Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
██╗ ██╗██╗███████╗██╗ ██████╗ ███╗ ██╗ ██║ ██║██║██╔════╝██║██╔═══██╗████╗ ██║ ██║ ██║██║███████╗██║██║ ██║██╔██╗ ██║ ╚██╗ ██╔╝██║╚════██║██║██║ ██║██║╚██╗██║ ╚████╔╝ ██║███████║██║╚██████╔╝██║...
A defensive MCP server for Claude Desktop / any MCP client — the blue-team counterpart to offensive tooling.
Play Netflix / Apple TV+ / YouTube / Spotify by name. Cast URLs. Multi-room audio. AI concierge. All from your terminal.
Production MCP server for multi-agent AI research. Plan, parallelize, synthesize.
gotoHuman makes it easy to add to AI agents and agentic workflows. A fully-managed async human-in-the-loop workflow with a customizable approval UI.
一个面向 Android 安全测试场景的 MCP Server，聚焦以下能力： - ADB 设备与应用操作自动化 - AAPT APK 信息分析 - JADX 反编译与代码审计支撑 - 静态安全扫描（密钥泄露、弱加密、调试泄露）
A command-line interface for MCP servers. curl for MCP.
An MCP server implementation that provides job search functionality.
Find and call JustOneAPI endpoints from MCP-compatible AI assistants using natural language.
🚀 Try it out · 🌐 Website · 📚 Documentation ·
This project provides examples of how to work with the TCP server in Health Auto Export app for iPhone/iPad.
"If I modify this class, what breaks?" — answered in 3 seconds, grounded in source. Source-grounded: structural facts from C++ source and binary assets.
Agent Skills
v2.0 核心理念： 像张雪峰在直播间跟你聊天——有段子、有金句、有压迫感； 同时每一个数据都标来源、每一个判断都有依据。
Heads up: the more agents you run, the more this skill is doing on hard mode — rebuilding context from transcripts every time.
一个面向社会科学论文写作的 Codex / ChatGPT Skill，用于辅助完成选题诊断、研究问题细化、论文大纲搭建、文献综述规划、文献检索到 Zotero 工作流、草稿评审、章节修订、引用与证据风险检查，以及投稿前检查。
OpenTUI platform reference docs. Covers the Core imperative API, React reconciler, Solid reconciler, layout system, components, keyboard handling, animations, and testing.
纠结跳槽还是留下，AI让你"列优缺点清单"——：反者道之动，不纠结的时候自然就清楚了。
Automatically download books from Anna's Archive and upload them to Google NotebookLM with one command.
A skill catalog that won't let you spend 6 months on a research gap that's already closed, isn't a real contribution, or isn't feasible.
Fable5 구조를 넣은 Sonnet이 Opus와 블라인드 테스트에서 사실상 비겼다!! 그것도 답 1건당 비용 3분의 1로!! Sonnet + Fable 5 structure virtually tied Opus in a blind test — at 1/3 the cost per response. (bench/)
一个 Claude Code skill：把一份参考 Word (.docx) 的排版样式（字体 / 字号 / 缩进 / 行距 / 对齐 / ）**复刻到新内容上。
A collection of skills I use with Claude Code to improve my life in various ways. Designed to pair with an AI-managed Obsidian vault — the skills read from and write to the vault.
Skill packs - BMAD, Spec-Kit, mattpocock/skills - teach your AI coding agent how to build. None of them remember who the client is, what you promised them, or who agreed it was delivered.
Started from a PyMol plugin, towards a comprehensive molecular design assistant.