agentleFS
wedsamuel1230wedsamuel1230/embedded-engineering-skills/AGENTS.md

embedded-engineering-skills

AGENTS.md28 starsChanged 28 days agoMITView on GitHub

The canonical skill content is under skills/. Select the smallest matching SKILL.md, and load references/ or docs/ only when the skill points to it. Preserve the raw ordered constexpr int pin-declaration convention and C/C++ conventions for native firmware. For explicitly selected MicroPython, use that port's Python/runtime conventions instead. Keep compile, upload, hardware, system, and deployment evidence separate. Do not claim physical success without a user provided measurement, log, or photo. For physical or multi-session work, load skills/embedded-project-loop/SKILL.md first, then use…

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

Files
AGENTS.md

Embedded Engineering Skills source

The canonical skill content is under skills/. Select the smallest matching SKILL.md, and load references/ or docs/ only when the skill points to it.

Preserve the raw ordered constexpr int pin-declaration convention and C/C++ conventions for native firmware. For explicitly selected MicroPython, use that port's Python/runtime conventions instead. Keep compile, upload, hardware, system, and deployment evidence separate. Do not claim physical success without a user provided measurement, log, or photo.

For physical or multi-session work, load skills/embedded-project-loop/SKILL.md first, then use the workflow router for specialist routing.

Provider manifests in .codex-plugin/, .claude-plugin/, and .cursor-plugin/ are adapters only; do not duplicate skill instructions there.

Browse catalog/README.md by job; keep actual bundles flat under skills/. Current platform routes include Arduino, ESP-IDF, Zephyr, STM32Cube, Pico SDK and MicroPython. Rust is deferred. Validate with the repository validators and uv run --frozen python -m unittest discover -s tests -p 'test_*.py'. Build-only platform fixtures use scripts/validate_platforms.py; do not infer hardware success or silently choose a port/probe. New plugin identity is embedded-engineering-skills; old installed IDs need an explicit host upgrade.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.