Embedded Skills workflow
embeddedskills
Skills for embedded development: AI drives compilers, debuggers (J-Link and others) and buses (CAN) from code to hardware checks. README in Chinese and English
- 741 ★ on the repository
- Last commit
- MIT
Broad access
Why this level
- The agent flashes and debugs real hardware
- Version 0.1.0 with some skills untested on hardware
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add workflows/embeddedskillsDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewBroad accessThe tool can change data, run commands or handle secrets.
- The agent flashes and debugs real hardware
- Version 0.1.0 with some skills untested on hardware
This is third-party code. Review the repository files before installing.
What it does
Embedded Skills let AI drive compilers, debuggers (J-Link, OpenOCD, probe-rs) and buses such as CAN, closing the loop from code generation to verification on real hardware. Installation: `npx skills add https://github.com/zhinkgit/embeddedskills -g -y`, a single skill: `--skill jlink`. The README is in Chinese with an English version. Version 0.1.0 from 15.04.2026, MIT license. The project is early and part of the skills are marked in the README table as awaiting hardware testing.
Who it is for. For embedded developers who want to close the build, flash and debug loop with an agent.
Good fit when
- You need a build, flash and debug loop for a microcontroller through an agent
- You need control of J-Link, OpenOCD or probe-rs
- You need CAN bus work from an agent
Not a fit when
- You cannot let an agent flash real hardware
- You need a mature version: it is 0.1.0 now with some skills untested on hardware
Example request
Build the project for a training board, flash it through J-Link and check with the debugger that the LED blinksLimitations
The agent flashes and debugs real hardware, so access is wide: a mistake can brick a board. Version 0.1.0, and part of the skills are marked in the README as awaiting hardware testing. Start with a training board and a separate bench. The README is in Chinese.
How to disable. Remove the skill from the agent's folder or the plugin through the plugin manager.
FAQ
What does the set do?
It lets AI drive compilers, debuggers and buses for a closed loop from code to hardware verification.
Is it ready for working hardware?
No, version 0.1.0 with some skills untested on hardware: start with a training board.
How do I install it?
npx skills add https://github.com/zhinkgit/embeddedskills -g -y.
Discussion
No questions or reviews yet.
Related
WorkflowsDimillian Skills
Skills
A set of 16 engineering skills for agents: Apple platform work, macOS packaging, React performance, code review and refactoring
An Agent Skills plugin for 1C:Enterprise 8.3 development: core domain rules plus a build-and-database skill, tested across three environments
A set of Claude Code skills for the dev workflow: worktree isolation, a service layer, evidence and review
A shared skill and tooling infrastructure for 1C development, wired in as a git submodule and laid out across several agents at once
1C:Element IDE skill
onec-element-ide
A Codex skill for the cloud 1C:Element IDE: pulls sources through the control panel, helps edit them locally and pushes fixes back
Builder Skills
Skills for agents
A set of small skills from Builder.io for agent work habits: visual plans and diff recaps, docs-first checks, cross-agent review and clean status updates
README in short
The README describes skills for embedded development driving compilers, debuggers and the CAN bus and installation through npx skills. MIT license.