Cursor Руководство установки
AI-редактор кода, часто используемый с developer MCP.
MCP Servers
AI-powered penetration testing MCP server
MCP-based assistant for busy people who are context switching
A single-binary MCP server that connects Claude Desktop and Claude Code to Microsoft Outlook via the Microsoft Graph API.
The . The historical and kept only for legacy/self-hosted workflows. New users should start with the extension-first path below.
An MCP server for Basecamp 3. It lets MCP-capable clients such as Codex, Cursor, and Claude Desktop read and manage Basecamp projects through OAuth-authenticated Basecamp API calls.
🤝 Show your support - give a ⭐️ if you liked the content
一款面向 的跨平台桌面工具。把提示词模板、自定义 Prompt、第三方 API 供应商、会话同步、Skills / MCP 和 TOML 配置都放进可视化界面里，不用反复手改文件。
Agent Skills
yoooclaw is a standalone CLI — — built for both humans and AI agents. It receives phone notifications locally, manages the Relay tunnel, handles recording ASR and light-effect rule evaluation,...
A Codex skill for turning rough brand ideas into professional image-first identity systems, VI guidelines, and editable HTML brand manuals.
— L1/L2 dual-mode supervision, MCP tool integration, session checkpoints, and 217+ round verified stability. One-click Windows install, zero dependencies.
一个面向百万/千万字长篇的 AI 写作 SKILL，解决长篇小说后期走形的核心问题。
The most powerful command-line interface for Notion — built for AI agents first, humans too.
面向中国教育场景的开源 Agent Skill Pack：教材同步、备考复习、拍照答疑、错题复盘、亲子陪学、阅读写作和教师工具，Hermes Agent 可直接使用，也可导出到 OpenClaw、Codex、Cursor、Claude Code 等 AI 工具。
面向女性化表达与成年人身体探索的中文 Agent Skill 尊重每一种自我称呼，也尊重不被任何标签定义的你
A small collection of practical Agent Skills.
它不只帮你写“电影感、浅景深、光影高级”。 它会先设计镜头是谁，从哪里出发，按什么顺序经过哪些人，怎么绕过障碍物，最后停在哪里。
Official Perplexity API Platform skills, published as portable Agent Skills. They work in Claude Code, OpenAI Codex CLI, and any other Agent Skills client, and the repository doubles as a Claude Code...
它的作用很简单：当你在 API 形式使用 Codex App，没法直接用官方内置 imagegen 时，让 Codex 改走你自己配置的 OpenAI-compatible 图片接口，例如通过 CPA 反代出来的 gpt-image-2。
This is the official implementation of the paper (Sun, Wei, and Hsieh, 2026), accepted to .