zhinkgit/embeddedskills
An open-source collection of embedded development and debugging skills for Claude Code, Copilot, TRAE, and other AI coding assistants that support the Skill protocol. Once installed, the AI assistant can directly operate compilers, debuggers, and communication buses, automating the full workflow from code generation to hardware verification.
What it solves
Embedded development typically requires a manual loop of writing code, compiling, flashing, and debugging. This project provides a set of "skills" that allow AI coding assistants to directly control compilers, debuggers, and communication buses, closing the loop from code generation to hardware verification without manual intervention.
How it works
The project encapsulates various command-line tools (such as Keil MDK, GCC, J-Link, OpenOCD, and probe-rs) into structured Python scripts. These scripts are exposed to AI agents via SKILL.md files that describe their capabilities in natural language. When the AI calls a skill, the scripts return a unified JSON output containing the status, summary, and suggested next actions, allowing the AI to autonomously decide the next step in the development cycle.
Who it’s for
Embedded software engineers who use AI coding assistants (like Claude Code, Cursor, or Trae) and want to automate the build-flash-debug cycle on real hardware.
Highlights
- Full Workflow Loop: Automates the sequence of requirement communication $\rightarrow$ code generation $\rightarrow$ compilation $\rightarrow$ flashing $\rightarrow$ debugging $\rightarrow$ error correction.
- Tool-Agnostic: Works with any AI tool that supports the Skill/CLAUDE.md/Rules protocol.
- Broad Hardware Support: Supports Keil MDK and CMake/GCC build systems, as well as J-Link, OpenOCD, and probe-rs debuggers.
- Communication Bus Monitoring: Includes skills for monitoring and interacting with UART (Serial), CAN/CAN-FD, and Ethernet (Net) traffic.
Related
- Project
- Project
- Project
- Project
- Project