Low Power Embedded logo

Low Power Embedded

Community
mohitmishra786
low-power-embedded

Low-power embedded skill for sleep modes and energy optimization. Use when configuring MCU sleep/stop/standby, peripheral clock gating, wake-up sources, or measuring firmware current draw. Activates on queries about WFI, STOP mode, STM32 PWR, nRF sleep, wake-up EXTI, or reducing embedded power consumption.

Overview

Publishermohitmishra786
Repositorylow-level-dev-skills
Skill namelow-power-embedded
Stars
266
Forks
31
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by mohitmishra786 on GitHub. Read the source before you install it.

Installation

Install the Low Power Embedded AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/mohitmishra786/low-level-dev-skills/tree/main/skills/baremetal/low-power-embedded
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/mohitmishra786/low-level-dev-skills.git /tmp/low-level-dev-skills
mkdir -p .claude/skills
cp -r /tmp/low-level-dev-skills/skills/baremetal/low-power-embedded .claude/skills/low-power-embedded
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Low Power Embedded in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Low Power Embedded on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Low Power Embedded is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Low-Power Embedded

Purpose

Guide agents through MCU low-power modes: sleep vs deep sleep (stop/standby), peripheral and bus clock gating, wake-up source configuration, and practical current measurement — with Cortex-M WFI/WFE and vendor PWR examples (STM32-focused patterns apply broadly).

When to Use

  • Battery-powered firmware missing power budget
  • Wake-up latency vs consumption tradeoffs
  • Debugging "device won't wake" or "current still mA in sleep"
  • Before shipping RTOS idle hook or bare-metal main loop sleep
  • Cross-linking with skills/baremetal/interrupts-and-exceptions-baremetal

Workflow

1. Power mode hierarchy (STM32-style)

ModeCPUPeripheralsRAMWake sourceRelative current
Runononon—highest
Sleepoffononany IRQmedium
Stopoffmost offonEXTI, RTC, UARTlow
Standbyoffofflost*WKUP pins, RTClowest

* Standby clears most SRAM; use backup domain or external EEPROM for state.

2. Enter Sleep (WFI)

c
/* Cortex-M — sleep until interrupt */
__disable_irq();
/* configure wake source (e.g. EXTI, RTC alarm) */
__enable_irq();
__WFI(); /* or __WFE() for event-based wake */

Ensure pending interrupts are cleared before WFI or wake may be immediate.

3. STM32 Stop mode pattern

c
#include "stm32f4xx.h"

void enter_stop_mode(void)
{
    /* Gate clocks you do not need */
    RCC->AHB1ENR &= ~RCC_AHB1ENR_GPIOAEN; /* example — only if safe */

    PWR->CR |= PWR_CR_CWUF;   /* clear wake flags */
    PWR->CR |= PWR_CR_PDDS;   /* deep sleep = Stop */
    SCB->SCR |= SCB_SCR_SLEEPDEEP_Msk;

    __WFI();

    /* After wake: re-enable HSE/PLL — clocks lost in Stop on many parts */
    SystemInit();
}

After Stop, re-init clocks and peripherals that lost their registers.

4. Clock gating checklist

Before sleep
├── Disable unused peripheral clocks (RCC xENR)
├── Disable ADC/DAC continuous modes
├── Stop DMA channels
├── Enter peripheral low-power (UART mute, SPI off)
└── Configure lowest viable regulator scale (Voltage Scale 2/3)

5. Wake-up sources

SourceConfig
EXTI GPIOSYSCFG + EXTI IMR, edge trigger
RTC alarmRTC WUT/WAKEUP
UARTStart bit detection (some MCUs)
IWDGNot a wake source — resets device

6. Measurement tips

  • Use ammeter in series with VDDA/VDD; short sampling window for uA
  • DWT cycle counter for wake latency benchmarking
  • Compare run vs sleep current with same clock tree documented

7. RTOS note

FreeRTOS configUSE_TICKLESS_IDLE maps to WFI/Stop — coordinate with skills/embedded/freertos.

8. Agent usage

/low-power-embedded Configure STM32 Stop mode with EXTI0 wake and PLL restore

Common Problems

SymptomCauseFix
Still mA in "sleep"Debug interface active (SWD)Disconnect debugger; disable DBGMCU
Immediate wake from WFIPending NVIC IRQClear flags before WFI
Lost state after wakeEntered Standby not StopUse Stop if RAM must persist
UART dead after wakeClock tree not restoredCall SystemInit() path
Higher than datasheet uAFloating GPIOSet unused pins analog or pull

Related Skills

  • skills/baremetal/interrupts-and-exceptions-baremetal — EXTI wake IRQs
  • skills/baremetal/gpio-baremetal — pin mode for leakage control
  • skills/baremetal/stm32-baremetal — RCC and PWR registers
  • skills/baremetal/timers-pwm-baremetal — stop timers before sleep
  • skills/embedded/freertos — tickless idle integration

Frequently asked questions

What does the Low Power Embedded AI skill do?

Low-power embedded skill for sleep modes and energy optimization. Use when configuring MCU sleep/stop/standby, peripheral clock gating, wake-up sources, or measuring firmware current draw. Activates on queries about WFI, STOP mode, STM32 PWR, nRF sleep, wake-up EXTI, or reducing embedded power consumption.

Why use Low Power Embedded on TypingMind?

Because you install it once and use it with any model. Low Power Embedded is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Low Power Embedded in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/mohitmishra786/low-level-dev-skills/tree/main/skills/baremetal/low-power-embedded. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Low Power Embedded?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Low Power Embedded?

As many as you like. As long as a model supports skills, you can use Low Power Embedded with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Low Power Embedded AI skill free?

Yes. It is published on GitHub by mohitmishra786 under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇