ylongw

ylongw / embedded-review

Public

Embedded/firmware code review skill for AI agents. Memory safety, interrupt correctness, RTOS pitfalls, hardware interfaces, C/C++ traps. STM32/Cortex-M/FreeRTOS focused.

ai-skill code-review cortex-m embedded firmware
10
0
100% credibility
Found Mar 05, 2026 at 10 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Shell
AI Summary

This repository offers an AI skill for reviewing code changes in embedded firmware projects, using single or dual-model analysis to detect issues like memory safety and hardware interface problems.

How It Works

1
🔍 Discover the Helper

You find a smart code review expert designed for firmware projects that spots tricky bugs others miss.

2
📥 Add to Your AI Tool

You simply place it into your AI assistant's skills folder so it's ready to use anytime.

3
📂 Point to Your Changes

You show it your firmware project's folder and the recent updates you made.

4
Pick Review Style
⚡
Quick Review

Fast check for everyday changes to get speedy feedback.

🔬
Deep Cross-Review

Two smart reviewers compare notes to catch more hidden issues.

5
🚀 Ask for the Review

You tell your AI helper to review the changes, and it dives in with expert eyes.

6
⏳ Watch It Analyze

It examines your code for safety issues, hardware quirks, and best practices.

✅ Get Your Report

You receive a clear list of findings with severity levels and fixes, helping you build safer firmware.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 10 to 10 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is embedded-review?

This Shell-based skill turns AI agents like OpenClaw or Claude Code into embedded review experts for firmware code on GitHub repos or local projects. It grabs git diffs—from uncommitted changes to PRs—and runs dual-model checks with Claude for embedded-specific pitfalls (memory safety, interrupt correctness, RTOS traps, hardware interfaces) and Codex for broader C/C++ catches, then cross-compares results for high-confidence bugs. Developers get structured reports with severity levels (P0 critical to P3 low) focused on STM32, Cortex-M, and FreeRTOS environments.

Why is it gaining traction?

Unlike single-model linters that miss embedded/firmware nuances like DMA coherence or priority inversion, its heterogeneous AI cross-review catches blind spots both models agree on as real issues. CLI usage is dead simple: "Review firmware-pro2 feat/nfc changes" or paste a GitHub PR link, with modes for quick single reviews or thorough dual ones. It stands out in embedded reviews by prioritizing hardware correctness and security over generic style nits.

Who should use this?

Embedded firmware engineers reviewing C/C++ changes in bare-metal MCUs or RTOS setups like FreeRTOS on STM32. Teams handling PRs for I2C/SPI peripherals, interrupt handlers, or firmware updates who want agent-assisted checks before merge. Small shops without dedicated QA for embedded quality review.

Verdict

Worth a test drive for embedded firmware GitHub workflows if you're in STM32/FreeRTOS land—solid docs and targeted features punch above its 10 stars and 1.0% credibility score. Still early-stage with no tests visible, so pair it with human eyes on P0 findings until it matures.

(187 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.