Cursor インストールガイド
開発者向け MCP サーバーとよく使われる AI コードエディタ。
MCP Servers
Catalog of official Microsoft MCP (Model Context Protocol) server implementations for AI-powered data access and tool integration
Model Context Protocol server for DeepSeek's advanced language models
Public Python SDK, CLI, and MCP server for extracting metadata, text, timed transcripts, media, and supported comments from Douyin, RedNote, Bilibili, and YouTube.
MCP (Model Context Protocol) server for blockchain data interaction through the Bankless API.
Community plugin to control Blender 3D with any LLM of your choice
A Model Context Protocol (MCP) server for Mailgun that gives AI agents a practical, workflow-oriented interface to send email, diagnose deliverability, and manage account operations.
A local-first Model Context Protocol server for reading, searching, and sending through the macOS Messages app.
A powerful Model Context Protocol server for LinkedIn API integration
A unified Model Context Protocol server for MiniMax CLI (mmx)
A Model Context Protocol (MCP) server for ATLAS, a Neo4j-powered task management system for LLM Agents - implementing a three-tier architecture (Projects, Tasks, Knowledge) to manage complex...
Model Context Protocol Server for Komodo 🦎 - Enables AI assistants to interact with Docker containers, deployments, stacks, and servers managed by Komodo.
Chrome DevTools for coding agents
Agent Skills
本仓库是基于 WorkBuddy / Claude Code / Cursor 等 AI Agent 的**。每个 Skill 是一个自包含文件夹，包含 SKILL.md（Agent 执行指令）、README.md（人类文档）、references/（Prompt 参考）和 assets/（模板 HTML）。
这是 codex-windows-fast-patch skill 的公开版本，用于让支持 Agent Skills 的智能体修复 Windows 版 Codex Desktop 更新后常见的功能失效问题。
🌳 A type-safe HTML template engine for Python. Build dynamic web pages using Python components with a React-like approach.
A collection of AI agent skills useful for projects using the Kotlin language. Skills are following the Agent Skills standard, see agentskills.io for more information.
PPT Agent 基于软件工程理念的演示文稿全自动生成框架 English | 中文
a desktop app for getting work done with any model
Building a domain-specific enterprise agent from scratch is complex and requires significant effort: agent and tool orchestration, planning logic, safety and alignment policies, evaluation for...
— This project is in early development. APIs and skill content may change.
The trust layer for agent-to-agent commerce — natural-language mandates, ERC-7710 delegated permissions, x402 payments, escrow, and dispute resolution as one open, catch-all Agent Skill / Claude Code...
Add both Manim skills to your AI agent instantly:
Write a SKILL.md, drop in some evals, and find out — empirically — whether your skill actually makes the model better at the task.
“论文不是把字堆满，而是把项目事实、样文规范、图表截图和 Word 交付一次性闭环。”