Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
🚀 Generate executable TypeScript tools from MCP servers with 98% token savings. Progressive loading pattern for AI agents. Production-ready.
A simple MCP server that provides hourly weather forecasts using the AccuWeather API.
Bilibili 视频字幕/弹幕/评论提取 MCP Server — 扫码登录，自动提取字幕/弹幕/评论与元数据，输出结构化 Markdown 供 AI 理解
Build ToolJet apps end-to-end via governed MCP tools and an app-builder skill.
kiro SPEC mode impl by mcp
Connect to MCP servers right from your shell. Plugin for simonw/llm.
可扩展的节点流编辑器与工作流引擎，内置 MCP，支持 AI 自动生成节点与流程。An extensible node-flow editor and workflow engine with built-in MCP, enabling AI-powered generation of nodes and workflows.
An MCP server for semantic code search & navigation that helps AI agents work efficiently without burning through costly tokens.
MCP server for orchestrating Claude Code or Codex sessions via iTerm2 or tmux
The agent never holds a kubeconfig. Every write is policy-checked, human-approved, and traced.
An MCP App for AI-powered video creation. It combines an MCP server with an interactive View — the model writes React/Remotion code, the server compiles it in real-time, and a live video player...
Complete Docker-based AI operations infrastructure: Paperclip, n8n, Supabase, OpenClaw, ruflo, and MCPs
Agent Skills
Spider King 是一套面向 Web 协议恢复、参数还原、挑战链路拆解与纯协议交付的逆向工程 Skill。
A Claude Code Skill that transforms any idea into professional Seedance 2.0 video storyboard prompts.
Multi-platform AI skill pack for generating, reviewing, and refactoring web UI with stronger visual judgment.
LLM agents forget everything between sessions. Context compaction drops critical decisions, cross-session knowledge vanishes, and long conversations push early information out of the window.
Production-ready patterns for React Native development, packaged as a Claude Code plugin. Maintained by Software Mansion.
LightClaw: The Real Lightweight AI Assistant
managed-agents helps teams move AI agents from demos to production with runtime infrastructure for sessions, tools, approvals, sandboxed execution, memory, credential vaults, audit trails, replayable...
This collection of skills grew out of my day-to-day paper-writing workflow and has been iteratively refined over time.
⚠️ 本项目是作者为**而创建的个人学习项目，代码结构和实现均以探索为目的，。 ：网页版 AI 对工具调用的支持参差不齐，稳定性和准确性均有较大局限，距离实用仍有差距。 OpenLink 通过浏览器扩展模拟用户操作来驱动网页 AI，，不适合作为日常 API 调用使用。请合理使用，勿滥用。
An analysis of Moonshot AI's Kimi agent architecture (K2.5 model).
A simple template for creating persistent AI companions that remember you
A skill for AI coding agents that enables full control of Obsidian vaults from the terminal using the official (v1.12+).