stm32-hal-ll-integration

stm32-hal-ll-integration is a skill for Claude Code, Codex from easyzoom/aix-skills. It costs 43 tokens per session (692 once invoked), scanned A, original, MIT.

A troubleshooting guide for STM32 microcontrollers using ST’s HAL and LL libraries, including code generated by STM32CubeMX.

In plain words
What is it for?
Use it to diagnose STM32 peripheral initialization, polling versus DMA or interrupt behavior, callbacks, low-power issues, and generated-code problems.
Why use it?
It helps find configuration mismatches in clocks, pins, DMA, interrupts, and peripheral setup that can make firmware fail or break after code regeneration.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to diagnose STM32 peripheral initialization, polling versus DMA or interrupt behavior, callbacks, low-power issues, and generated-code problems.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/easyzoom/aix-skills/stm32-hal-ll-integration
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add easyzoom/aix-skills --skill stm32-hal-ll-integration
Clone the repo
git clone --depth 1 https://github.com/easyzoom/aix-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for stm32-hal-ll-integration

README.md
[![agentmods](https://agentmods.dev/badge/skills/easyzoom/aix-skills/stm32-hal-ll-integration/github.svg)](https://agentmods.dev/skills/easyzoom/aix-skills/stm32-hal-ll-integration)
Your own site
<a href="https://agentmods.dev/skills/easyzoom/aix-skills/stm32-hal-ll-integration"><img src="https://agentmods.dev/badge/skills/easyzoom/aix-skills/stm32-hal-ll-integration/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for stm32-hal-ll-integration

Your own site · 80×15
<a href="https://agentmods.dev/skills/easyzoom/aix-skills/stm32-hal-ll-integration"><img src="https://agentmods.dev/badge/skills/easyzoom/aix-skills/stm32-hal-ll-integration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 692 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00043 $0.00692
Opus 5 $0.00022 $0.00346
Sonnet 5 $0.00009 $0.00138
Haiku 4.5 $0.00004 $0.00069

Measured 8d ago against content hash de04d72e6e22, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

stm32-hal-ll-integration scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/stm32-hal-ll-integration/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

STM32 HAL LL Integration

Overview

Use this skill to debug STM32 projects by separating Cube-generated configuration, clock tree, pin mux, HAL handle state, DMA, and interrupt routing. STM32 bugs often come from generated configuration drift.

When To Use

Use this skill when:

  • The user is working with STM32CubeMX, STM32CubeIDE, HAL, LL, or Cube firmware examples.
  • The issue involves clock configuration, GPIO alternate functions, DMA, interrupts, peripheral init, callbacks, low power, or generated code regions.
  • A peripheral works in polling but fails with DMA/interrupts, or works until Cube regenerates files.

Do not use this skill for non-STM32 MCUs or pure protocol logic. Use the matching protocol or peripheral skill instead.

First Questions

Ask for:

  • STM32 part number, board, Cube package version, IDE/toolchain, and HAL version.
  • .ioc settings, clock tree, pin mux, DMA streams/channels, and NVIC priorities.
  • Peripheral instance, HAL/LL mode, generated init code, callbacks, and logs.
  • Whether user code is inside preserved USER CODE regions.
  • Current symptom, return code, error flags, and register snapshot if available.

Debug Workflow

  1. Freeze Cube configuration. Inspect .ioc, generated init functions, clock tree, pin mux, DMA, and NVIC.

  2. Prove clocks and pins. Confirm peripheral clock enable, GPIO alternate function, speed, pull, and external signal presence.

  3. Check HAL handle state. Inspect handle init, state, error code, MSP init, callbacks, and return codes.

  4. Add interrupt or DMA carefully. Verify IRQ handler names, priorities, DMA request mapping, cache policy, and callback completion.

  5. Compare HAL and LL boundaries. Do not mix direct register/LL changes with HAL state machines unless the ownership is explicit.

  6. Protect generated code. Keep edits in user regions or separate files so Cube regeneration is safe.

Common Failures

  • Peripheral clock or GPIO alternate function is missing.
  • DMA request/channel mapping is valid on another STM32 family, not this one.
  • IRQ handler is not linked or has the wrong name.
  • HAL callback never fires because interrupt enable is missing.
  • Direct register writes break HAL's state machine assumptions.
  • User edits outside preserved regions are lost after Cube regeneration.

Read the full file on GitHub · 92 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 92 lines · 43 tokens per session scan A de04d72e6e22

Subscribe to this mod's changes

stm32-hal-ll-integration is a skill published in the GitHub repository easyzoom/aix-skills (31 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 692 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.