Cursor 安装指南
常与开发类 MCP Server 搭配使用的 AI 代码编辑器。
MCP Servers
Add vision to text-only models in Opencode (, ) — , no manual file saving.
Open-source, local-first memory and context for AI agents. One memory store, every agent.
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.
Self-hosted, agent-native web app and MCP server for your Obsidian-style Markdown vault. Browse, search, and edit notes from a fast UI or from AI agents.
个人知识库 MCP 服务器 — 对本地文档建立索引，并提供一组飞书 API 工具，通过 MCP 协议供 AI 客户端访问。
LogLead performs log loading, log enhancement, log feature engineering, log analysis, log anomaly detection also via MCP-server.
Agent Skills
Your agent downloads the framework, walks through configuration with you, restructures its soul (preserving content), and starts evolving.
Infrastructure for agent-native applications, with pluggable runtimes.
- PP-OCRv6 文字检测 + 识别的 实现，纯 ONNX Runtime 推理， - 。完整复现预处理 / 后处理（DB 后处理、CTC 解码、 - pyclipper 等价的多边形 unclip。 - doc_ori 文档方向分类模型，支持（4 类：0°/90°/180°/270°）在检测前对整图做方向校正，避免用户侧倒拍/横拍导致识别失败。
My Claude stuff (skills, agents and whatnot.)
A Claude Code plugin with skills for working with the Sentio platform — building blockchain data processors, running SQL queries, managing alerts, dashboards, and endpoints.
A Claude Code plugin containing 22 focused skills for programming, optimizing, evaluating, and deploying LLM applications with DSPy.
i don't actually recommend u use this principle without fully understanding. it's just a reference at what's possible
A Claude Code skill that designs, documents, and tracks object-oriented software architecture using live Mermaid UML diagrams inside CLAUDE.md.
skills 质量检测工具——对已安装的 skills 进行自动化质量评估
不露脸商业/消费调查长片的完整生产流程：一句话出 10 分钟成片，以 Claude Code skill 形式开源（TTS 逐字时间戳、素材覆盖、Remotion 拼贴、闪避混音、封面与八平台文案）
把法律画出来 · Make the Law Visible —— 给法律人的诉讼可视化工具集：把凌乱的诉讼图重画成能进材料的图，直接读案件材料画准一张时间轴，并提供庭前三大法宝（大事记表、庭审对抗图、法律关系图）。Claude Skill / DeepSeek Harness 通用。
A Formally Grounded, Self-Improving Agentic Framework for Automated Research in Causal Inference