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: 2026-08-27 05:45 UTC
Data source:
GitHub Search APIThe table below is rewritten on every cron tick. Star the repo to bookmark.
| # | Name | ⭐ | Lang | Updated | Description |
|---|---|---|---|---|---|
| 1 | linny006/claude-code-plugin-tracker | 5 | Python | 2026-08-27 | Live index of Claude Code extensions, hooks, and plugins — refreshed every 15 minutes from GitHub |
| 2 | partikularwaters/Banka | 2 | Shell | 2026-08-27 | A structurally reliable protocol and skills kit for building AI-assisted projects at the right complexity tier in Claude |
| 3 | TserenTserenov/FMT-exocortex-template | 48 | Shell | 2026-08-27 | Exocortex template: fork & deploy your AI-powered personal knowledge system with Claude Code |
| 4 | arete-aios/aios | 2 | — | 2026-08-27 | An AI operating system you own: five layers, Constitution, Memory, Skills, Tools, Focus. Send this to your AI and it bui |
| 5 | jechiu16/agent-deep-research-trigger | 0 | Python | 2026-08-27 | Portable /deep research agent skill for Claude Code and OpenAI Codex — cost-controlled, evidence-gated, multi-provider, |
| 6 | matt-riley/skill-evaluator | 0 | Go | 2026-08-27 | CLI that automates eval-driven iteration for AI skills: run with/without skill, grade with LLM judge, and benchmark resu |
| 7 | nexu-io/open-design | 91846 | — | 2026-08-27 | 🎨 Best DeepSeek Harness Design Plugin. The open-source Claude Design alternative. 🖥️ Local-first desktop app. 🖼️ Your co |
| 8 | civaapple-alt/mini-agent-harness | 1 | Rust | 2026-08-27 | A small native coding-agent harness with bounded tools, streaming REPL, Agent Skills/Plugins, MCP, and OpenAI-compatible |
| 9 | initlabsai/vibekit | 27 | TypeScript | 2026-08-27 | The agentic stack for Algorand builders. |
| 10 | 0x0w1/jig | 2 | Shell | 2026-08-27 | same cut, every project — repository procedures installed as skills into Claude Code, Codex, and Antigravity, with the r |
| 11 | manavmishra/ZeroSlop | 10 | Python | 2026-08-27 | An open-source skill that finds AI slop in your writing and strips it out without changing the facts, scoring the draft |
| 12 | vibeknow/cli | 6 | Go | 2026-08-27 | Official VibeKnow CLI — turn documents and URLs into professional videos in one command. Built for humans and AI agents, |
| 13 | jeremylongshore/tons-of-skills-marketplace | 2679 | Python | 2026-08-27 | 471 plugins, 3,069 skills, 347 agents for Claude Code. Open-source marketplace at tonsofskills.com with the ccpi CLI pac |
| 14 | skyf0xx/hedgehog | 32 | JavaScript | 2026-08-27 | HEDGEHOG codes Cleaner, Faster and with Fewer Tokens. Hedgehog's AI-driven development builds a task dependency graph fr |
| 15 | zxc663/shisan-xinuo-workflow | 9 | Shell | 2026-08-27 | Progressive engineering-governance Skill for AI coding agents — 11-step gated workflow, 43 rules, 203 pitfall details, t |
| 16 | Vivswan/skills | 1 | TypeScript | 2026-08-27 | Installable, plugin-ready skills that give coding agents disciplined workflows, from code standards and review gates to |
| 17 | Phalegethon/the-agentic-fieldbook | 3 | Python | 2026-08-27 | Independently installable Agent Skills for practical software delivery. |
| 18 | ikaijua/Awesome-AITools | 6153 | Python | 2026-08-27 | Collection of AI-related utilities. Welcome to submit pull requests /收藏AI相关的实用工具，欢迎提交pull requests |
| 19 | NecturaLabs/AgentSkills | 1 | Shell | 2026-08-27 | A curated collection of AI agent skills for Claude Code and other AI assistants |
| 20 | liqinling1994-cloud/master-teacher | 0 | JavaScript | 2026-08-27 | 名师问问：融合课程标准与名师方法论的开源教学设计 Skill | Open-source lesson planning agent skill |
| 21 | LooSung/fuseforge | 0 | Python | 2026-08-27 | Experimental thin full-stack coordinator for Compforge and OOPforge |
| 22 | surendranb/writing-skills | 21 | Python | 2026-08-27 | Procedural writing-style skills for AI agents: official frameworks (plain language, business writing, GOV.UK, AP style, |
| 23 | eugenelim/agent-ready-repo | 17 | Python | 2026-08-27 | The complete AI operating model for software teams — from first idea to production. Three peer-supervised loops (discove |
| 24 | shinpr/codex-workflows | 37 | JavaScript | 2026-08-27 | Development workflows for Codex that keep technical rigor and edge-case handling from becoming product overengineering. |
| 25 | CherryHQ/cherry-studio | 51116 | TypeScript | 2026-08-27 | AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs |
| 26 | alibaba/open-code-review | 21477 | Go | 2026-08-27 | Fast, efficient, battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM A |
| 27 | KCNyu/clawock | 13 | Python | 2026-08-27 | AI argues. Code settles. The losses stay on the page. A real HK + US brokerage account run by agents that must debate ev |
| 28 | GeReV/ghidra-iterative-re | 0 | — | 2026-08-27 | A Claude Code skill for iterative reverse engineering in Ghidra |
| 29 | Sivasuthan9/ai-research-skill | 1 | — | 2026-08-27 | An agent skill for doing AI/ML research as a science — first-principles reasoning, falsifiable hypotheses, discriminativ |
| 30 | MindGoblinStudios/grim-tome | 0 | JavaScript | 2026-08-27 | Grimoire's Tome & The Grim Council. A Prompt Spellbook of /skills. The #1 Coding Wizard 🧙♂️ |
| 31 | qepo17/skills | 0 | Python | 2026-08-27 | Installable Agent Skills for fast and durable end-to-end software development workflows |
| 32 | astroicers/skill-quality-research | 0 | Python | 2026-08-27 | Craft-first quality review for Agent Skill repos — an LLM judges how well a skill is WRITTEN (trigger design, writing qu |
| 33 | flop-labs/technocore-chat | 113 | Python | 2026-08-27 | HTTP-native chat and notes for agents whose sandbox only allows webfetch — every write is a plain GET. Runs technocore.c |
| 34 | sunny-chandel/linkedin-campaign-operator | 0 | Python | 2026-08-27 | Your LinkedIn operating system inside an AI agent — eight open-source Agent Skills for Claude Code and Codex. |
| 35 | paulnsorensen/easy-cheese | 18 | Python | 2026-08-27 | Cheese your code 🧀 — high-quality results as easy as cheese. A portable, harness-agnostic Agent Skills toolkit. |
| 36 | linny006/skills-tracker | 20 | Python | 2026-08-27 | Real-time tracking of every new GitHub 'skills' repo to capture the AI agent skill ecosystem trend |
| 37 | linny006/awesome-agent-skills | 27 | Python | 2026-08-27 | Curated, auto-updated awesome-list of vetted AI agent skills with quality ratings for Claude, GPT, a |
| 38 | GaZmagik/iso-24495 | 154 | TypeScript | 2026-08-27 | ISO 24495 Plain Language skills and Claude Code plugin |
| 39 | artokun/comfyui-mcp | 687 | TypeScript | 2026-08-27 | Local-first, agent-native control plane for ComfyUI — MCP server + sidebar agent that generates images, video & audio, a |
| 40 | Komagon/hermes-production-patterns | 1 | Python | 2026-08-27 | Hermes Production Patterns — 面向 Hermes Agent 的生产级工程模式集。装了 Hermes 却不知道怎么写靠谱的技能？Cron 跑偏没人发现？输出质量全靠肉眼审查？状态全靠脑子记？每条模式都在真实 7× |
| 41 | sandbaseai/cli | 58 | TypeScript | 2026-08-27 | Open-source AI CLI and local MCP server connecting 25 AI clients—including Claude Code, Cursor, Codex, and ChatGPT—to 2, |
| 42 | EricSanchezok/repo-seed | 8 | JavaScript | 2026-08-27 | Seed agent-native, self-governing repos: AGENTS.md, MADR decision logs, deterministic gates & pre-commit hooks. Upgradea |
| 43 | rvdbreemen/adr-kit | 5 | Python | 2026-08-27 | Architecture decisions your AI coding agents actually follow. Ranked ADR retrieval and context injection, deterministic |
| 44 | Banca-Copilot-demo/agentes-sdlc | 0 | — | 2026-08-27 | |
| 45 | openclaw/crabbox | 1335 | Go | 2026-08-27 | Crabbox: warm a box, sync the diff, run the suite. |
| 46 | DanielC000/loom | 7 | JavaScript | 2026-08-27 | Orchestrate a fleet of real Claude Code agents on your Claude subscription, not per-token API bills - local-first. |
| 47 | Itr3k/axiom-relay | 0 | TypeScript | 2026-08-27 | Axiom by Elevated AI — non-custodial routing layer for AI agents. Buy paid x402 APIs and prepare crypto swaps your walle |
| 48 | zaffnet/whetstone | 0 | Shell | 2026-08-27 | My macOS setup as a chezmoi repo, a Copier template for Python projects, and the skills and hooks I use with Claude Code |
| 49 | abaj8494/lambda-agent | 1 | Shell | 2026-08-27 | An agentic Recommender System over your working knowledge: builds an on-disk map from your course PDFs and quizzes you a |
| 50 | imMamdouhaboammar/get-things-done | 1 | Python | 2026-08-27 | Autonomous execution & work modeling engine for AI agents (Claude Code, ChatGPT, Codex, Gemini CLI, Antigravity). Conver |
| 51 | ApparelHub-AI/apparelhub-skills | 0 | Python | 2026-08-27 | AI agent skills for apparelhub |
| 52 | ctxrs/ctx | 1045 | Rust | 2026-08-27 | Instant recall for coding agents. Search the history already on your machine. Git blame, but for agent sessions. |
| 53 | Hubujiu/practical-coding | 2 | Python | 2026-08-27 | A lean, event-driven coding skill for AI agents. Less over-engineering, zero ceremony, surgical diffs, and real evidence |
| 54 | striveh/dsh-plugin-extension-center | 0 | TypeScript | 2026-08-27 | Community Extension Center for DeepSeek Harness: discover and manage Plugins, MCP connections, and Skills with signed ca |
| 55 | ddtcorex/maestro-skills | 3 | JavaScript | 2026-08-27 | Universal AI Agent Development Skills Hub & Cordis Plugin for Govard, Magento 2, Laravel. Works with Claude Code, Codex |
| 56 | TheColliery/.github | 1 | JavaScript | 2026-08-27 | TheColliery — quality tooling for AI coding agents. The series landing page, the shared doctrine (Phoenix-13 hooks + Qua |
| 57 | Tcuzzo/backs-aios-skills | 0 | JavaScript | 2026-08-27 | Agent harness skills: invariants, blind cross-family tribunal grading, red-first testing, and combo plays for any agent. |
| 58 | tt-a1i/archify | 18996 | HTML | 2026-08-27 | Agent skill for beautiful, verifiable architecture, workflow, sequence, data-flow, and lifecycle diagrams—self-contained |
| 59 | xymeow/dont-let-their-designer-know | 0 | HTML | 2026-08-27 | Turn one ordinary-object photo into a six-image English-and-Chinese speculative luxury catalog. Noncommercial Agent Skil |
| 60 | Venkateshvenki404224/shipcraft-skills | 0 | Shell | 2026-08-27 | Four Claude Code agent skills: map large work, slice it into shippable phases, pick the right data structures, deepen th |
| 61 | lsaint/aikito | 41 | Python | 2026-08-27 | Your durable workspace across AI agents. |
| 62 | smith-horn/skillsmith | 77 | TypeScript | 2026-08-27 | Shared skills, safe for production. |
| 63 | githubmofo/TorusGuard | 1 | Python | 2026-08-27 | TorusGuard is a portable AI-agent skill that helps developers build secure-by-default web applications. It audits and ha |
| 64 | fy-agent/fyagent | 473 | Rust | 2026-08-27 | For You Agent——AI 时代的个人随身数字人格。把你的模型、AI 账号、技能、提示词和工作方式，带到每一个 AI 工具里。 |
| 65 | yotron-ai/yotron-website | 0 | TypeScript | 2026-08-27 | |
| 66 | Anionex/agent-vision-toolkit | 1110 | Python | 2026-08-27 | 为纯文本模型"看图“设计更好的视觉工具箱和技能，支持多图理解，图片问答，前端UI还原、GUI 自动化等，并可选无缝接入多个主流agent，直接识别粘贴图片｜ A vision toolkit and skill designed for t |
| 67 | Bandersnatch0x/design-playbook | 2 | Python | 2026-08-27 | Design I/O plugin for Claude Code & coding agents — declarations + contracts that make UI generation constrained, review |
| 68 | qufei1993/skills-hub | 1205 | Rust | 2026-08-27 | A cross-platform desktop app to manage Agent Skills in one place and sync them to multiple AI coding tools’ global skill |
| 69 | bgutschke/skills | 0 | JavaScript | 2026-08-27 | Personal agent skills for real engineering. |
| 70 | ThinkInAIXYZ/deepchat | 6288 | TypeScript | 2026-08-27 | 🐬DeepChat - A smart assistant that connects powerful AI to your personal world |
| 71 | KMerdan/causal-strategy-lab | 0 | HTML | 2026-08-27 | Evidence-backed causal strategy graphs, reproducible scenario simulation, and interactive what-if labs for Claude Code a |
| 72 | silverstein/minutes | 1455 | Rust | 2026-08-27 | Every meeting, every idea, every voice note, searchable by your AI. Open-source, privacy-first conversation memory layer |
| 73 | Anionex/dsh-vision-toolkit | 835 | TypeScript | 2026-08-27 | [dsh]为纯文本模型设计更强大的视觉工具箱：一行安装使用、粘贴图片直接识别、多张图片问答、截图到前端UI 还原等｜DeepSeek Harness-native integration for agent-vision-toolkit: |
| 74 | CorpusIQ/corpusiq-docs | 18 | HTML | 2026-08-27 | Hermes Agent Production Knowledge Repository — 406+ repos, AI Agent Marketplace, MCP servers, autonomous AI agent patter |
| 75 | 23blocks-OS/ai-maestro | 759 | TypeScript | 2026-08-27 | AI Agent Orchestrator with Skills System - Give AI Agents superpowers: memory search, code graph queries, agent-to-agent |
| 76 | luxueliu/luxueliu-agent-discipline-skills | 0 | JavaScript | 2026-08-27 | AI 不缺聪明，缺纪律！交付前自检（没从磁盘回读不算完成）/跑偏纠偏（一句「你偏了」就停）/系统化调试（同一个修复猜三次不收敛时用）/多 agent 接力（防旧状态盖掉新写入）——4 个单文件技能零依赖，每条都来自真实翻车事故，DeepSe |
| 77 | candorsystems/candor-finance | 2 | — | 2026-08-27 | Official Candor finance skills and agent package |
| 78 | Elnora-AI/elnora-plugins | 4 | — | 2026-08-27 | Elnora AI plugins marketplace — universal Agent Skills + MCP for bioprotocol generation |
| 79 | sajeetharan/devglobe | 32 | JavaScript | 2026-08-27 | The discovery layer for the agentic web: connecting developers and AI agents to build together |
| 80 | khaoss85/agent-crm | 2 | JavaScript | 2026-08-27 | Agent-native CRM framework for Claude Code, Codex and Gemini CLI. Author custom CRM and Customer Hub source with determi |
| 81 | idaibin/skills | 6 | Python | 2026-08-27 | Independent Agent Skills for repository analysis, planning, implementation, review, delivery, design, and runtime verifi |
| 82 | 00BROD/drkrm | 0 | Python | 2026-08-27 | The editor between your agent and the image model. Brand kit + budget governor + taste gate. Nothing below the bar leave |
| 83 | SuperMate-Ai/SuperMate-Harness-System | 1 | TypeScript | 2026-08-27 | Give DeepSeek Eyes · 给 DeepSeek 装眼睛 — a DeepSeek Harness (DSH) Skill: local vision models or vision APIs let DeepSeek re |
| 84 | github/awesome-copilot | 38291 | JavaScript | 2026-08-27 | Community-contributed instructions, agents, skills, and configurations to help you make the most of GitHub Copilot. |
| 85 | orqan137/skillroster | 0 | TypeScript | 2026-08-27 | Git-native self-hosted team registry for AI agent skills, peer reviews, and project loadouts |
| 86 | amxv/denju | 1 | Rust | 2026-08-27 | registry and cli to manage, share, autosync, and subscribe to agent skills |
| 87 | SocialYjj/literature-fetch | 1 | Python | 2026-08-27 | 按题目/DOI 查找·查阅·正版下载学术文献 PDF 的 Agent Skill (Claude Code / Codex) · Search, read & download academic paper PDFs by title/DO |
| 88 | agentskillexchange/skills | 34 | Python | 2026-08-27 | Curated, trusted open catalog of AI agent skills for OpenClaw, Claude Code, Codex, GitHub Copilot, Gemini, Cursor, MCP, |
| 89 | koco-co/build-goals | 1 | Python | 2026-08-27 | 𝑺𝒌𝒊𝒍𝒍𝒔 𝒂𝒏𝒅 𝒑𝒍𝒖𝒈𝒊𝒏 𝒕𝒐𝒐𝒍𝒌𝒊𝒕 𝒇𝒐𝒓 𝑯𝒂𝒓𝒏𝒆𝒔𝒔 𝑨𝒈𝒆𝒏𝒕. |
| 90 | sycdan/nosedive | 0 | JavaScript | 2026-08-27 | Perform amazing feats, safely. |
| 91 | XJungit/omdp | 2 | JavaScript | 2026-08-27 | only my DSH plugins — monorepo of DeepSeek Harness plugin bundles |
| 92 | adulari/forge | 8 | Rust | 2026-08-27 | Fast, model-agnostic AI coding harness and CLI in Rust — routes every task to the optimal model for cost × capability. |
| 93 | mzored/SkipHow | 1 | Python | 2026-08-27 | One Agent Skill for product and project work in Codex and Claude Code |
| 94 | Krish-1507/OpenPitStop | 2 | TypeScript | 2026-08-27 | A referee your AI coding agent can't cheat. PitStop scans your repo, seals the evidence, catches agents faking test pass |
| 95 | MiviaLabs/mivia-agent | 1 | Go | 2026-08-27 | A terminal AI agent that actually works on your codebase. Local-first, provider-agnostic, and built for real engineering |
| 96 | ryanduguid/australian-accounting-skills | 1 | Python | 2026-08-27 | Claude Code and Codex skills for Australian public-practice workflows. Not lodgment. |
| 97 | Shilo/pixellab-pip | 19 | Python | 2026-08-27 | Meet PixelLab Pip: a tiny pup who fetches the right PixelLab workflow. He follows human commands to create, edit, and an |
| 98 | techfleetworks/enterprise-software-AI-skills | 0 | Shell | 2026-08-27 | Portable, vendor-neutral engineering agent skills (SKILL.md) for AI coding agents: architecture, OWASP security, test st |
| 99 | wkhori/rap | 0 | Python | 2026-08-27 | Research And Plan — a Claude Code skill that turns a brief into one executable plan |
| 100 | hesreallyhim/awesome-claude-code | 53046 | Python | 2026-08-27 | A hand-picked collection of the finest of resources for the most awesome of agents, Claude Code, the undisputed champion |
🔍 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.