Cursor インストールガイド
開発者向け MCP サーバーとよく使われる AI コードエディタ。
MCP Servers

Code Mode MCP — aggregate all your MCP servers behind search() + execute()

这是一个 mcp 服务器,提供大模型访问 boss 直聘部分接口的能力,让大模型替代用户人工筛选工作岗位并向 boss 打招呼

An MCP server that exposes the Revit API docs and sample code to LLMs.

Unofficial Mi Fitness data export to local SQLite, CSV and JSON, with a local stdio MCP server. 小米运动健康数据导出;实验性,兼容性依设备与地区而异。

MCP Server for executing PowerShell scripts

MCP server that enables LLM agents to talk with IFC (Industry Foundation Classes) files

Загружает метаданные и код конфигураций 1С в графовую базу данных Neo4j и предоставляет инструменты MCP, веб-консоль и встроенного AI агента для анализа данных конфигурации.

1 MCP to rule all them chains

A minimal MCP server built on crawl4ai for LLM-friendly web extraction

Welcome to , your streamlined dev environment for rapidly prototyping with MCP Server for Azure AI Foundry, including the ability to explore and use from Azure AI Foundry Catalog and Azure AI Foundry...

A Kubernetes operator that provides a declarative API to deploy, manage, and safely roll out MCP Servers, handling their full lifecycle with production-grade automation and ecosystem integrations.

MCP server and CLI toolkit for web search and crawling, built on Crawl4AI and SearXNG.
Agent Skills

There are plenty of skills out there. This library avoids slop and only ships skills that:

Human-defined workflows. AI-powered execution. YAML decision trees with scheduling, hooks, MCP, and 21 built-in tools.

A single, readable bash script that takes a fresh Ubuntu/Debian VPS from default install to a hardened, ready-to-use server.

DeckWeaver 可以把 GPT、Gemini等输出的图片重建为可编辑的 PowerPoint 文件。它可以作为Agent的Skill使用,或者直接作为一个无大模型介入的命令行工具。

去 AI 味:繁體中文寫作與翻譯的風格規範(Claude Code skill)

Semi-automated research assistant and local knowledge base for paper analysis, ideation, coding, experiments, writing, and publication workflows.

One URL in, an agency-grade launch video out. A Claude Code skill (Remotion + React) with a 16-law taste codex — 12 brands, 12 worlds, zero templates.

Run Claude Code workflow scripts, unmodified, on the OpenAI Codex CLI — fable plans, codex executes, fable verifies. Parallel agent fleets, builder–verifier loops, token budgets, full-screen TUI.

LegalWork - legal AI workbench

赛博人物库 · 把中国互联网最有辨识度的人物蒸馏成 AI Skill / Claude Code Skill / LLM character distillation

Environment-Runtime 是一个面向工程场景的轻量级 Agent Runtime。随着 OpenClaw 在企业工程流程中的关注度持续提升,一个现实需求也逐渐显现:面向通用场景的 agent runtime 设计未必能直接覆盖所有工程落地形态。这个项目把视角收窄到高确定性工程流程,希望把常见工程任务组织成更清晰、更可复用、更容易维护的运行时。

A hypothesis-driven debugging skill for Claude Code, Codex, and Gemini CLI. Instead of blindly guessing fixes, it instruments your code with runtime logs, generates multiple hypotheses, and...