Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
Give Claude on the (claude.ai) and read/edit access to files and a whitelisted shell on your local machine, over HTTPS via Tailscale Funnel, gated by OAuth 2.1. No desktop app, no device install.
Sovereign, encrypted, portable memory for AI agents.
Your digital developer twin — because "explain our setup again" gets old fast.
A library built on top of the MCP TypeScript SDK that makes it easier to implement MCP with auth into your MCP client and/or server.
OpenPets is a native macOS desktop pet for visible agent progress, review prompts, completion states, and lightweight animations across local coding tools.
An MCP server that connects to a Swagger specification and helps an AI to build all the required models to generate a MCP server for that service.
A Stdio MCP server which proxies an SSE MCP server.
Transparent MCP proxy that reduces the token cost of large upstream tool responses for nearly every other MCP server imaginable.
MCP server to enable an LLM to do basic static triage of a PE.
MCP server to extract contents from a PDF file
Shared MCP server for the Upvote.club Public API.
The Open Source Analytics and Visibility Layer for ChatGPT Apps and MCP Apps.
Agent Skills
面向中文用户的 AI 图像提示词工程 Skill。它可以把图片、粗糙想法、短关键词、中文提示词、英文提示词或中英混合输入，转成可直接用于生图工具的高质量提示词。
An agentic web research tool that searches, reads, and synthesizes well-cited answers.
Claude Skill to provide assistance with planning family history and genealogy research projects.
一个专注毕业论文生产的 Claude Code skill，针对中文理工科毕业论文的写作风格调整和内容审校。目标是让论文读起来是有脑子的活人研究生写的。
This repo answers how well can agents use Supabase across various tasks.
OpenClaw skill and helper CLI for generating or editing images through the ChatGPT/Codex backend with local OAuth credentials.
A provider-aware plugin for auto-maintained LLM wikis — based on Andrej Karpathy's LLM Wiki pattern.
Conversation-driven video editing for AI agents. Transcribe raw footage with ElevenLabs Scribe, pack phrase-level transcripts, reason over an EDL, render with ffmpeg, and self-evaluate cut boundaries...
Everything else you see here is just the source code behind that file — you don't need to touch it.
We use Kimi-K2.5 as the MLLM and Z-Image-Turbo / Qwen-Image-2512 as the Generator. We use Sglang to serve MLLM and Diffusers to serve the Generator.
SkillsMP.com • SkillHub • ClawHub • Quick Start • Features • Supported Tools
輸入股票代碼，自動從 Goodinfo.tw 讀取公開財報數據，生成互動式三維財務分析儀表板。