

VERIFIEDEXCELLENT · 86TRUST · 81SAFE · REVIEWEDCODING

Agent skills for fallow, codebase intelligence for JavaScript and TypeScript. Teaches AI agents how to find unused code, duplication, circular deps, complexity hotspots,…

$ npx skills add fallow-rs/fallow-skills
102 stars56 quality81 trustReviewed with permission notesClaude Code17d since pushSafe to try
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 gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario Coding agents

Claude Code + CLI · 4 targets

shell
by fallow-rsDetailsQuick view
11

Codex Cursor Unlimited

PROMISING · 69TRUST · 74SAFE · REVIEWEDCODING

codex app - AI coding tool for writing, reviewing, and debugging code. Comprehensive guide with setup instructions, feature highlights, and system requirements.

$ npx skills add Gulfsistable/codex-cursor-unlimited
392 stars52 quality74 trustReviewed with permission notesClaude Code + OpenAI Agents2mo since pushNeeds review
QualityUseful candidate, but compare it with alternatives before adopting.
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

Claude Code + OpenAI Agents · 4 targets

code-review
by GulfsistableDetailsQuick view
12

Cc 1c Skills

STRONG · 84TRUST · 77SAFE · REVIEWEDCODING

Набор навыков для AI(ИИ)-агентов (Claude Code, Cursor, Codex и др.), помогающий охватить полный цикл разработки на платформе 1С:Предприятие 8.3. Даёт модели абстракции н…

$ npx skills add Nikolay-Shirokov/cc-1c-skills
496 stars53 quality77 trustReviewed with permission notesClaude Code + OpenAI Agents5d since pushSafe to try
QualitySolid option that is likely worth shortlisting for production workflows.
TrustGood trust signals with a few areas worth checking before rollout.Review: Quality score needs review
Safety gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario Coding agents

Claude Code + OpenAI Agents · 4 targets

pythontesting
by Nikolay-ShirokovDetailsQuick view
13

Amazon Skills

STRONG · 78TRUST · 80SAFE · REVIEWEDCODING

Free AI agent skills for Amazon sellers— keyword research, competitor analysis, listing audit & more. Works with OpenClaw, Claude Code, Cursor, Windsurf, Codex and any a…

$ npx skills add nexscope-ai/Amazon-Skills
435 stars52 quality80 trustReviewedClaude Code + OpenAI Agents11d since pushSafe to try
QualitySolid option that is likely worth shortlisting for production workflows.
TrustGood trust signals with a few areas worth checking before rollout.Review: Quality score needs review
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario Coding agents

Claude Code + OpenAI Agents · 4 targets

pythonclaude-code
by nexscope-aiDetailsQuick view
14

Lazyskills

VERIFIEDEXCELLENT · 88TRUST · 79SAFE · REVIEWEDCODING

mission control for agent skills

$ npx skills add alvinunreal/lazyskills
201 stars57 quality79 trustReviewed with permission notesClaude Code18d since pushSafe to try
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 gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario Coding agents

Claude Code + CLI · 4 targets

go
by alvinunrealDetailsQuick view
15

Nori Skillsets

VERIFIEDEXCELLENT · 88TRUST · 82SAFE · REVIEWEDCODING

System for managing collections of agent skills. Switch between skillsets seamlessly!

$ npx skills add tilework-tech/nori-skillsets
148 stars58 quality82 trustReviewed with permission notesClaude Code11d since pushSafe to try
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 gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario Coding agents

Claude Code + CLI · 4 targets

typescript
by tilework-techDetailsQuick view
16

Styleseed

EXCELLENT · 86TRUST · 82SAFE · REVIEWEDCODING

Design engine for Claude Code, Codex & Cursor — teaches design judgment, not just data. 74 rules, 48 components, 7 brand skins (Toss/Stripe/Linear/Notion/Raycast/Arc/Ver…

$ npx skills add bitjaru/styleseed
799 stars54 quality82 trustReviewedClaude Code + OpenAI Agents14d since pushSafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustGood trust signals with a few areas worth checking before rollout.Review: Quality score needs review
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario Coding agents

Claude Code + OpenAI Agents · 4 targets

typescriptclaude-code
by bitjaruDetailsQuick 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