热门好用的 Agent Skill 推荐
用于审查、研究、写作和数据分析的可复用智能体工作流。
An Agent Skill for Claude Code, Codex, Cursor, and other compatible agents to use the Jev AI typed decision API.
一个Skill自动化工作流管理平台，它可以把Claude code、openclaw等可复用工作流沉淀成通用 SKILL.md，并选择 Claude、Codex、Hermes 或 OpenClaw 执行，支持自动化、主持主流平台的任何skill，大大解放生产力！
一个用女娲.skill生成的写作风格Skill，参考通俗历史读物作者渤海小吏
A curated collection of Claude Code plugins. Each plugin adds a specialized skill that Claude activates automatically for relevant tasks.
A curated, evidence-led directory of DeepSeek Harness (DSH) plugins: verified loadable extensions, skills, and permission-aware installation guidance.
— consumed by fxmind as the fivem knowledge pack.
A structured, AI-native framework for building scalable content systems.
For the O'Reilly course: Building Secure AI Agents with OpenClaw on AWS
Kimi PPT Skills
A local, AI-powered CLI that lets you chat with free LLMs (via OpenRouter) to edit files, run shell commands, and manage git—all from your terminal.
A toolkit for developers to get the most out of the Box Platform using AI
Can agents use?
A cursor plugin for JFrog
A forkable foundation for version-controlled AI agent behavior.
Ai skills for Frida dynamic instrumentation across Android, iOS, native hooks, agents, and troubleshooting
This repository contains an IBM Bob Skill for use with IBM App Connect Enterprise Toolkit
A collection of prompts used in my daily work
Codex skill and Cities: Skylines 1 mod for API-driven AI city building
A declarative AI agent framework built on RuleGo
A tool-agnostic, orchestrator-agnostic agent-driven development framework. Plain markdown contract, sibling-repo consumption model, works with any AI coding tool.
AiGB Skills: Andrew Gene Brown's USDA Agent Skills
A collection of skills for deploying and benchmarking llm-d. This project follows the anthropics/skills template format.
中央大學商事法課程用教學專案。以《圖解公司法》章節架構為骨幹，結合公司法、證券交易法相關實務案例，供課堂學習、案例討論與同學提交作業使用，同時作為本書未來改版的素材庫。
🔍 Discover + safety-vet Claude Code extensions before you install them - a 0-100 trust score for discovery + a 1-5 static-scan risk verdict, SHA-pinned install. Skills/MCP/plugins/commands.