Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
Arm's MCP server
Your Obsidian vault as LLM-native knowledge base + multi-account Google Workspace (Gmail, Calendar, Drive, Docs, Sheets, Slides) exposed as 25 MCP tools for Claude Code.
The TypeSpec MCP Server implements the MCP specification to enable you to quickly build out your own MCP servers powered by TypeSpec.
Original-SVG-first architectural community design copilot framework with mandatory OpenCrab MCP workflow.
Too many MCP tools slowing your agent down? Might be a Skill Issue 😉
一个基于 mijiaAPI 3.x 的产品化米家 MCP 服务。它不再要求客户端先理解 did、siid/piid/aiid 这些协议细节，而是优先面向“家庭、房间、设备名、场景名”提供更自然的查询和控制能力。
>The most seeable and free way to control Microsof applications by AI model.
Welcome to the Twitter MCP (Multi-Channel Platform) Server! This application helps you manage your Twitter account programmatically with a variety of powerful features.
Commands · MCP Servers · Plugins · Tools · Workflows · Agent Frameworks
MCP server that gives AI assistants direct access to ngspice circuit simulation — design, simulate, and verify circuits through natural language
An MCP server for your API
MCP server for the — 135 tools for managing Facebook & Instagram ad campaigns, audiences, creatives, insights, catalogs, and more.
Agent Skills
Türkçe sunum + LLM-Wiki skill'i. Ham sohbetleri, bir şemayla disipline edilen, aranabilir ve büyüyen bir wiki'ye dönüştürme deseni.
OpenClaw skills that replace a human executive assistant.
Claude Code와 Codex에서 에이전트 시스템 설계, 요구사항 구체화, 세션 마무리, 스킬 자동 최적화를 위한 메타 스킬 모음.
OpenClaw Skill — 微信 AI 个人助手 自动从微信聊天中提取待办、日程、干货，推送到 Discord，闭环追踪任务状态。 念念不忘，必有回响 — Important messages always echo back.
Скилл для AI-агентов: Claude Code, Codex, OpenClaw, Hermes и любых других, читающих SKILL.md. Берёт русский текст после нейросети и убирает всё, по чему его палят: канцелярит, «не просто X, а Y»,...
A Claude Code skill that scans Solidity codebases for security vulnerabilities by referencing 36 unique vulnerability types sourced from smart-contract-vulnerabilities.
是为 Claude Code、Trae 等 AI 客户端设计的专业代码安全审计 Skill。采用白盒静态分析方法论，通过五阶段标准化审计协议，系统性发现和验证源代码中的安全漏洞。
A simple skill you can use to fork your agentic coding tools to a new terminal window. Why? To offload context (delegate), to branch work, to parallelize work, to run the same command against...
A Claude skill for producing self-contained HTML artifacts instead of markdown when the task warrants it.
Orchestrate Claude Code sessions as managed background processes from any OpenClaw channel.
🌐 LangSkills — Evidence-Backed Skills for AI Agents
Install complete Claude Code infrastructure in 30 seconds with automatic framework detection and skill auto-activation.