Skill ディレクトリ

AI Agent のための再利用可能な Skill を見つける。

タスクで実際の GitHub Skill を検索し、利用前に Stars、Trust、監査、カテゴリ、インストール経路を確認できます。

すべての推奨は、リポジトリ、監査、インストール経路に明確につながっています。

検索結果: autonomous-agent

英語版ディレクトリ

AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs

50K
Stars
88/100
信頼
カテゴリ: agent-skills監査

Build and run autonomous AI agents for open-ended tasks

186K
Stars
77/100
信頼
カテゴリ: agent-frameworks監査

Autonomous coding agent as an SDK, IDE extension, or CLI assistant.

63K
Stars
77/100
信頼
カテゴリ: coding-agents監査

Fully autonomous AI Agents system capable of performing complex penetration testing tasks

21K
Stars
87/100
信頼
カテゴリ: agent-frameworks監査

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

56K
Stars
87/100
信頼
カテゴリ: agent-frameworks監査

Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free.

35K
Stars
87/100
信頼
カテゴリ: data監査

Run autonomous deep research over web and local sources

28K
Stars
77/100
信頼
カテゴリ: research監査

Core skill set for the OpenClaw autonomous agent platform

46K
Stars
82/100
信頼
カテゴリ: agent-frameworks監査

Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.

16K
Stars
79/100
信頼
カテゴリ: rag-knowledge監査

达尔文.skill —— 一个让你的Skill无限进化的系统:评估→改进→测试→保留或回滚 | Autoresearch-inspired autonomous skill optimization for Claude Code. Evaluate, improve, test, keep or revert.

5.6K
Stars
79/100
信頼
カテゴリ: development監査

Autonomous AI development loop for Claude Code with intelligent exit detection

9.4K
Stars
76/100
信頼
カテゴリ: agent-frameworks監査

PraisonAI 🦞 — Hire a 24/7 AI Workforce. Stop writing boilerplate and start shipping autonomous self-improving agents that research, plan, code, and execute tasks. Deployed in 5 lines of code with built-in memory, RAG, and support for 100+ LLMs.

8.1K
Stars
86/100
信頼
カテゴリ: agent-frameworks監査