Open source registry

Open source AI agent skills

A ranked shortlist of open-source AI agent skills across coding, research, finance, presentation, data, browser automation, and workflow automation use cases.

Developers and teams looking for reusable open-source capabilities that agents can inspect, compare, and install. Ranked from the OpenAgentSkill index using quality, trust, freshness, adoption, and install readiness.

open source AI agent skillsAI agents
30
Ranked
1.6M
Stars
78
Top trust
19
Agent proven

Search intent

Find open-source AI agent skills with GitHub repositories, license signals, install commands, and audit notes.

These pages are generated from real registry records. The list below is not a generic article; every row links to a skill profile with install, trust, audit, and risk fields.

#1

Agent Skills

115 fitTrust 78Excellent 100Agent Proven 19Audit 91 · Safe to try

Production-grade engineering skills for AI coding agents.

Excellent quality, 88K stars, and a 115 use-case fit score.

Best suited scenario

Inspect source files

88K starsAug 14, 2026 pushStrong shortlistEarly agent signalShellAI Agents
$ npx skills add addyosmani/agent-skills
#2

Reverse Skill

29 fitTrust 88Excellent 100Agent Proven Audit 93 · Safe to try

Reverse Engineering / Authorized Penetration Testing / Security Research Skill Router Pack AI-powered routing + On-demand toolchain bootstrapping + Self-evolving knowledge base Supports Claude Code, Kiro, Cursor, Cline, and other AI coding clients 逆向/渗透/安全技能路由包 - AI 自动路由 + 按需自举工具链 + 自动进化经验库 | 支持 Claude Code / Kiro / Cursor / Cline 等代码 AI 客户端

Excellent quality, 26K stars, and a 29 use-case fit score.

Best suited scenario

Inspect source files

26K starsAug 16, 2026 pushProduction candidateNeeds first agent runPowerShellClaude Code
$ npx skills add zhaoxuya520/reverse-skill
#3

Code Review

28 fitTrust 89Excellent 100Agent Proven Audit 92 · Safe to try

Review a branch or diff against repository standards and the originating spec in two independent analysis passes.

Excellent quality, 169K stars, and a 28 use-case fit score.

Best suited scenario

Inspect source files

169K starsJul 13, 2026 pushProduction candidateNeeds first agent runClaude CodeCodex
$ npx skills add mattpocock/skills --skill code-review
#4

Implement

28 fitTrust 87Excellent 100Agent Proven Audit 90 · Safe to try

Implement work from an approved spec or ticket set, run focused and full tests, invoke code review, and commit the result to the current branch.

Excellent quality, 176K stars, and a 28 use-case fit score.

Best suited scenario

Inspect source files

176K starsJul 17, 2026 pushProduction candidateNeeds first agent runClaude CodeCodex
$ npx skills add mattpocock/skills --skill implement
#5

Codex

28 fitTrust 85Excellent 100Agent Proven Audit 89 · Safe to try

Lightweight coding agent that runs in your terminal

Excellent quality, 91K stars, and a 28 use-case fit score.

Best suited scenario

Inspect source files

91K starsJun 16, 2026 pushStrong shortlistNeeds first agent runRustCoding Agent
$ npx skills add openai/codex
#6

Andrej Karpathy Skills

28 fitTrust 85Excellent 100Agent Proven Audit 87 · Safe to try

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

Excellent quality, 175K stars, and a 28 use-case fit score.

Best suited scenario

Inspect source files

175K starsApr 20, 2026 pushStrong shortlistNeeds first agent runClaude Code
$ npx skills add multica-ai/andrej-karpathy-skills
#7

Design.Md

26 fitTrust 90Excellent 100Agent Proven Audit 93 · Safe to try

A format specification for describing a visual identity to coding agents. DESIGN.md gives agents a persistent, structured understanding of a design system.

Excellent quality, 16K stars, and a 26 use-case fit score.

Best suited scenario

Inspect source files

16K starsJun 15, 2026 pushProduction candidateNeeds first agent runTypeScriptCoding Agent
$ npx skills add google-labs-code/design.md
#8

Cc Connect

26 fitTrust 83Excellent 100Agent Proven Audit 88 · Safe to try

Bridge local AI coding agents (Claude Code, Cursor, Gemini CLI, Codex) to messaging platforms (Feishu/Lark, DingTalk, Slack, Telegram, Discord, LINE, WeChat Work). Chat with your AI dev assistant from anywhere — no public IP required for most platforms.

Excellent quality, 12K stars, and a 26 use-case fit score.

Best suited scenario

Inspect source files

12K starsJun 16, 2026 pushStrong shortlistNeeds first agent runGoCoding Agent
$ npx skills add chenhg5/cc-connect
#9

Webapp Testing

25 fitTrust 87Excellent 100Agent Proven Audit 92 · Safe to try

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

Excellent quality, 171K stars, and a 25 use-case fit score.

Best suited scenario

Navigate pages

171K starsAug 21, 2026 pushProduction candidateNeeds first agent runClaude CodeCodex
$ npx skills add anthropics/skills --skill webapp-testing
#10

Graphify

25 fitTrust 85Excellent 100Agent Proven Audit 90 · Safe to try

A tool that converts codebases, SQL schemas, and other files into queryable knowledge graphs for AI coding assistants.

Excellent quality, 92K stars, and a 25 use-case fit score.

Best suited scenario

Inspect source files

92K starsJul 20, 2026 pushStrong shortlistNeeds first agent runPython
$ npx skills add Graphify-Labs/graphify
#11

Claude Code System Prompts

25 fitTrust 87Excellent 100Agent Proven Audit 91 · Safe to try

All parts of Claude Code's system prompt, 27 builtin tool descriptions, sub agent prompts (Plan/Explore/Task), utility prompts (CLAUDE.md, compact, statusline, magic docs, WebFetch, Bash cmd, security review, agent creation). Updated for each Claude Code version.

Excellent quality, 12K stars, and a 25 use-case fit score.

Best suited scenario

Inspect source files

12K starsJul 6, 2026 pushProduction candidateNeeds first agent runJavaScriptClaude Code
$ npx skills add Piebald-AI/claude-code-system-prompts
#12

Open Design

25 fitTrust 91Excellent 100Agent Proven Audit 94 · Safe to try

🎨 Local-first, open-source Claude Design alternative. 🖥️ Native desktop app. ⚡ 259+ Skills · ✨ 142+ Design Systems 🖼️ Web · desktop · mobile prototypes · slides · images · videos · HyperFrames 📦 Sandboxed preview · HTML/PDF/PPTX/MP4 export 🤖 Claude Code / OpenClaw / Codex / Cursor / OpenCode / Qwen / Copilot / Hermes / Kimi & 17+ CLIs.

Excellent quality, 88K stars, and a 25 use-case fit score.

Best suited scenario

Inspect source files

88K starsAug 17, 2026 pushProduction candidateNeeds first agent runTypeScriptAI Agents
$ npx skills add nexu-io/open-design
#13

Awesome Claude Code

24 fitTrust 87Excellent 100Agent Proven Audit 90 · Safe to try

A curated list of awesome skills, hooks, slash-commands, agent orchestrators, applications, and plugins for Claude Code by Anthropic

Excellent quality, 50K stars, and a 24 use-case fit score.

Best suited scenario

Inspect source files

50K starsJul 11, 2026 pushProduction candidateNeeds first agent runPythonClaude Code
$ npx skills add hesreallyhim/awesome-claude-code
#14

Antigravity Awesome Skills

24 fitTrust 84Excellent 100Agent Proven Audit 89 · Safe to try

A comprehensive library of over 1,273 agentic skills for various AI coding assistants, featuring clear documentation and installation instructions.

Excellent quality, 44K stars, and a 24 use-case fit score.

Best suited scenario

Inspect source files

44K starsJul 18, 2026 pushStrong shortlistNeeds first agent runClaude Code
$ npx skills add sickn33/antigravity-awesome-skills
#15

Marketingskills

24 fitTrust 90Excellent 100Agent Proven Audit 92 · Safe to try

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

Excellent quality, 41K stars, and a 24 use-case fit score.

Best suited scenario

Inspect source files

41K starsJul 16, 2026 pushProduction candidateNeeds first agent runJavaScriptClaude Code
$ npx skills add coreyhaines31/marketingskills
#16

Vercel React Best Practices

24 fitTrust 91Excellent 100Agent Proven Audit 94 · Safe to try

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

Excellent quality, 30K stars, and a 24 use-case fit score.

Best suited scenario

Inspect source files

30K starsAug 22, 2026 pushProduction candidateNeeds first agent runCodexClaude Code
$ npx skills add vercel-labs/agent-skills --skill vercel-react-best-practices
#17

Huashu Design

23 fitTrust 91Excellent 100Agent Proven Audit 94 · Safe to try

Huashu Design · HTML-native design skill for Claude Code · Claude Code 里 HTML 原生的设计 skill · 高保真原型 / 幻灯片 / 动画 + 20 设计哲学 + 5 维评审 + MP4 导出 · Agent-agnostic

Excellent quality, 23K stars, and a 23 use-case fit score.

Best suited scenario

Inspect source files

23K starsAug 13, 2026 pushProduction candidateNeeds first agent runHTMLClaude Code
$ npx skills add alchaincyf/huashu-design
#18

Playwright Browser Skill

23 fitTrust 81Excellent 100Agent Proven Audit 88 · Safe to try

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

Excellent quality, 25K stars, and a 23 use-case fit score.

Best suited scenario

Navigate pages

25K starsJul 14, 2026 pushStrong shortlistNeeds first agent runCodexClaude Code
$ npx skills add openai/skills --skill playwright
#19

Humanizer

23 fitTrust 88Excellent 100Agent Proven Audit 91 · Safe to try

Claude Code skill that removes signs of AI-generated writing from text

Excellent quality, 24K stars, and a 23 use-case fit score.

Best suited scenario

Inspect source files

24K starsJun 7, 2026 pushProduction candidateNeeds first agent runClaude Code
$ npx skills add blader/humanizer
#20

Agentmemory

23 fitTrust 88Excellent 100Agent Proven Audit 91 · Safe to try

#1 Persistent memory for AI coding agents based on real-world benchmarks

Excellent quality, 23K stars, and a 23 use-case fit score.

Best suited scenario

Inspect source files

23K starsJun 15, 2026 pushProduction candidateNeeds first agent runTypeScriptCoding Agent
$ npx skills add rohitg00/agentmemory
#21

Book To Skill

23 fitTrust 91Excellent 100Agent Proven Audit 94 · Safe to try

Turn any technical book PDF into a Claude Code skill — ready to study, reference, and use while you work.

Excellent quality, 21K stars, and a 23 use-case fit score.

Best suited scenario

Inspect source files

21K starsAug 12, 2026 pushProduction candidateNeeds first agent runPythonClaude Code
$ npx skills add virgiliojr94/book-to-skill
#22

Pm Skills

23 fitTrust 89Excellent 100Agent Proven Audit 92 · Safe to try

PM Skills Marketplace: 100+ agentic skills, commands, and plugins — from discovery to strategy, execution, launch, and growth.

Excellent quality, 22K stars, and a 23 use-case fit score.

Best suited scenario

Inspect source files

22K starsJul 3, 2026 pushProduction candidateNeeds first agent runAI AgentsClaude Code
$ npx skills add phuryn/pm-skills
#23

Vibe Kanban

23 fitTrust 87Excellent 100Agent Proven Audit 89 · Safe to try

Get 10X more out of Claude Code, Codex or any coding agent

Excellent quality, 27K stars, and a 23 use-case fit score.

Best suited scenario

Inspect source files

27K starsApr 24, 2026 pushProduction candidateNeeds first agent runRustAI Agents
$ npx skills add BloopAI/vibe-kanban
#24

Cmux

23 fitTrust 83Excellent 100Agent Proven Audit 88 · Safe to try

Ghostty-based macOS terminal with vertical tabs and notifications for AI coding agents

Excellent quality, 22K stars, and a 23 use-case fit score.

Best suited scenario

Inspect source files

22K starsJun 16, 2026 pushStrong shortlistNeeds first agent runSwiftCoding Agent
$ npx skills add manaflow-ai/cmux
#25

Frontend Slides

23 fitTrust 88Excellent 100Agent Proven Audit 91 · Safe to try

Create beautiful slides on the web using a coding agent's frontend skills

Excellent quality, 22K stars, and a 23 use-case fit score.

Best suited scenario

Inspect source files

22K starsJun 13, 2026 pushProduction candidateNeeds first agent runJavaScriptCoding Agent
$ npx skills add zarazhangrui/frontend-slides
#26

Hallmark

23 fitTrust 90Excellent 100Agent Proven Audit 93 · Safe to try

Anti-AI-slop design skill for Claude Code, Cursor, and Codex.

Excellent quality, 20K stars, and a 23 use-case fit score.

Best suited scenario

Inspect source files

20K starsJul 31, 2026 pushProduction candidateNeeds first agent runCSSClaude Code
$ npx skills add Nutlope/hallmark
#27

Herdr

23 fitTrust 82Excellent 97Agent Proven Audit 86 · Needs review

agent multiplexer that lives in your terminal.

Excellent quality, 18K stars, and a 23 use-case fit score.

Best suited scenario

Inspect source files

18K starsJul 19, 2026 pushStrong shortlistNeeds first agent runRustAI Agents
$ npx skills add ogulcancelik/herdr
#28

Illa Builder

23 fitTrust 87Excellent 100Agent Proven Audit 91 · Safe to try

Low-code platform allows you to build business apps, enables you to quickly create internal tools such as dashboard, crud app, admin panel, crm, cms, etc. Supports PostgreSQL, MySQL, Supabase, GraphQL, MongoDB, MSSQL, Rest API, Hugging Face, Redis, etc. Automate workflows with schedule or webhook. Open source Retool.

Excellent quality, 12K stars, and a 23 use-case fit score.

Best suited scenario

Inspect source files

12K starsMay 27, 2026 pushProduction candidateNeeds first agent runTypeScriptDeveloper Tools
$ npx skills add illacloud/illa-builder
#29

Humanlayer

23 fitTrust 86Excellent 96Agent Proven Audit 88 · Safe to try

The best way to get AI coding agents to solve hard problems in complex codebases.

Excellent quality, 11K stars, and a 23 use-case fit score.

Best suited scenario

Inspect source files

11K starsJun 19, 2026 pushProduction candidateNeeds first agent runTypeScriptCoding Agent
$ npx skills add humanlayer/humanlayer
#30

Ccstatusline

23 fitTrust 86Excellent 100Agent Proven Audit 90 · Safe to try

🚀 Beautiful highly customizable statusline for Claude Code CLI with powerline support, themes, and more.

Excellent quality, 11K stars, and a 23 use-case fit score.

Best suited scenario

Inspect source files

11K starsJun 19, 2026 pushProduction candidateNeeds first agent runTypeScriptDeveloper Tools
$ npx skills add sirmalloc/ccstatusline

Selection method

How this list is ranked

OpenAgentSkill scores each candidate against the workflow keywords, then balances fit with GitHub stars, quality signals, trust profile, Agent Proven outcome evidence, maintenance freshness, and whether there is a clear install path.

How does OpenAgentSkill rank open source skills?

The ranking combines workflow fit, quality score, trust profile, GitHub adoption, maintenance freshness, and whether a clear install path exists.

Should I install the top skill immediately?

No. Treat the list as a shortlist, open the skill detail page, inspect the repository and license, then test the install command in a sandbox workflow.

Can my agent consume this ranking through an API?

Yes. Use /api/skills/search with the related task or /api/agent/rankings?slug=best-open-source-ai-agent-skills-skills to fetch ranked skill data.