Baremetal Startup logo

Baremetal Startup

Community
mohitmishra786
baremetal-startup

Bare-metal startup skill for reset-to-main bring-up. Use when writing startup code, vector tables, .data/.bss init, stack setup, or crt0 for Cortex-M/RISC-V. Activates on queries about reset vector, VTOR, startup.s, bss init, or bare-metal entry point.

Overview

Publishermohitmishra786
Repositorylow-level-dev-skills
Skill namebaremetal-startup
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 Baremetal Startup 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/baremetal-startup
  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/baremetal-startup .claude/skills/baremetal-startup
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Baremetal Startup 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 Baremetal Startup 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 Baremetal Startup 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.

Bare-Metal Startup

Purpose

Guide agents through bare-metal startup from reset to main(): reset and exception vectors, .data/.bss initialization, stack and heap setup, C runtime integration with linker scripts, and common Cortex-M and RISC-V bring-up bugs.

When to Use

  • Firmware hangs before reaching main()
  • Porting to a new MCU without vendor HAL
  • Writing custom startup.s or Reset_Handler
  • Integrating with skills/embedded/linker-scripts
  • Debugging uninitialized globals or stack overflows at boot

Workflow

1. Boot sequence mental model

Power-on / reset
├── CPU loads SP from vector[0]
├── CPU branches to Reset_Handler from vector[1]
├── Reset_Handler: init clocks (optional), copy .data, zero .bss
├── Configure stack pointer (if not already from vector)
├── Call SystemInit() / platform_init()
└── Call main() — must not return (loop or WFI)

2. Cortex-M vector table

On Cortex-M, the vector table starts at address 0 or a relocatable base (VTOR):

IndexEntry
0Initial stack pointer (_estack)
1Reset_Handler
2NMI_Handler
3HardFault_Handler
4+IRQ handlers per NVIC
asm
/* startup.s — minimal Cortex-M */
.syntax unified
.thumb

.section .isr_vector,"a",%progbits
.global g_pfnVectors
g_pfnVectors:
    .word _estack
    .word Reset_Handler
    .word NMI_Handler
    .word HardFault_Handler
    /* ... device IRQ vectors from vendor CMSIS ... */

.section .text.Reset_Handler
.thumb_func
.global Reset_Handler
Reset_Handler:
    ldr r0, =_sidata    /* .data load address (LMA) */
    ldr r1, =_sdata     /* .data VMA start */
    ldr r2, =_edata
    b LoopCopyDataInit
CopyDataInit:
    ldr r3, [r0], #4
    str r3, [r1], #4
LoopCopyDataInit:
    cmp r1, r2
    blt CopyDataInit
    ldr r2, =_sbss
    ldr r4, =_ebss
    movs r3, #0
    b LoopFillZerobss
FillZerobss:
    str r3, [r2], #4
LoopFillZerobss:
    cmp r2, r4
    blt FillZerobss
    bl SystemInit
    bl main
    b .
c
/* Linker symbols — declared extern in startup */
extern uint32_t _estack, _sidata, _sdata, _edata, _sbss, _ebss;

3. VTOR relocation (Cortex-M)

c
#include "core_cm4.h"  /* CMSIS */

void relocate_vector_table(uint32_t base) {
    SCB->VTOR = base & 0xFFFFFF80U;  /* must be aligned per ARM ref manual */
    __DSB();
    __ISB();
}

Bootloader jumping to app often requires setting VTOR to the application's vector table address (e.g., 0x08020000 on STM32 flash).

4. RISC-V startup (overview)

asm
/* entry.S — simplified */
.section .text.entry
.global _start
_start:
    la sp, _stack_top
    la t0, _bss_start
    la t1, _bss_end
clear_bss:
    beq t0, t1, bss_done
    sw zero, 0(t0)
    addi t0, t0, 4
    j clear_bss
bss_done:
    call main
    j .

Trap vector: mtvec for M-mode; see skills/platform/riscv-privileged.

5. crt0 responsibilities

TaskWho does it
Copy .data LMA→VMAReset_Handler / crt0
Zero .bssReset_Handler
Init stackVector[0] or explicit sp
Heap (_sbrk)Optional; libc or custom
C++ constructors__libc_init_array() if using full libc
FPU enableSystemInit on Cortex-M4F/M7

6. Linker script integration

ld
_estack = ORIGIN(RAM) + LENGTH(RAM);
_sidata = LOADADDR(.data);

Cross-link skills/embedded/linker-scripts for MEMORY/SECTIONS layout.

7. Agent usage examples

/baremetal-startup My STM32 never reaches main — what should Reset_Handler do?
/baremetal-startup How do I relocate the vector table after bootloader jump?

Common Problems

SymptomCauseFix
HardFault immediatelyStack pointer invalidSet _estack to valid RAM top
Globals wrong at boot.data not copiedCopy LMA→VMA in Reset_Handler
BSS non-zero.bss not zeroedAdd bss clear loop
IRQs don't fireVTOR points to wrong tableSCB->VTOR = app_vector_addr
main returns into garbageNo loop after mainwhile(1) or WFI loop
C++ static init crashConstructors before clocksCall SystemInit first

Related Skills

  • skills/embedded/linker-scripts — _estack, LMA/VMA, section placement
  • skills/baremetal/interrupts-and-exceptions-baremetal — vector table IRQ entries
  • skills/baremetal/bootloaders-embedded — VTOR relocation on app jump
  • skills/embedded/openocd-jtag — halt at Reset_Handler with GDB
  • skills/low-level-programming/assembly-arm — Thumb-2 syntax
  • skills/platform/riscv-privileged — RISC-V trap setup

Frequently asked questions

What does the Baremetal Startup AI skill do?

Bare-metal startup skill for reset-to-main bring-up. Use when writing startup code, vector tables, .data/.bss init, stack setup, or crt0 for Cortex-M/RISC-V. Activates on queries about reset vector, VTOR, startup.s, bss init, or bare-metal entry point.

Why use Baremetal Startup on TypingMind?

Because you install it once and use it with any model. Baremetal Startup 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 Baremetal Startup in TypingMind?

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

Which AI models can use Baremetal Startup?

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 Baremetal Startup?

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

Is the Baremetal Startup 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 👇