by buchidonggua
# Add to your Claude Code skills
git clone https://github.com/buchidonggua/dg-ai-notesLast scanned: 7/20/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-07-20T06:45:20.193Z",
"npmAuditRan": true,
"pipAuditRan": true,
"promptInjectionRan": true
}dg-ai-notes is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by buchidonggua. It has 114 GitHub stars.
Yes. dg-ai-notes passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/buchidonggua/dg-ai-notes" and add it to your Claude Code skills directory (see the Installation section above).
dg-ai-notes is primarily written in MDX. It is open-source under buchidonggua on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh dg-ai-notes against similar tools.
No comments yet. Be the first to share your thoughts!
冬瓜的 AI 学习笔记 · 当前重点:Pi-Agent SDK 深度教程
Pi-Agent 是 @earendil-works 开源的 Agent SDK,定位是生产级 AI Agent 的运行时底座。
它不是玩具框架,而是一套真正能上线的 Agent 工程参考实现——同类产品(Claude Code、Cursor、Cline 等)的内部架构都能在 Pi 里找到对应。看懂 Pi,等于看懂一个完整的 Agent SDK 应该怎么设计。
核心能力:
谁该学:
10 章系统拆解 Pi-Agent 的源码设计与实现,每一章都回答三个层次的问题:是什么(概念)、怎么做(源码分析)、为什么这样做(设计取舍)。
ch01 开篇总览 → ch02 三层架构 → ch03 Agent Loop → ch04 模型调用 → ch05 工具系统
↓
ch06 消息系统 → ch07 事件驱动 → ch08 上下文工程 → ch09 上下文压缩 → ch10 会话管理
每一章都提供 TypeScript 版(与 Pi 原作同语言)和 Python 版(方便只熟悉 Python 的读者)双版本对照。
| 方式 | 入口 | 适合场景 |
|---|---|---|
| 🌐 Web 在线版(推荐) | https://dg-ai-notes.pages.dev | PC 端沉浸式阅读,三栏布局 + 配图联动 + 主题切换 |
| 📥 Markdown 下载版 | pi-agent/docs/ | 下载到本地,配合 AI(Claude / Cursor / 等)边读边问、对照源码 |
| 📕 PDF 版 | v1.0 Release | 离线阅读、打印、长期存档 |
TS 版路径:pi-agent/docs/typescript/ Python 版路径:pi-agent/docs/python/
notebooks/agent-loop.ipynb 是第 3 章 Agent Loop 的可执行实验场,可以单步运行、改参数、观察 loop 状态。
⚠️ 本教程主体为"阅读型",配套实验代码(L00-L31 课程实战)暂未公开。Notebook 仅作 Agent Loop 章节的补充实验场。
发现 typo / 内容错误?欢迎:
详见 CONTRIBUTING.md。