Claude Desktop Руководство установки
Десктопный клиент с поддержкой локальной конфигурации MCP.
MCP Servers
Universal MCP-Server for your Databases optimized for LLMs and AI-Agents.
Vibe Check is a tool that provides mentor-like feedback to AI Agents, preventing tunnel-vision, over-engineering and reasoning lock-in for complex and long-horizon agent workflows.
This MCP server provides browser automation capabilities through Puppeteer, allowing interaction with both new browser instances and existing Chrome windows.
Agentic RAG for local and self-hosted document search: hybrid retrieval, reranking and multimodal RAG on embedded LanceDB, with Docling parsing and an MCP server
A hands-on workshop, presented at AI Engineering Conference Europe, building a multi-agent AI system with two MCP servers: a and a . Both connected to a harness like Claude Code or Cursor.
A Model Context Protocol (MCP) server that provides tools for interacting with Trello boards.
MCP servers for the UniFi suite of applications, Network, Protect, Access, and Drive
Real-time data — and real trades — for Claude and any AI agent.
vs-punk: ADT to MCP bridge - Vibe code in ABAP / AMDP
Baidu Map MCP Server
A MCP Server for APK Tool (Part of Android Reverse Engineering MCP Suites)
Local-first Apple Health MCP server. Lets AI assistants answer questions about your sleep, workouts, activity and heart data from a local export.
Agent Skills
This repository contains sample prompts and agent instructions for Microsoft Copilot, GitHub Copilot, and Microsoft 365 Copilot.
A personal AI assistant that evolves with you. 8 different types of memory (episodic, semantic, procedural, emotional, prospective, behavioral, narrative, shared) make it truly yours.
CAR is a meta-harness for coding agents (Codex, Hermes, OpenCode, OMP, anything ACP). It is not a coding agent itself. You bring the plan and the agents; CAR coordinates the long-running execution.
A procedural terrain generation engine for use with the Three.js 3D graphics library for the web.
本项目把传统术数相关的 AI skill 拆成可审计、可复用、可逐步扩展的工程模块。目标不是把模型包装成“更会玄学”，而是尽量减少它在排盘、流派口径、步骤顺序和解释链路上的幻觉。
现代化可灵活嵌入的任务面板，支持 Codex、DeepSeek Harness
Linear Chain-of-Thought anchors on whatever it says first. Tree-of-Thought widens the search but still walks a single shared context, so the anchoring persists across branches.
是一个 AI Agent 技能库，收录了一系列可被 Agent 直接调用的结构化技能。每个技能都是独立的、可组合的工作流单元，覆盖信息获取、内容处理、图像工具等场景。
A collection of skills for AI financial analysis.
A Cursor skill that gives the AI agent real UI component knowledge — best practices, layout patterns, and design-system conventions for 60+ interface components — so it generates production-grade UI...
1. 对话 skill 模式：在聊天中按 SKILL.md 约束执行单轮改写；安装本仓库作为 skill 后即可直接使用。 2. 脚本 API 模式：通过 scripts/run_aigc_round.py 执行单轮分段处理，并按需调用外部 OpenAI 兼容接口。 3. Web 模式：启动本地后端和前端页面，在浏览器中完成上传、配置、执行和导出。 4. app：安装app可直接使用
next-1688/1688-customer-opportunity agent skill.