Awesome Agent Skills
Curated, auto-updated awesome-list of vetted AI agent skills with quality ratings for Claude, GPT, and open-source agents
⭐ Star this repo to bookmark — fresh data every 15 minutes
English · 中文 · 日本語 · 한국어 · Español · Português
💡 What is this?
A living, auto-updated directory of functional AI agent skill repositories, evaluated by agent type, quality, and maintenance status. Unlike static awesome-lists, this project uses GitHub Actions to crawl, test, and rate skills daily, ensuring practitioners find only working, high-quality capabilities.
This list is auto-updated every 15 minutes by a GitHub Actions cron. Each commit reflects a real change in the upstream data source — new items added, expired items removed — so you can rely on what you see being current.
📋 Current Items
⏰ Last updated: 2026-09-06 05:46 UTC
Data source:
GitHub Search APIThe table below is rewritten on every cron tick. Star the repo to bookmark.
| # | Name | ⭐ | Lang | Updated | Description |
|---|---|---|---|---|---|
| 1 | sandbaseai/workbuddy-skill | 1 | Python | 2026-09-06 | 15,000+ public Agent Skills, a provenance-first catalog, and 277 reviewed WorkBuddy packages |
| 2 | linny006/skills-tracker | 20 | Python | 2026-09-06 | Real-time tracking of every new GitHub 'skills' repo to capture the AI agent skill ecosystem trend |
| 3 | linny006/claude-code-plugin-tracker | 5 | Python | 2026-09-06 | Live index of Claude Code extensions, hooks, and plugins — refreshed every 15 minutes from GitHub |
| 4 | tikalk/adlc-team-skills | 132 | Shell | 2026-09-06 | 🐙 ADLC Team Skills — Agentic SDLC for Engineering Teams |
| 5 | amruthpillai/reactive-resume | 42222 | TypeScript | 2026-09-06 | A one-of-a-kind resume builder that keeps your privacy in mind. Completely secure, customizable, portable, open-source a |
| 6 | dkharlanau/agent-ready-web-profile | 0 | JavaScript | 2026-09-06 | Interoperability profile and MCP gateway for agent-ready websites — llms.txt, Agent Skills, WebMCP, MCP, A2A, schemas an |
| 7 | superczach/lunar-gatekeeper-sentinel | 0 | HTML | 2026-09-06 | Lunar Gateway 2026: Agent-Native MCP Security & Governance Hub for AI Workloads |
| 8 | smith-horn/skillsmith | 78 | TypeScript | 2026-09-06 | Shared skills, safe for production. |
| 9 | theeranon/JamesSkills | 0 | Python | 2026-09-06 | 22 agent skills across three plugins for Claude Code, Cursor, Codex and Antigravity. One enforced structural contract pe |
| 10 | hemanshulabs/skills | 1 | JavaScript | 2026-09-06 | AI-powered API traffic profiling and load-testing skill for Claude Code, Cursor, and Codex. Auto-detects routes, runs Au |
| 11 | sandbaseai/awesome-workbuddy | 2 | Python | 2026-09-06 | Community-maintained bilingual directory of Tencent WorkBuddy resources, Skills, MCP servers, workflows, and practical g |
| 12 | m0m0i/gate-oriented-sdd | 0 | Shell | 2026-09-06 | Spec-driven development where the review gate is enforced by a hook, not requested by prose. One plugin for Claude Code |
| 13 | nerymurillohnd/codex-essentials | 1 | TypeScript | 2026-09-06 | Community marketplace for Codex plugins, with schemas, generators, validators, docs, and quality gates for reusable skil |
| 14 | aigorahub/elves | 218 | Python | 2026-09-06 | Autonomous multi-batch development skill for Claude Code and Codex. They work while you sleep. |
| 15 | biletian/zhiyike-connect | 1 | TypeScript | 2026-09-06 | 知一刻公开只读 MCP、Skill 与 RSS 备用镜像 |
| 16 | wuaishare/sharextract | 0 | Python | 2026-09-06 | Protocol-first public share content extractor and Agent Skill for AI chats, social posts, media and web pages. |
| 17 | aks129/HealthClawGuardrails | 30 | Python | 2026-09-06 | Open-source guardrails between AI agents and FHIR clinical data — PHI redaction, immutable audit, step-up auth, tenant i |
| 18 | mzored/SkipHow | 3 | Python | 2026-09-06 | Adaptive virtual CTO for Claude Code and Codex. You own product decisions; the agent owns the technical lifecycle throug |
| 19 | CherryHQ/cherry-studio | 51496 | TypeScript | 2026-09-06 | AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs |
| 20 | kissgyorgy/coding-agents | 13 | TypeScript | 2026-09-06 | Nix packages, skills, extensions for coding-agents (Claude Code, Gemini CLI, Pi Coding Agent, Codex) |
| 21 | mohamoudj6-del/AlterLab-FC-Agent-Playbook | 0 | HTML | 2026-09-06 | AlterLab FC 2026 AI Playbook 🚀 Ultimate Skills & Strategy Guide |
| 22 | tale-project/tale | 25 | TypeScript | 2026-09-06 | The Orchestrator for AI Agents — Connect OpenClaw, Hermes Agent, Claude Code, Codex, Cursor, Gemini CLI, OpenCode, Pi, a |
| 23 | Wayne2Wang/codex-cat-hatcher | 13 | Python | 2026-09-06 | Your cat, by your side in Codex. |
| 24 | aiworkskills/wechat-article-skills | 561 | Python | 2026-09-06 | 微信公众号 AI 运营助手 | 选题、写稿、审稿、排版、配图、发布全流程 Skill，支持 OpenClaw / Claude Code / Cursor / Codex |
| 25 | calebnewtonusc/Chewbacca | 4 | Swift | 2026-09-06 | Turns Claude into the world's best sidekick. Standards, skills, subagents, hooks, MCP, and macOS tools that install them |
| 26 | bolens/agent-skills | 1 | HTML | 2026-09-06 | Personal agent skills for software development, concurrent Git workflows, fleet CI, web interfaces, and Linux homelab op |
| 27 | Sathvikkrishna2520/pev-framework-ts | 1 | HTML | 2026-09-06 | Best Free PEV Harness Plugin 2026 - Claude Code AI Pipeline Tool |
| 28 | AllyJuma1/easel-js-cpu-render-kit | 2 | HTML | 2026-09-06 | 🚀 WebGPU Agent Skill 2026: Build GPU Apps with Easel.js & AI Coding Agents |
| 29 | XDParth/ethos-realignment-toolkit | 0 | HTML | 2026-09-06 | AI Prompt Power Calibrator 2026 – Eliminate Sycophancy in Coding Agent Outputs |
| 30 | tiny-glitch/recipe-timeline | 0 | — | 2026-09-06 | A skill that turns a written recipe into an execution-order cooking timeline. |
| 31 | bonboruyau-dev/html-to-feishu-doc | 0 | Python | 2026-09-06 | 将 HTML 网页/文件转换为飞书云文档：表格、图片上传、大标题层级、完整性回查。WorkBuddy / Claude Code / Codex 通用 Agent Skill。 |
| 32 | cblanquera/chrisai | 1 | JavaScript | 2026-09-06 | Me + LLM = Godly |
| 33 | bonboruyau-dev/wechat-article-to-md | 0 | Python | 2026-09-06 | 抓取微信公众号文章并转换为 Markdown：标题/作者/图片/表格(GFM)/大标题层级，支持 Obsidian。WorkBuddy / Claude Code / Codex 通用 Agent Skill。 |
| 34 | yansfil/sasu | 1 | JavaScript | 2026-09-06 | 사수 (sasu) - the senior who double-checks your coding agent's work. It interviews the tacit knowledge out of your head, p |
| 35 | linny006/awesome-agent-skills | 32 | Python | 2026-09-06 | Curated, auto-updated awesome-list of vetted AI agent skills with quality ratings for Claude, GPT, a |
| 36 | AgentWorkforce/relay | 812 | TypeScript | 2026-09-06 | Real time communication for agents. Wake on message, channels, DMs and actions. Useful for orchestrating agents. |
| 37 | amsbangs1975-collab/unity-shader-agent-canvas | 0 | HTML | 2026-09-06 | Unity Shader Agent Toolkit 2026: AI-Powered GPU Optimization Hub for Mobile & WebGL |
| 38 | a-novel-kit/stack | 1 | Go | 2026-09-06 | Development tools backing a-novel and a-novel-kit. Home of the a-novel CLI and AI skills. |
| 39 | KCNyu/clawock | 14 | Python | 2026-09-06 | AI argues. Code settles. The losses stay on the page. A real HK + US brokerage account run by agents that must debate ev |
| 40 | event4u-app/agent-config | 10 | TypeScript | 2026-09-06 | Every claim machine-checked, including "zero runtime daemon" — governed skills, rules and replayable state. One contract |
| 41 | JKHeadley/instar | 77 | TypeScript | 2026-09-06 | Persistent Claude Code agents with scheduling, sessions, memory, and Telegram. |
| 42 | j7an/superpowers-manager | 0 | TypeScript | 2026-09-06 | Install and update the latest stable obra/superpowers release directly from upstream. Codex supported today. |
| 43 | sakshisantoshthorat/artisan-dev-handbook | 0 | HTML | 2026-09-06 | Top Dev Skill Builder 2026: Master Git Worktrees, Code Reviews & DDD |
| 44 | openclaw/crabbox | 1369 | Go | 2026-09-06 | Crabbox: warm a box, sync the diff, run the suite. |
| 45 | codemistake/human-writing | 0 | PowerShell | 2026-09-06 | Russian-first writing skill for AI agents. Removes AI slop, bureaucratic Russian and chatbot habits without making text |
| 46 | blessings1234/skill-shipyard-pipeline | 3 | HTML | 2026-09-06 | Skill Package 2026: Ultimate AI Skills Deployment Tool – Plugin, ZIP & CI/CD |
| 47 | AlainRic/ralph-wiggum-codex-review-triage | 2 | HTML | 2026-09-06 | Codex Autonomous Objective Loops 2026: AI with Mandatory Review & Verification |
| 48 | zztimur/skill-forge | 1 | Python | 2026-09-06 | Validate, pressure-test, and release-gate SKILL.md packages for OpenAI and portable agent runtimes. |
| 49 | vraj-ai/skills | 4 | JavaScript | 2026-09-06 | Agent skills for running software work as a factory, not a conversation: a four-stage pipeline where no agent reviews it |
| 50 | Kenny27lokku/prompt-integrity-validator | 2 | HTML | 2026-09-06 | Lint Your Prompts, Ship Better Agents – Prompt Refiner 2026 Rule Engine |
| 51 | RedGranite/smartskill | 0 | PowerShell | 2026-09-06 | 给想读懂并长期维护自己项目的人的 Agent Skills：动手前先判断，改代码先画影响面，交付时指出哪段值得完全理解。16 个 skill 按需自选，兼容 Claude Code / Codex / OpenCode / Pi / Her |
| 52 | garibong-labs/openclaw-skills | 3 | JavaScript | 2026-09-06 | OpenClaw skills by Garibong Labs |
| 53 | yinxiaowai/xiaowai-photo-poetic-postcard | 0 | Python | 2026-09-06 | One photo to one poetic postcard. Model-neutral Agent Skill for Codex, Claude Code, WorkBuddy, Dreamina and Doubao. 照片诗意 |
| 54 | JasonColapietro/suede-creator-skills | 130 | JavaScript | 2026-09-06 | 74 open-source Agent Skills for Claude Code and Codex: AI SEO, AEO and GEO, code review with an A-F ship grade, CI gates |
| 55 | 784697524-ux/yishufan-viral-video-replica-workflow | 1 | Python | 2026-09-06 | 内置历史爆款向量案例库，支持新视频拉片、双模型 ASR、Seedance 提示词与分层质量门禁的 Codex Skill |
| 56 | ronhuafeng/skills-release | 0 | Python | 2026-09-06 | Reusable Agent Skills and deterministic engineering harnesses. |
| 57 | thevibeworks/claude-code-docs | 39 | Jupyter Notebook | 2026-09-06 | Everything Anthropic ships for builders, archived and updated 4× daily. 3,900+ files. 12 sources. API, Claude Code, MCP, |
| 58 | UllrAI/VibeSKU-Clips | 1 | — | 2026-09-06 | AI 带货短视频神器：一张商品图，自动产出抖音/快手/小红书/TikTok Shop 卖货短视频 |
| 59 | pedroknigge/orderfield | 0 | Python | 2026-09-06 | Contract kernel for multi-agent software work. The plan lives on disk. Children cannot rewrite it. Close is proof. |
| 60 | yantrikos/yantrikdb-mcp | 24 | Python | 2026-09-06 | Persistent cognitive memory for AI agents — drop-in MCP server for Claude Code, Cursor, Windsurf. Temporal decay, contra |
| 61 | hraness/message-like-me | 0 | TypeScript | 2026-09-06 | A local-first CLI and Agent Skill for studying private messaging history and drafting messages that sound like you. |
| 62 | inkeep/open-knowledge | 4039 | TypeScript | 2026-09-06 | Beautiful, AI-native markdown IDE and LLM wiki |
| 63 | mimukit/skills | 1 | Shell | 2026-09-06 | My personal collection of AI agent skills; the *kit family. Portable, one install away. |
| 64 | TserenTserenov/FMT-exocortex-template | 49 | Shell | 2026-09-06 | Exocortex template: fork & deploy your AI-powered personal knowledge system with Claude Code |
| 65 | belialberu4-oss/exo-harness-ai-pipeline | 116 | HTML | 2026-09-06 | Claude Code AI Pipeline 2026 – PEV Framework Harness Plugin for Developers |
| 66 | Art4/continuous-refactoring | 1 | Python | 2026-09-06 | Agent skill suite for continuous refactoring a code base |
| 67 | qepo17/skills | 0 | Python | 2026-09-06 | Installable Agent Skills for fast and durable end-to-end software development workflows |
| 68 | flop-labs/technocore-chat | 147 | Python | 2026-09-06 | HTTP-native chat and notes for agents whose sandbox only allows webfetch — every write is a plain GET. Runs technocore.c |
| 69 | reticlehq/reticle | 442 | TypeScript | 2026-09-06 | AI agents can generate code, but they still struggle to understand what they build. Reticle gives them runtime perceptio |
| 70 | gilvangonzalez/technical-founding-gtm-toolkit | 4 | HTML | 2026-09-06 | The Complete AI & Technical Founder GTM Toolkit 2026 – Pricing, PLG & Enterprise Sales |
| 71 | vineetu/simple-host | 1 | HTML | 2026-09-06 | Deploy websites to simple-host.app from your coding agent (Claude Code, Codex, Cursor) — one-command install. Static hos |
| 72 | PigeonDan1/paper_claw | 36 | Python | 2026-09-06 | Paper Claw sends personalized daily research digests from arXiv and beyond straight to your inbox, featuring customizabl |
| 73 | Ogabriel-Pro/skill-forge | 1 | HTML | 2026-09-06 | 2026 AI Skills Toolkit for Devs & Creators - 27+ Specialized Tools |
| 74 | Meizu1330/neural-context-archive | 0 | HTML | 2026-09-06 | GitHub Memory Snapshot 2026 – Auto Recall & Prune Project Context Across Sessions |
| 75 | Bateelco/neo4j-agent-toolkit | 0 | HTML | 2026-09-06 | 🚀 Neo4j Knowledge Agents: Next-Gen Cypher Tools 2026 |
| 76 | Marco9442/openclaw-skills | 0 | Python | 2026-09-06 | Automated CC Switch-compatible mirror of openclaw/openclaw skills |
| 77 | abgne/line-dev | 0 | Python | 2026-09-06 | AI agent skills for LINE platform development — Messaging API, Login, LIFF, MINI App, and Notification Messages. |
| 78 | Rick-254/moodle-quizsmith | 0 | HTML | 2026-09-06 | Claude Quiz Engine 2026 - Moodle MCQ Generator for GIFT XML Aiken |
| 79 | hsandhu/serve-avd | 9 | TypeScript | 2026-09-06 | The npx serve of Android Emulators |
| 80 | boonkgim/setup-project | 0 | JavaScript | 2026-09-06 | Agent skill that scaffolds a production-grade full-stack web app on Next.js, GraphQL and Postgres, deployed to Cloudflar |
| 81 | yeyuan98/bioresearcher-skills | 0 | JavaScript | 2026-09-06 | Agent Skills/Plugins/Connectors for biomedical research with the biomcp-ts MCP server. |
| 82 | mizzlelover/communication-science-skill | 0 | HTML | 2026-09-06 | 人类传播与社群增长引擎 | Evidence-aware communication methodology Skill for AI agents: 216 mechanism nodes · 13 platform adapters · |
| 83 | idea2go2go/smartfolder-skill | 13 | Python | 2026-09-06 | A Claude skill that turns a folder into a collaboration knowledge base for you, your AI, and your humans |
| 84 | michaelinghilterra-creator/trajecktory | 4 | JavaScript | 2026-09-06 | Run your entire job search from one local, AI-powered dashboard: find the roles worth your time, tailor for each, work t |
| 85 | kwhi6693-web/photo-abstract-editorial | 96 | Python | 2026-09-06 | Turn photos into source-faithful editorial artworks with an Agent Skill — adaptive layouts, controlled abstraction, and |
| 86 | MincongZhou/fengge-distill | 0 | JavaScript | 2026-09-06 | 把@峰哥亡命天涯 的 559 条微博 + 2440 条≥30赞评论，蒸馏成可复用的「峰哥语体引擎」：串子、蹭子、装颓、被看穿的自我吹嘘。含语料管道(nodejs)、筛选脚本、统计口径。/ Distilling @fengge's Weibo |
| 87 | ashfordeOU/aero-agent-skills | 0 | Python | 2026-09-06 | 🚀 The aerospace knowledge layer for AI agents — 567 verified skills in 85 installable packs across 12 engineering famili |
| 88 | maskshell/solidforge-pi | 0 | Python | 2026-09-06 | A loop-engineering system for AI coding agents, delivered as a Pi package. Converge → specify → implement: parallel TDD |
| 89 | rmusser01/tldw-stuff | 0 | Python | 2026-09-06 | Optional prompts, character packs, Buddy packs, skills, lorebooks, and chatbooks (knowledge packs) for tldw_chatbook and |
| 90 | kantaro4123/illustrator-ai-editing-skill | 0 | TypeScript | 2026-09-06 | Safely edit Adobe Illustrator files with Codex and Claude Code. |
| 91 | Dpro-at/Tel-Agent | 169 | Python | 2026-09-06 | AI phone assistant | open-source |
| 92 | Frankfromfuture/Brizo | 0 | JavaScript | 2026-09-06 | Open browser Use runtime, local bridge, CLI, and AI harness adapters for Brizo. |
| 93 | dereknex/immune-brain | 1 | TypeScript | 2026-09-06 | Deterministic workflow & quality engine for Pi |
| 94 | AoiOTA/Kiss-My-Agent | 1 | Python | 2026-09-06 | A Codex plugin that reduces over-design, hidden failure, and evidence inflation in research engineering. |
| 95 | soycodetrail/ai-skills-workshop | 0 | HTML | 2026-09-06 | AI 技能工坊 · 精选 Agent Skill 合集（绘图/写作/视频）——同步自 soycodetrail.top/skills |
| 96 | nexu-io/open-design | 94314 | TypeScript | 2026-09-06 | 🎨 Best DeepSeek Harness Design Plugin. The open-source Claude Design alternative. 🖥️ Local-first desktop app. 🖼️ Your co |
| 97 | savanna0425/skillhot | 37 | JavaScript | 2026-09-06 | 每天更新的开源 Agent Skills 中文发现站、分类索引与 GitHub 榜单 |
| 98 | cyanseek/dsh-landscape | 7 | JavaScript | 2026-09-06 | Agent-first DeepSeek Harness plugin intelligence: verify existing plugins, identify missing capabilities, and generate b |
| 99 | marcusrbrown/dev-like | 2 | JavaScript | 2026-09-06 | Profile a shop's engineering culture from public sources and install develop-like- agent skills. /dev-like Every |
| 100 | hraness/oh | 0 | TypeScript | 2026-09-06 | open-source tools for agentic research |
🔍 How it works
Every 15 minutes, a GitHub Action runs tracker.py. That script:
- Fetches the latest state from
GitHub Search API. - Diffs against
data/items.json(the previous snapshot). - Rewrites the table above between the
<!-- TRACKER_TABLE_* -->markers. - Commits
feat: +N added, -M removed (timestamp)if anything changed.
No external services. No paid APIs. Just a public data source and a free GitHub Action.
🤝 Contributing
See CONTRIBUTING.md — usually you don't need to: the tracker keeps itself current.
If you spot a data-source bug or want to suggest a new column for the table, open
an issue.
🔗 Related live trackers
If you find this useful, you might also like these other auto-updated trackers from the same maintainer — same mechanism, different upstream:
- trending-claude-skills — What's shipping in Claude Skills this week (
topic:claude-skills) - mcp-servers-live — Live index of newest MCP servers (
topic:mcp-server) - cursor-rules-live — Newest Cursor rules and .cursorrules patterns (
topic:cursor-rules) - claude-code-plugin-tracker — Claude Code plugins and hook configs (
topic:claude-code) - llm-agents-radar — Newest LLM agent frameworks (
topic:llm-agent) - rag-radar — Newest RAG implementations and tools (
topic:rag) - llm-eval-tracker — Newest LLM evaluation tools and benchmarks (
topic:llm-eval) - agent-framework-radar — Newest agent frameworks shipping on GitHub (
topic:agent-framework) - vector-db-live — Newest vector DB projects and integrations (
topic:vector-database) - llmops-radar — Newest LLMOps tooling (observability, deployment) (
topic:llmops) - prompt-tools-live — Newest prompt-engineering tools and prompt repos (
topic:prompt-engineering) - agent-eval-harness — Live benchmark of AI coding agents (
topic:llm-eval) - skills-tracker — Tracking new GitHub 'skills' repos (
topic:agent-skills)
📜 License
MIT — see LICENSE.
More from linny006
-
Awesome Agent Skills — Curated, auto-updated awesome-list of vetted AI agent skills with quality ratings for Claude, GPT, and open-source agents (⭐ 0)
-
Agent Skills Daily Tracker — Real-time tracking of every new GitHub 'skills' repo to capture the AI agent skill ecosystem trend (⭐ 0)
-
Agent Eval Harness — Live, open-source benchmark for comparing AI coding agents on real GitHub issues (⭐ 0)
-
Prompt Tools Live — Live-updating tracker of prompt engineering tools, libraries, and techniques — refreshed every 15 minutes (⭐ 0)
-
LLMOps Radar — Live index of the newest LLMOps tooling — track what's shipping in LLM observability and deployment (⭐ 0)
No comments yet
Be the first to share your take.