Home / duncanyoung-1 / micu-auto-embedded · GitHub

auto-embedded SKILL.md skillA

auto-embedded from duncanyoung-1/micu-auto-embedded is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add duncanyoung-1/micu-auto-embedded/auto-embedded@git:20260726.f3327aa

Pins git:20260726.f3327aa in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
duncanyoung-1/micu-auto-embedded
Path
SKILL.md
Versions recorded
4
Latest version
git:20260726.f3327aa, committed Jul 26, 2026
First version recorded
May 29, 2026
Size
9,665 bytes
Repository stars
258
License
a license file GitHub does not identify

全平台嵌入式 AI 开发框架（对标 Trellis）：把 RIPER-5 五阶段协议 + 四文件记忆 + 分层架构门禁 + Scout/Builder/Verifier 多 Agent + 24 个工具调用技能（build/flash/debug/serial/can/modbus/visa/static/memory/rtos/scons），做成『装进工程、项目级 hook 必然运行、按角色自动注入相关 spec、REVIEW 学习回流』的闭环，并一次写、全平台交付（Claude/Cursor/Codex/OpenCode/Copilot/Gemini/Windsurf）。用 `aemb init` 在固件工程里安装运行时与各平台注入接线。当用户要为 STM32/ESP32/GD32/MSPM0/RISC-V/国产 MCU 工程搭建可复用开发规范基座、让约定自动注入、跨会话可恢复、编译/烧录/调试一体化，或问到 auto-embedded/aemb/spec 注入/项目级 hook/全平台时使用。不适用于纯 Web/移动/桌面软件或与硬件无关的通用 C/C++。.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# auto-embedded —— 装进工程、跨 7 个 AI 平台的 RIPER-5 + spec 注入 + 工具链框架

## 它是什么（与 embedded-dev 的区别）

`embedded-dev` 是**全局单 skill 插件**：refs 全局只读、靠模型自觉、frontmatter hook 对 user-skill 不生效、且只在 Claude 可用。
`auto-embedded` 对标 Trellis，把同一套能力做成**装进每个固件工程、跨多个 AI 编码平台的基座**：

- **项目级 hook 必然运行**：`aemb init` 把注入接线写进工程的各平台配置（Claude `settings.json`、Cursor/Codex/Copilot `hooks.json`、Gemini `settings.json`、OpenCode JS 插件…），AI 工具必然执行（不依赖 skill frontmatter hook）。
- **项目级 spec 库**：`.auto-embedded/spec/`（分层、可版本化、可覆盖），而非全局只读 refs。
- **相关性自动注入**：会话起始注入阶段+spec 索引；派 Scout/Builder/Verifier 时按 per-task `*.jsonl` 只 push 该角色相关的 spec。
- **学习回流**：REVIEW 用 `task.py promote` 把决策/约定/坑沉淀回 spec，跨会话/跨任务复利。
- **工具链一体化**：24 个工具调用技能（编译/烧录/调试/串口/CAN/Modbus/VISA/静态分析/内存分析/RTOS/检索），脚本随框架装进 `.auto-embedded/tools/`，全平台都能调。
- **一次写、全平台交付**：同一套 common 命令/技能/Agent 经占位符渲染成各平台正确语法，由各平台 configurator 写对应注入接线。

## 支持平台

**已打通（7）**：`claude` `cursor` `codex` `opencode` `copilot` `gemini` `windsurf`
**预留位（7，注册表就绪、configurator 待实现）**：`kilo` `kiro` `antigravity` `qoder` `codebuddy` `droid` `pi`

## 第一步：判断工程是否已安装

主交付物是固件且在某个工程目录时，**先查该工程根有没有 `.auto-embedded/`**：

- **没有** → 新接入，跑一次 init：
  ```bash
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add duncanyoung-1/micu-auto-embedded/auto-embedded@sha256:3de149daa8d60a33

The line at the top of this page pins the label git:20260726.f3327aa, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_g27cyvegt6or3fdd.svg)](https://markdownregistry.com/a/art_g27cyvegt6or3fdd)

1 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 4 versions of this file, between May 29, 2026 and Jul 26, 2026, about one every 19 days.

versioncommittedcommitsizeaudit
git:20260726.f3327aa latest2026-07-26 f3327aa 9,665 BA view · diff
git:20260725.9bd2d612026-07-25 9bd2d61 9,653 BA view · diff
git:20260612.1794b012026-06-12 1794b01 9,202 BA view · diff
git:20260529.b5a82202026-05-29 b5a8220 29,685 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (9665 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

duncanyoung-1/micu-auto-embedded · 258 stars · license a license file GitHub does not identify · pushed 2026-10-07 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_g27cyvegt6or3fdd
GET https://markdownregistry.com/api/v1/resolve?ref=duncanyoung-1/micu-auto-embedded/auto-embedded
GET https://markdownregistry.com/api/v1/blob/3de149daa8d60a3326d07a4e8d26648e528699c7419473883a812440f41df981

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from duncanyoung-1/micu-auto-embedded

CLAUDE.md CLAUDE.md file
duncanyoung-1/micu-auto-embedded · CLAUDE.md
git:20261006.86f17b5 · audit A · 258 stars

Every file in duncanyoung-1/micu-auto-embedded

Browse by kind, by grade A, or by owner.