Claude Desktop Руководство установки
Десктопный клиент с поддержкой локальной конфигурации MCP.
MCP Servers
A powerful Python recreation of Claude Code with enhanced real-time visualization, cost management, and Model Context Protocol (MCP) server capabilities.
A Model Context Protocol server that gives an LLM assistant — mail, calendar, people, tasks, drafts and (explicitly gated) sending — speaking EWS natively. No Graph proxy, no Microsoft 365 connector.
An MCP (Model Context Protocol) server that provides Ethereum blockchain data tools via Etherscan's API.
Chrome MCP Server is a Chrome extension-based Model Context Protocol (MCP) server that exposes your Chrome browser functionality to AI assistants like Claude, enabling complex browser automation,...
This project contains Model Context Protocol servers, implemented in Java using the Quarkus MCP server framework.
A Model Context Protocol (MCP) server implementation that provides Google News search capabilities via SerpAPI integration.
Documentation • Prompt Decorators Specification
The official Figma MCP server has only read-only tools. You can use AI Agent in Figma Make. But, it is not convenient to chat in Figma Make and then move result to Figma to continue.
An MCP server that provides safe, read-only access to SQLite databases through Model Context Protocol (MCP).
Remote MCP Servers
A specialized MCP server for Payload CMS 3.0 Validate code, generate templates, and scaffold projects following best practices
MCP is an open protocol that enables AI models to securely interact with local and remote resources through standardized server implementations.
Agent Skills
Distilled design judgment from Claude Design system prompt, packaged as a Claude Code skill.
KY Design to HTML 不是一个 UI 生图 skill。它主要面向已有 UI 截图或设计稿的 HTML/CSS 还原，重点是资产分离、画布适配、截图验证和视觉误差修正。 适用于 Codex / Claude 的 设计截图 转 HTML/CSS skill。
A fast, fallback-aware vision layer for text-first agents.
A Claude Code skill that turns Markdown outlines into interactive, offline mind maps with markmap.js — white-on-dark, searchable (match + ancestors), with a zoom / expand / export toolbar.
基于6个维度（著作、深度采访、表达DNA、他者视角、决策记录、时间线） 共1528行调研素材的深度蒸馏， 提炼6个核心心智模型、8条决策启发式、5种割味造句公式。
AI-orchestrated visual production for Obsidian Canvas. Create presentations, flowcharts, mood boards, knowledge graphs, and galleries with intelligent layout and AI-generated content.
Claude Code plugin that lets Claude drive real Onshape CAD: sketches, extrudes, fillets, mates, parametric iteration via Variable Studios, custom FeatureScript features.
First human cognitive framework integrated into an LLM. Claude learns to detect if you're assessing, deciding, or doing—and responds appropriately.
"你是否也想与先贤对话，无论你想和任何人对话，学习任何人的思维模式，Anyone to Skill都能满足你。现在，你可以直接和马斯克、黄仁勋、孔子对话了。"
Welcome to the repository! This project provides a set of best practices, coding rules, and prompt instructions to guide AI-assisted development, especially with GitHub Copilot and similar tools.
An extension for analyzing and improving AI prompt files. Works with SKILL.md, .agent.md, .instructions.md, and .prompt.md files — providing LLM-powered semantic analysis directly in VS Code.
Terminal UI for NVIDIA Nsight Systems profiles — timeline viewer, kernel navigator, NVTX hierarchy