Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
Drive KiCad schematic, PCB, DRC/ERC, DFM, and manufacturing review from any MCP-capable AI agent.
A Model Context Protocol server that executes commands in the current iTerm session - useful for REPL and CLI assistance
This project is a python server that implements the Model Context Protocol (MCP) for Zotero, giving you access to your Zotero library within AI assistants.
Though I'm fairly confident the overall architecture is sound, and I myself rely on the implementation — so it should work :tm:. But definitely alpha software.
Call MCPs via TypeScript, masquerading as simple TypeScript API. Or package them as cli.
Model Context Protocol server for Cyclops
A Model Context Protocol server for DuckDuckGo Search
Plugin for JADX to integrate MCP server
MCP server for Atlassian tools (Confluence, Jira)
Curated Claude workflow infrastructure. HeyClaude is a file-backed, human-reviewed directory for Claude agents, MCP servers, skills, hooks, commands, tools, prompts, rules, guides, templates, and...
A local MCP server for agent literature work. Original-LaTeX section reads, BibTeX from arXiv metadata, and topic watches. Papers stay on disk. Search is optional.
Most RAG frameworks fall into one of three traps: (1) they require you to ship your data to a cloud API, (2) they hand you 300 building blocks and 0 opinionated defaults, or (3) they bundle RAG as a...
Agent Skills
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。
做企业 AI 视频项目逼出来的工具包 · 411 prompt · 15 模型 · 7 Claude Skill · 14 篇方法论
Autonomous formalization of research-level mathematics in Lean 4
An LLM programming assistant engine built with Go. It provides capabilities via the WebSocket protocol, supporting multi-turn dialogues, tool calling, permission control, and skill extension.
LightClaw: The Real Lightweight AI Assistant
This skill makes an AI agent write in a plain style. The full rules are in SKILL.md.
Heads up: the more agents you run, the more this skill is doing on hard mode — rebuilding context from transcripts every time.
— 基于 Claude Code Agent Teams 的多智能体协作安全分析框架
A community collection of skills for Minis — reusable instruction sets that extend Claude's capabilities with specialized workflows, domain knowledge, and bundled resources.
本项目是一个 Claude Code 插件，通过 SubAgents 和 Skills 实现：
OpenCode, Claude Code, Cursor, OpenClaw and beyond. Search the web with SearXNG, browse with Camofox, bypass protections with CloakBrowser. All self-hosted, free, unlimited.
A portable skill for Claude Code, Codex, Antigravity — or any AI agent — that turns long-form Markdown (plans, specs, system designs, RFCs, runbooks, postmortems, brainstorms, notes) into a single...