Claude Desktop 安装指南
支持本地 MCP 配置的桌面客户端。
MCP Servers
Knowledge graph + MCP tool server for LLM agents with hybrid retrieval, live DB sync, Korean FTS, and memory feedback.
Local academic paper tool MCP server — , multi-source download, AI-powered analysis, citation graph, code-based paper recommendation.
The ngrok alternative with .local domains, a scriptable CLI, and an MCP server for AI agents
A lightweight way to use environment variables in your Cursor MCP server definitions.
A single-binary MCP server that connects Claude Desktop and Claude Code to Microsoft Outlook via the Microsoft Graph API.
combining Claude Code monitoring, Claude Code config management, hooks, agents, and MCP servers in a single 5.8MB binary. 89x faster startup with SQLite cache, 492 tests, 0 clippy warnings.
Self-hosted, agent-native web app and MCP server for your Obsidian-style Markdown vault. Browse, search, and edit notes from a fast UI or from AI agents.
A starting point for Claude Code to Codex collaboration
Battle-tested Odoo knowledge for AI agents, validated against real Odoo v17 instances in CI.
ChatSpatial replaces ad-hoc LLM code generation with . Instead of generating arbitrary scripts, the LLM selects tools and parameters from a curated registry, making spatial transcriptomics workflows...
Spring AI Playground is a cross-platform desktop app for building, testing, validating, and executing MCP tools in a controlled local environment.
MCP server to extract contents from a PDF file
Agent Skills
are modular packages of instructions, resources, and scripts that teach an agent to handle a specialized task. On disk, a skill is just a folder: a SKILL.
A dynamic skills plugin for OpenCode that provides tools for loading and using reusable AI agent skills.
刘润（前微软战略合作总监、润米咨询创始人、《5分钟商学院》主理人）28 年商业写作经验的完整复刻。基于其《我这28年的写作心法》提炼的 8 大心法、3 种结构、SCQA 逻辑势能、5商派 SCA++ 模板、7 种 callout，专为商业长文创作设计。
Built for (trust signals, provenance, staleness), while the rest of the ecosystem still targets v0.1.
-- Actively developed. Core functionality is complete and tested. Breaking changes may occur before v1.0.
Bring your Entire context to your agents with cross-agent skills.
tell your agent to run uvx repren@latest --help and follow the instructions to install repren as a skill. Once installed, it uses repren automatically for bulk refactors and renames. See Agent Use.
公众号 / 小红书 / B站 / 知乎： 空格的键盘 ｜ [email protected]
Let your AI agent find, compare, install, and report outcomes for the right reusable skill automatically.
Point it at a folder of Markdown files and edit your notes from any browser — with a CodeMirror editor, live preview, wikilinks, an interactive graph, full-text search, GitHub sync (incl.
Ship faster. Ship better. Ship with The Agentic Startup .
Hi, I'm — a silicon-based rabbit who documents the open-source skills Veronica created. Veronica has a PhD in Quantitative Sciences, 10+ years across quantitative research, AI, and clinical trials,...