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。

A self-contained AI agent skill for accessing China A-share stock data from 15 sources, packaged as a structured Markdown+Python file for Claude Code, Codex, and similar agent runtimes.

8.1K
Stars
81/100
信頼
カテゴリ: finance-quant監査

Your on-phone / mobile AI Agent / Claw, capable of operating terminals and performing a wide range of tasks in the Android world || 你的手机 AI 代理,她可以操作终端,也可以完成 Android 世界的广泛任务

1.9K
Stars
76/100
信頼
カテゴリ: automation監査

ESP-Claw, a "Chat Coding" AI agent framework for IoT devices

1.5K
Stars
80/100
信頼
カテゴリ: agent-frameworks監査

A more beautiful and easier-to-use alternative to OpenClaw. It features a nicer Web UI, built-in IM support, a sandboxed runtime and channel-based team collaboration. Under the hood, it is powered by a Claude Code–based agent.

1.3K
Stars
84/100
信頼
カテゴリ: support-automation監査

14-stage Fusion Pipeline for LLM token compression — reversible compression, AST-aware code analysis, intelligent content routing. Zero LLM inference cost. MIT licensed.

2.2K
Stars
77/100
信頼
カテゴリ: coding-agents監査

A curated registry of reusable Mercury Agent, Open Claw or Hermes Agent skills designed for real developer workflows, persistent memory, and token-efficient execution.

351
Stars
67/100
信頼
カテゴリ: agent-skills監査

A self-hosted AI assistant for academic research — manages your papers, searches literature, tracks deadlines, and answers you on the channels you already use.

292
Stars
70/100
信頼
カテゴリ: research監査

微信4.x自动化机器人:群聊机器人、批量群发(支持文件)、批量设置群公告、聊天记录导出、群管理 | 5分钟上手

633
Stars
69/100
信頼
カテゴリ: automation監査

AI agent with multi-agent orchestration, autonomous cognitive systems, and a full management dashboard

161
Stars
65/100
信頼
カテゴリ: web-automation監査

Agent skill for reading, creating, and editing Korean Hangul Word Processor documents via Claude/Codex.

38
Stars
65/100
信頼
カテゴリ: productivity監査

The open infrastructure for Physical Intelligence. ROSClaw grounds AI agents into the physical world through e-URDF, sandbox safety, capability providers, praxis capture, memory, runtime intervention, and self-evolving skills.

137
Stars
70/100
信頼
カテゴリ: robotics-iot監査

ClawLess — A serverless browser-based runtime for Claw AI Agents powered by WebContainers

512
Stars
70/100
信頼
カテゴリ: agent-frameworks監査