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
Persistent, shared AI memory backed by Notion for MCP-compatible assistants.
A Model Context Protocol (MCP) server that enables AI agents to remotely control Windows, Linux, macOS or anything else that can run a VNC server (don't worry, it's probably fine).
A complete implementation of the Model Context Protocol (MCP) for Haskell, split into two packages:
This is a Model Context Protocol (MCP) server implementation for RetellAI, allowing AI assistants to interact with RetellAI's voice services.
A Model Context Protocol (MCP) server for interacting with Twitter (X) via AI tools. This server allows you to fetch tweets, post tweets, search Twitter, manage followers, and more, all through...
MCP Server for interacting with the Old School RuneScape (OSRS) Wiki API and data files. This server provides tools to search the OSRS Wiki and access game data definitions through the Model Context...
A Gate MCP (Model Context Protocol) server that enables AI agents to interact with the Gate cryptocurrency exchange for market data, trading, and account management.
A Model Context Protocol (MCP) server that exposes your recipes as LLM-readable resources — and lets an LLM like Claude create or update recipes in your Paprika app.
Cuts AI tool costs 40–80% and guards against prompt injection. Stops re-reads, extracts one function vs. whole file, shrinks screenshots 97%.
A simple Model-Context-Protocol (MCP) server for executing bash commands. This project allows you to execute bash commands via an MCP server interface, with all the potential security risks that...
This is an that runs in Docker and gives AI assistants (like Claude, Cursor, or any MCP-compatible client) the ability to generate real Office files on demand.
A Model Context Protocol (MCP) server that exposes Agent Zero's battle-tested code execution capabilities.
Agent Skills
zvm (Zig Version Manager) lets you easily install/upgrade between different versions of Zig.
为纯文本模型"看图“设计更好的视觉工具箱和技能，支持多图理解，图片问答，前端UI还原、GUI 自动化等，并可选无缝接入多个主流agent，直接识别粘贴图片｜ A vision toolkit and skill designed for text-only llms — image Q&A, long-screenshot OCR, frontend UI restoration, and...
This project is under active development and evolving rapidly. Contributions, feedback, and discussions are warmly welcome.
山音超级编剧大师 - 全格式影视编剧 Skill 由 @山音 设计的自然语言驱动编剧 Agent Skill 覆盖 1-3 分钟概念超短片→90 分钟电影长片→多集剧集的全流程剧本创作，一站式搞定人物、大纲、场景、剧本全链路
Screenshot testing is key to validate your app's appearance and functionality. It efficiently detects visual issues and tests the app as users would use it, making it easier to spot problems.
Blossom Carousel is the first carousel library that builds on native browser scrolling instead of replacing it.
橙皮书 (Orange Book) Series · by HuaShu (花叔)
About • How It Works • Documentation • Quickstart • Skills • Templates
vet supports special mode for Agent Skills. Run vet scan --agent-skill to scan an Agent Skill hosted in a GitHub repository.
remocn is a copy-paste component library for building videos in Remotion. Instead of writing every fade, wipe, and kinetic title from scratch, you npx shadcn add a polished primitive into your...
for quasi-experimental designs in Python.
The autonomous research agent that beats Claude Code and Codex by 2.5× on the same compute budget