Updated 1mo ago
by notnameuse
embedded-debug-skill
面向真实嵌入式设备的系统化调试 Skill。重点覆盖 STM32/ARM Cortex-M + FreeRTOS 场景,并通过 Serial Agent/MCP 能力完成“获取现场→分析→修改→编译→烧录→运行→验证”的闭环。用户提及 STM32、FreeRTOS、HardFault、I2C/SPI/UART/CAN、DMA、RTOS 任务异常、死机、偶发故障、串口日志、SWD/JTAG、GDB、逻辑分析仪、示波器、固件烧录或需要连接真实开发板进行调试时使用。
47 GitHub stars (47)
- 2 skills (2 skills found in its SKILL.md files)
- 1 forks (1 forks)
- 1mo ago last update (Last updated 1mo ago)
Install
Skills CLI
npx skills add notnameuse/embedded-debug-skill
Asks which skills and agents to install. Just one: npx skills add notnameuse/embedded-debug-skill --skill embedded-debugging — add -g for every project.
Claude Code
git clone https://github.com/notnameuse/embedded-debug-skillcp -r "embedded-debug-skill/skills/embedded-debugging" ~/.claude/skills/
Copies the embedded-debugging skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add notnameuse/embedded-debug-skill
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md.
-
embedded-debugging
面向真实嵌入式设备的系统化调试 Skill。重点覆盖 STM32/ARM Cortex-M + FreeRTOS 场景,并通过 Serial Agent/MCP 能力完成“获取现场→分析→修改→编译→烧录→运行→验证”的闭环。用户提及 STM32、FreeRTOS、HardFault、I2C/SPI/UART/CAN、DMA、RTOS 任务异常、死机、偶发故障、串口日志、SWD/JTAG、GDB、逻辑分析仪、示波器、固件烧录或需要连接真实开发板进行调试时使用。
skills/embedded-debugging/SKILL.md on GitHub (opens in a new tab) -
keil-mcp-debug
在任意工作区为 STM32F4 + ST-Link 搭建并运行"AI 源码级在线调试"链路(OpenOCD + arm-none-eabi-gdb + mcp-gdb)的引导式技能。当用户想在某个工作区用 AI 通过 MCP 对真实 STM32 硬件下断点/单步/看变量/读内存/查调用栈, 或需要首次配置环境(探测/安装工具链、注册 MCP、验证能连板)、执行一次真机调试闭环时使用。仅限 Windows + ST-Link + STM32F4(其它系列/OS 未验证)。
skills/keil-mcp-debug/SKILL.md on GitHub (opens in a new tab)
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.