Claude Desktop Руководство установки
Десктопный клиент с поддержкой локальной конфигурации MCP.
MCP Servers
Flagship Model Context Protocol server for generating Product Requirement Documents (PRDs) from codebase context.
MCP server for Minecraft Development
Model Context Protocol server for KiCad on Mac, Windows, and Linux
A Model Context Protocol (MCP) server that provides a standardized interface for AI assistants to interact with a SurrealDB database.
PubNub MCP Model Context Protocol Server for use in Cursor, Windsurf, Claude Desktop, Claude Code and OpenAI Codex and more!
Enterprise MCP server for SQL Server with 20 tools for schema discovery, data operations, and administration.
Asterisk Model Context Protocol (MCP) server.
Bioinformatic MCP server that wraps the most useful functions of the gget library
MCP server for AvaloniaUI
Model Context Protocol server for GraphQL
mem-agent mcp server
TypeScript MCP server for retrieving YouTube transcripts in Claude Desktop, Cursor, Cline, Codex, and other MCP clients
Agent Skills
- 🤝 团队与**达成合作，Supervisor-Skills 正式作为**的核心科研技能完成部署，驱动「」与「」两大官方能力，将本项目沉淀的科研方法论带给亿级用户。 - 🚀 ：新增 paper-writer（证据门控的论文正文写作）、paper-polish（忠于原意的语言润色）、deep-research（综述级文献调研）三个技能；intro-drafter...
A Claude Code plugin that maintains FILETREE.md — a one-line description per file with content hashes for staleness detection.
Point it at an existing site and it finds the generic patterns, the missing states, and the sloppy code, then fixes them in place without rewriting your project.
DeepClause Typescript DML SDK and runtime
of cursor/plugins/pstack — kept in sync for standalone use. See also backnotprop/bro, referenced by the /bro skill below.
A股全栈数据工具包 · 十一层架构 · 54端点 · 19数据源 · 零鉴权 | Full-stack China A-share data toolkit for AI agents — 11 layers, 54 endpoints, 19 sources, zero-auth
Structured workflow packs for AI coding assistants, with built-in conversation memory, project memory, and learning-oriented collaboration patterns.
FTE+AI is an end-to-end program execution framework that guides R&D organizations through the complete journey of vendor replacement—from initial planning through successful cutover and optimization.
AI-native quantitative research framework
Anti-laziness skill for AI agents. Core: the Depth Tree method, which splits a task N layers deep and gives every leaf the full time budget of the whole task, so effort multiplies with depth.
Open-source Environment toolkit of claw-like agents, support task/harness generation and evaluation
Spec docs drift from code, or they bloat every PR. Skeeper picks neither.