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
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.
⏰ Last updated: 2026-09-01 05:15 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/skills-tracker | 20 | Python | 2026-09-01 | Real-time tracking of every new GitHub 'skills' repo to capture the AI agent skill ecosystem trend |
| 2 | linny006/claude-code-plugin-tracker | 5 | Python | 2026-09-01 | Live index of Claude Code extensions, hooks, and plugins — refreshed every 15 minutes from GitHub |
| 3 | Win-Hao/caseboard | 0 | JavaScript | 2026-09-01 | Agent skill: pin any topic to an interactive 3D detective evidence board — Vite + three.js, zero image assets, determini |
| 4 | ml4t/skills | 0 | Python | 2026-09-01 | Agent skills for Machine Learning for Algorithmic Trading: leakage-safe quant ML, backtesting, validation, and autonomou |
| 5 | smileynet/teach-me | 2 | GDScript | 2026-09-01 | Learn any topic through AI-generated lessons, diagrams, quizzes, and spaced repetition. |
| 6 | yschimke/compose-ai-tools | 110 | Kotlin | 2026-09-01 | Helping the Agents Compose the Things |
| 7 | civaapple-alt/mini-agent-harness | 1 | Rust | 2026-09-01 | A small native coding-agent harness with bounded tools, streaming REPL, Agent Skills/Plugins, MCP, and OpenAI-compatible |
| 8 | 88lin/computer-repair-skill | 10 | Python | 2026-09-01 | 让 Codex、Claude Code 等 AI Agent 成为你的跨平台电脑维修助手：62 个按需加载的 Playbook，覆盖诊断、清理、性能、网络与安全维护——C 盘爆满、电脑卡顿、流氓软件、应用迁移、数据恢复都能直接问；先取证、再 |
| 9 | githubnext/rig | 12 | TypeScript | 2026-09-01 | Multi Agent Harness as a Skill |
| 10 | xiaotonng/destiny-skill | 0 | Python | 2026-09-01 | 🔮 梅花易数 AI Skill — 三个数字起卦，生成本卦/互卦/动爻/变卦/错卦五重卦象，配一份克制、条件式、可执行的中文决策分析。起卦由确定性脚本完成，模型只负责核对经文与解读。 |
| 11 | avivsinai/skills-marketplace | 2 | Python | 2026-09-01 | Central plugin marketplace for Claude Code and Codex |
| 12 | wardawgmalvicious/agent-config | 2 | PowerShell | 2026-09-01 | Personal Claude Code config — skills, subagents, hooks, and rules for Microsoft Fabric and Power BI workflows on Windows |
| 13 | avivsinai/bitbucket-cli | 197 | Go | 2026-09-01 | Bitbucket CLI with gh-like ergonomics |
| 14 | 0x0w1/jig | 5 | Shell | 2026-09-01 | same cut, every project — repository procedures installed as skills into Claude Code, Codex, and Antigravity, with the r |
| 15 | saramjh/interaction-doctor | 0 | HTML | 2026-09-01 | A conflict matrix for touch gestures. Drag vs scroll, tap vs long-press, and the rest. |
| 16 | syncfusion/blazor-ui-components-skills | 4 | — | 2026-09-01 | The skills guide Blazor development across all hosting models (Server, WASM, Hybrid, Auto) including data grid, chart, s |
| 17 | syncfusion/aspnetcore-ui-components-skills | 0 | — | 2026-09-01 | This repository contains AI Skills of ASPNET Core UI Components |
| 18 | linny006/awesome-agent-skills | 28 | Python | 2026-09-01 | Curated, auto-updated awesome-list of vetted AI agent skills with quality ratings for Claude, GPT, a |
| 19 | ChenLiangyu-sc/codex-monitor-skills | 0 | Python | 2026-09-01 | Deterministic, detached monitoring skills for Codex long-running tasks and Slurm jobs |
| 20 | chriskimjj/agent-extensions | 0 | Python | 2026-09-01 | Agent skills and runtime plugins maintained by Chris A. Kim |
| 21 | AlephAITech/DoubaoWorkGuide | 1 | JavaScript | 2026-09-01 | 豆包工作系统化中文实践指南：教程、真实任务、Skills、连接器、自动化与多 Agent 工作流。 |
| 22 | Marshall-Jimmy/trae-skill-manager | 1 | TypeScript | 2026-09-01 | 桌面端搜索、安装与管理 Agent Skills / MCP Server（Tauri 2 + React + Rust） |
| 23 | CorpusIQ/corpusiq-docs | 18 | HTML | 2026-09-01 | Hermes Agent Production Knowledge Repository — 406+ repos, AI Agent Marketplace, MCP servers, autonomous AI agent patter |
| 24 | TheColliery/.github | 1 | JavaScript | 2026-09-01 | TheColliery — quality tooling for AI coding agents. The series landing page, the shared doctrine (Phoenix-13 hooks + Qua |
| 25 | nradawg/new-business-screen | 0 | — | 2026-09-01 | Agent skill that screens a business idea with conjunctive kill gates, base rates, and a pre-mortem. Refuses to give you |
| 26 | syncfusion/aspnetmvc-ui-components-skills | 0 | — | 2026-09-01 | This repository contains AI Skills of ASPNET MVC UI Components. |
| 27 | TeFuirnever/azhou-ai-hub | 1 | Python | 2026-09-01 | Proof-driven, model-neutral Agent Skills with deterministic gates, reproducible setup, and human-controlled evolution. |
| 28 | sandeepyadav1478/touchstone | 0 | Python | 2026-09-01 | Improves a production agent system by repairing the evals that judge it. Failures are mined into new eval cases, and gat |
| 29 | jeremylongshore/tons-of-skills-marketplace | 2687 | Python | 2026-09-01 | 471 plugins, 3,069 skills, 347 agents for Claude Code. Open-source marketplace at tonsofskills.com with the ccpi CLI pac |
| 30 | github/awesome-copilot | 38490 | JavaScript | 2026-09-01 | Community-contributed instructions, agents, skills, and configurations to help you make the most of GitHub Copilot. |
| 31 | timurgaleev/vibestack | 6 | TypeScript | 2026-09-01 | vibestack is a portable skill pack for AI coding agents. Slash commands like /office-hours, /ship, /investigate, /tdd, / |
| 32 | CherryHQ/cherry-studio | 51315 | TypeScript | 2026-09-01 | AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs |
| 33 | agentskillexchange/skills | 35 | Python | 2026-09-01 | Curated, trusted open catalog of AI agent skills for OpenClaw, Claude Code, Codex, GitHub Copilot, Gemini, Cursor, MCP, |
| 34 | first-fluke/oh-my-agent | 1257 | TypeScript | 2026-09-01 | The multi-agent harness that checks the work: verifies agent runs by artifacts (stop-hook gates, independent judges, app |
| 35 | topoteretes/cognee | 30381 | Python | 2026-09-01 | Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory across sessions |
| 36 | Bateelco/neo4j-agent-toolkit | 0 | HTML | 2026-09-01 | 🚀 Neo4j Knowledge Agents: Next-Gen Cypher Tools 2026 |
| 37 | barotdhrumil21/auravms-agent-plugin | 0 | — | 2026-09-01 | Official AuraVMS agent rules, procurement skill, portable Agent Plugin, and MCP configuration. |
| 38 | Love-Ash/archforge | 5 | Python | 2026-09-01 | The preflight linter for AI-generated PowerPoint: silent font fallback (deep CJK coverage), collisions, off-canvas text, |
| 39 | roc1103/visum-releases | 0 | Shell | 2026-09-01 | |
| 40 | ityaadiii/skills-that-say-i-dont-know | 0 | TypeScript | 2026-09-01 | Nine Claude Skills for evaluating AI systems and the skills you install to do it. Every one has a stated refusal. |
| 41 | akhy/agent-skills | 1 | Shell | 2026-09-01 | LLM agent skills collection |
| 42 | Nick2bad4u/codex-skills | 0 | Python | 2026-09-01 | Personal multi-skill repository for reusable Codex workflows. |
| 43 | andr-ca/agentharness | 1 | Python | 2026-09-01 | Portable engineering policies for coding agents — git, testing, logging, and language conventions written once and refer |
| 44 | MaoyuanYang/foundry | 1 | JavaScript | 2026-09-01 | Foundry — AI-native, spec-driven development suite for coding agents: greenfield (0->1), brownfield takeover, and contin |
| 45 | shimo4228/claude-harness | 2 | Python | 2026-09-01 | Curated, MIT-licensed Agent Skills, subagents & rules from shimo4228's harness — open Agent Skills standard, not Claude- |
| 46 | nexu-io/open-design | 93125 | — | 2026-09-01 | 🎨 Best DeepSeek Harness Design Plugin. The open-source Claude Design alternative. 🖥️ Local-first desktop app. 🖼️ Your co |
| 47 | smorinlabs/agent2linear | 8 | TypeScript | 2026-09-01 | agent2linear is a command-line interface for Linear designed to work seamlessly with both humans and AI agents. Unlike L |
| 48 | Cournot-AI/cournot-skills | 0 | JavaScript | 2026-09-01 | Official Agent Skills for Cournot prediction-market intelligence |
| 49 | kina2711/data-department-agent-skills | 1 | Python | 2026-09-01 | Governed operating system for a complete Data Department: 32 role skills, 809 atomic task contracts, 45 slash commands, |
| 50 | sajeetharan/devglobe | 31 | JavaScript | 2026-09-01 | The open-source talent graph for humans and AI agents. |
| 51 | yht0912/bcm-geo-optimizer | 0 | Python | 2026-09-01 | Outcome-first GEO Skill for verifiable AI citations, recommendations, search visibility, and growth. |
| 52 | zaffnet/whetstone | 1 | Shell | 2026-09-01 | My macOS setup as a chezmoi repo, a Copier template for Python projects, and the skills and hooks I use with Claude Code |
| 53 | zznabil/lean-agent-skill-collection | 1 | PowerShell | 2026-09-01 | Twenty-three compact, vendor-neutral agent skills for engineering, research, communication, documents, experiments, and |
| 54 | 0xc000022070/agentic-flake | 1 | Nix | 2026-09-01 | Composable agent skills and project-scoped environments for Nix. |
| 55 | hamadou-08/roboclaw-reports | 3 | HTML | 2026-09-01 | AI Robotics Demos 2026 - VLM Policies, MCP Skills & HTML Reports |
| 56 | sharith45/atlas-Assistant | 1 | — | 2026-09-01 | Tu asistente personal, directamente en tu ordenador. Habla contigo por voz, gestiona WhatsApp, atiende llamadas, consult |
| 57 | CheshireMew/project-steward | 3 | Python | 2026-09-01 | 一个帮你看懂项目、提前避免返工，并在出问题后从根因修好的项目治理 Skill。 |
| 58 | reem-plus/quiver-compass | 0 | HTML | 2026-09-01 | GTM Research & Competitive AI Toolkit 2026 - Raine Soriano |
| 59 | gurutersesat24/ai-site-forge | 0 | HTML | 2026-09-01 | Ultimate AI Static Site Generator 2026 – Free No-Lock-in Build Tool for Claude & Cursor |
| 60 | mikyan/codearts-agent-plugin-guide | 1 | TypeScript | 2026-09-01 | Community compatibility guides for running agent plugins, skills, hooks, and MCP integrations on Huawei Cloud CodeArts A |
| 61 | Edward0l1/skill-flare-discover | 1 | HTML | 2026-09-01 | Best AI Agent Skill Finder 2026 – Multi-Registry Install & Security Labels |
| 62 | hraness/wrench | 4 | TypeScript | 2026-09-01 | Open-source CLI and TypeScript SDK for precise web capabilities for AI agents: page capture, verified media archives, en |
| 63 | samuelfaj/sam-harness | 0 | Go | 2026-09-01 | Executable development harness for AI coding agents |
| 64 | dotnet/skills | 5307 | C# | 2026-09-01 | Repository for skills to assist AI coding agents with .NET and C# |
| 65 | conorbronsdon/agent-context-os | 15 | Python | 2026-09-01 | Portable, evolving context and workflow layer that works across Claude Code, Codex, Hermes Agent, and other compatible c |
| 66 | builtin-pb/dsh-developer | 2 | JavaScript | 2026-09-01 | The single plugin you need for DSH — develop, audit, isolate, and future-proof DeepSeek Harness plugins. |
| 67 | Abhillashjadhav/PM-agent-OS | 1 | Python | 2026-09-01 | Evidence-aware product-management skills and reviewer agents for discovery, strategy, build, launch, and iteration. |
| 68 | owen-tech-ramblings/pdad-governed-development | 0 | — | 2026-09-01 | Portable agent skill for applying repository policy to software work. |
| 69 | Raymondhou0917/speak-human-tw | 919 | Python | 2026-09-01 | 「說人話」：繁體中文的去 AI 味改寫 skill。抓 38 種 AI 寫作痕跡，順手校正中國用語與半形標點，給 Claude Code / Codex / Cursor 用。 |
| 70 | ak2tx/ceiling-guard | 1 | Python | 2026-09-01 | Local plan-window meter and observe-only watchdog for Claude Code, Codex, and Grok CLI |
| 71 | AlephAITech/.github | 0 | — | 2026-09-01 | AgentWork community profile: real scenarios, reproducible processes, deliverable results, and clear boundaries. |
| 72 | adaltomatos01/perfex-crm-guardrails | 2 | HTML | 2026-09-01 | 9 Hidden Perfex CRM Module Breaking Rules 2026 – Best Developer Safety Checklist |
| 73 | gmomakeshop/agent-skills | 2 | HTML | 2026-09-01 | GMOメイクショップが開発・公開するエージェントスキル集 |
| 74 | CarlLee1983/dbcli | 2 | TypeScript | 2026-09-01 | 🤖 Safe database access for coding agents (Claude Code, Codex, Cursor…) • Permission-gated CLI • PostgreSQL, MySQL, Maria |
| 75 | zenstory-ai/drama-skills | 1436 | Python | 2026-09-01 | AI 短剧/漫剧创作 skill 合集，覆盖剧本、资产、分镜、图片/视频提示词到独立审查全链路，适配 Claude Code 与 Codex。| An AI short-drama skill suite for Claude Code & |
| 76 | kotyasmol/codex-project-hygiene | 0 | Python | 2026-09-01 | Prevent Codex project clutter before it starts with persistent, reviewable AGENTS.md hygiene rules. |
| 77 | tang730125633/huangque-agent-skill | 0 | Python | 2026-09-01 | One Huangque CLI skill for DeepSeek Harness, Codex, OpenClaw, Pi Agent, and MCP |
| 78 | sharma23yash-oss/dalal-street-skills | 0 | Python | 2026-09-01 | Agent skills for Indian markets — NSE/BSE filings, SEBI & RBI regulation, Ind AS, India-calibrated valuation, portfolio |
| 79 | weshopai/weshop-skill-package | 1 | TypeScript | 2026-09-01 | Creative AI Skills for Codex, Claude Code, Cursor, Deepseek harness and any Agent Skills-compatible runtime. |
| 80 | citrolabs/ego-lite | 14531 | JavaScript | 2026-09-01 | The fastest browser for AI agents to run browser automation, built for sharing your logged-in browser state with your AI |
| 81 | vanawaker/youxiake-go | 0 | Python | 2026-09-01 | Query Youxiake (youxiake.com) travel activities & departure availability — an Agent Skills-compatible skill for AI agent |
| 82 | bgutschke/skills | 0 | JavaScript | 2026-09-01 | Personal agent skills for real engineering. |
| 83 | BENZEMA216/awesome-weread | 59 | JavaScript | 2026-09-01 | 基于微信读书官方 Agent Skill 的二创项目精选 · Curated projects built on WeRead's official Agent Skill (released 2026-05-17) |
| 84 | benbenmoss/adversarial-review | 0 | Shell | 2026-09-01 | Local, host-agnostic adversarial code review for Claude Code -- auto-triggers on every prompt and task-list update, patc |
| 85 | steve-piece/token-coupons | 0 | JavaScript | 2026-09-01 | Stop paying for skills your agent never uses. Turn your session history into suggestions that save money and clean up yo |
| 86 | eugenelim/agent-ready-repo | 18 | Python | 2026-09-01 | The complete AI operating model for software teams — from first idea to production. Three peer-supervised loops (discove |
| 87 | slowdini/eval-magic | 1 | Rust | 2026-09-01 | One-stop CLI for running structured skill evals across all agent harnesses |
| 88 | Vincentwei1021/video-talkcraft | 422 | HTML | 2026-09-01 | Agent skill that turns Claude Code / Codex into a motion-design studio for voiceover-driven explainer videos — word-leve |
| 89 | troycheng/cuda-kernel-optimizer | 7 | Python | 2026-09-01 | Evidence-driven CUDA, CUTLASS, Triton and GPU workload optimization for ChatGPT · 使用 ChatGPT 驱动 GPU workload 性能优化 |
| 90 | Peng-Wen/skill-audit | 0 | Python | 2026-09-01 | Audit the Agent Skills installed on your machine for prompt injection, credential theft, spec violations, and context co |
| 91 | KaguraNanaga/format-agent-skill | 1 | Python | 2026-09-01 | 通用文档格式排版 Skill。A document-formatting Agent Skill for any types of documents. |
| 92 | TryWorld2026/paper-algorithm | 25 | Python | 2026-09-01 | 纸上算法 PAPER ALGORITHM · 试界TryWorld 官方 AI 技能合集：口播总入口 koubo、纸上算法出片 paper、AIHOT 选题 topics——一句话到成片的口播视频生产线 |
| 93 | openclaw/crabbox | 1349 | Go | 2026-09-01 | Crabbox: warm a box, sync the diff, run the suite. |
| 94 | A1S4kuR4/A1S4kuR4-skills | 0 | JavaScript | 2026-09-01 | |
| 95 | CTctikki/sufy-image2 | 0 | Python | 2026-09-01 | Agent Skill for LTS4AI SF-gpt-image-2 text-to-image and multi-reference editing |
| 96 | silkyland/seed-ah | 0 | — | 2026-09-01 | Seed fake-but-production-like demo databases with media, demo accounts, and a manifest. |
| 97 | agentlas-ai/Agentlas-OS | 1101 | Python | 2026-09-01 | Agent OS: keep specialist agents in a hub, spin up a temporary orchestrator per task. Local-first, works with any model. |
| 98 | EdbertChan/catstack | 1 | Python | 2026-09-01 | Personal Claude, Cursor, and Codex skills — one install, one source of truth |
| 99 | kylehughes/the-unofficial-swift-programming-language-skill | 46 | Python | 2026-09-01 | The Swift Programming Language, packaged as a Skill for LLMs. |
| 100 | levyflux/codex-skills | 1 | Ruby | 2026-09-01 | Reusable Codex skills for UI design, crypto risk analysis, and smart-contract security |
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.
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.
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)
MIT — see LICENSE.
-
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)