Cursor Руководство установки
AI-редактор кода, часто используемый с developer MCP.
MCP Servers
🔥 MCP Mastery: Build AI Apps with Claude, LangChain and Ollama
A lightweight way to use environment variables in your Cursor MCP server definitions.
This MCP server provides tools for listing and retrieving content from different knowledge bases.
- — MCP Protocol v2 (spec revision 2026-07-28, streamable HTTP) and experimental StrongDM API support are here — see the release notes.
MCPSafari: Native Safari MCP Server for AI Agents
MCP server to perform various OSINT tasks by leveraging common network reconnaissance tools.
A starting point for Claude Code to Codex collaboration
allows AI to control the Godot Editor to create scenes, nodes, scripts. It can debug script errors, debugger and output logs.
Agent Browser eliminates the need to configure each MCP server in every client. Connect your clients once to Agent Browser, and it will manage all your Server-Sent Events (SSE) MCP servers for you.
移动端 AI 自动化测试平台 —— MCP 工具 + AI Agent + 可视化操控台
MCP server to extract contents from a PDF file
OpenPets is a native macOS desktop pet for visible agent progress, review prompts, completion states, and lightweight animations across local coding tools.
Agent Skills
Fetch WeChat Official Account articles and convert them to clean Markdown.
AI Agent Skills for LibLib.tv — 让你的 AI Agent 轻松调用 LibTV 的生图、生视频等 AIGC 能力。
The trust layer for agent-to-agent commerce — natural-language mandates, ERC-7710 delegated permissions, x402 payments, escrow, and dispute resolution as one open, catch-all Agent Skill / Claude Code...
Generative AI can make mistakes. You should consider reviewing all output and costs generated by your chosen AI model and agentic coding assistant. See AWS Responsible AI Policy.
A curated collection of reusable Agent Skills for Warp AI agents and Oz.
Welcome to , a repository of specialized "brains" for your AI coding assistants. This project provides a suite of designed to supercharge GitHub Copilot, Claude, Google Gemini, Cursor and other...
You wrote a good SKILL.md. But did the agent actually follow it, or skip the late safety rule, grab an undeclared tool, and report "done" with no proof?
把中文故事文案或一组有序的手绘图片,转换成 3:4 竖屏**:手写体字幕、从左到右的「文字 → 黑白画稿 → 彩色插画」揭示、可选的右下角卷页翻书转场、安全不裁剪的画面构图。基于 Remotion,默认输出无配音、无音乐的 H.264 画面轨,方便后期配音。
— Anthropic Labs' AI design workspace. DESIGN.md files grouped by aesthetic family, remix recipes, prompt packs with example outputs, skills, video teardowns, and launch-week community signal.
本仓库是基于 WorkBuddy / Claude Code / Cursor 等 AI Agent 的**。每个 Skill 是一个自包含文件夹，包含 SKILL.md（Agent 执行指令）、README.md（人类文档）、references/（Prompt 参考）和 assets/（模板 HTML）。
鲁班 | Luban — 把'能用的Skill'打磨成'能被装、能传播、能验证、能进化'的公共资产。Agent skill-polishing workshop: 验料·访行·过尺·慢刨·回炉
你只想说一句“帮我做个 App”，但 Codex 真正需要的是一个能执行、能验证、知道边界、知道何时停下来的目标。 qiaomu-goal-meta-skill turns vague work into a copy-ready Codex /goal command with defaults, verification, boundaries, and pause conditions.