Jetson Init Image logo

Jetson Init Image

Organization
NVIDIA-AI-IOT
jetson-init-image

Extract Jetson Linux + sample-rootfs tarballs and run apply_binaries.sh for the active target, then record bsp_image in the profile. Use after jetson-init-target; not for source-tree setup.

Overview

PublisherNVIDIA-AI-IOT
Repositoryjetson-bsp-skills
Skill namejetson-init-image
Stars
73
Forks
13
Bundled files
4
LicenseApache-2.0
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.

  • 4 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by NVIDIA-AI-IOT on GitHub. Read the source before you install it.

Installation

Install the Jetson Init Image 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/NVIDIA-AI-IOT/jetson-bsp-skills/tree/main/skills/jetson-init-image
  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/NVIDIA-AI-IOT/jetson-bsp-skills.git /tmp/jetson-bsp-skills
mkdir -p .claude/skills
cp -r /tmp/jetson-bsp-skills/skills/jetson-init-image .claude/skills/jetson-init-image
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Jetson Init Image 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 Jetson Init Image 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 Jetson Init Image 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.

Initialize BSP Image

Output is only bsp_image: in the active profile: derived version plus root_path only when overriding <workspace>/Image.

When to invoke

  • The user asks to extract, prepare, or initialize the BSP image.
  • A downstream skill reports missing <bsp_image.root_path>/Linux_for_Tegra/.
  • The active profile has no bsp_image: block yet.

Procedure

Resolve target and image path

Resolve the active profile per ../../context/target-platform-contract.md. Refuse if there is no active profile or reference_devkit: is missing.

<workspace> is the parent of the active profile's target-platform/ directory. <bsp_image.root_path> defaults to <workspace>/Image.

Profile stateAction
bsp_image.root_path existsUse it without prompting.
bsp_image: exists without root_pathUse <workspace>/Image.
No bsp_image: blockAsk once: Enter for default, or absolute override path.

For an override, validate that the closest existing parent is writable. Omit root_path when the default is used.

Determine GPU stack

Use the shared GPU-driver invariant from ../../context/target-platform-contract.md. Derive the expected stack from reference_devkit.module.id and the catalogue:

Chip familyModule IDsStackapply_binaries.sh flag
T234 / Orinp3701, p3767nvgpunone
T264 and later / Thor+p3834OpenRM--openrm

Refuse unknown module IDs. The --openrm flag is only valid on BSP releases that ship the OpenRM stack; if the active BSP doesn't expose the flag, omit it regardless of what the target wants.

Reuse or extract

If <bsp_image.root_path>/Linux_for_Tegra/ already exists:

  1. Do not extract over it unless the user explicitly requested re-extraction and accepted the overwrite risk.

  2. Derive the on-disk version from Linux_for_Tegra/nv_tegra_release. Ask before replacing a different recorded bsp_image.version.

  3. Verify the installed GPU stack against the platform-derived expectation when possible. Detection precedence (first probe that yields a definitive answer wins):

    1. Linux_for_Tegra/rootfs/etc/nv_tegra_release carries an INSTALL_TYPE= token on BSP releases that expose it (newer lines). Read and compare directly.
    2. Otherwise, find Linux_for_Tegra -name nvgpu.ko: present → nvgpu, absent → OpenRM.
    3. If the chip family has only ever shipped one stack (e.g. T234 / Orin is always nvgpu in current BSPs), fall back to the catalogue-derived expectation without disk probing.

If the installed stack conflicts with the active target, refuse and ask the user to re-extract with the correct stack or fix the target profile. Otherwise skip extraction and update the profile.

Locate tarballs

When extraction is needed, search:

  1. <bsp_image.root_path>/
  2. <workspace>/
  3. current working directory

Prompt for absolute paths for anything missing. Required filenames:

  • Jetson_Linux_R<ver>_aarch64.tbz2
  • Tegra_Linux_Sample-Root-Filesystem_R<ver>_aarch64.tbz2

Both filenames must contain the same R<ver> token. Refuse mismatches and record <ver> as bsp_image.version. Do not download tarballs.

Extract and apply binaries

Use absolute tarball paths; they may live outside <bsp_image.root_path>.

bash
ROOT="<bsp_image.root_path>"
BSP_TARBALL="<absolute path to Jetson_Linux_R<ver>_aarch64.tbz2>"
ROOTFS_TARBALL="<absolute path to Tegra_Linux_Sample-Root-Filesystem_R<ver>_aarch64.tbz2>"

mkdir -p "$ROOT"
tar xjf "$BSP_TARBALL" -C "$ROOT"
sudo tar xpjf "$ROOTFS_TARBALL" -C "$ROOT/Linux_for_Tegra/rootfs"

cd "$ROOT/Linux_for_Tegra"
if [ "$GPU_STACK" = "openrm" ]; then
  sudo ./apply_binaries.sh --openrm
else
  sudo ./apply_binaries.sh
fi

Set GPU_STACK from the "Determine GPU stack" step above. Abort on the first failing command and surface the failed command.

Update the active profile

Persist the resolved BSP image metadata in the active target profile so later skills can find the BSP without re-prompting. Preserve existing blocks, comments, and quoted SKU values; use a round-tripping YAML writer such as ruamel.yaml.

yaml
bsp_image:
  root_path: <absolute override path>  # omit for <workspace>/Image
  version: "<derived version>"

Rules:

  • Same version and same root path: no rewrite.
  • Different version: ask before updating.
  • Different recorded root_path: refuse automatic rewrite.
  • Always quote version.

Finish

Report the image path, extracted vs reused state, GPU stack, derived version, and profile update status. Then suggest /jetson-init-source.

Purpose

Materialize Linux_for_Tegra/ on disk by extracting the right Jetson Linux + sample-rootfs tarballs and running apply_binaries.sh with the GPU-stack flag derived from the active target (nvgpu for T234, OpenRM for T264+). Then commit the derived BSP version into the profile's bsp_image: block.

Prerequisites

  • Active target profile resolved per ../../context/target-platform-contract.md.
  • Jetson Linux BSP tarball and matching sample-rootfs tarball staged on disk (e.g. by /jetson-download-bsp or hand-placed).
  • Write access to the workspace Image/ root (or the override bsp_image.root_path).
  • sudo available for apply_binaries.sh.

Limitations

  • Writes only the bsp_image: block; source tree, documents, and carrier profile are owned by sibling skills.
  • Refuses to overwrite an existing Linux_for_Tegra/ without explicit user direction.
  • Does not download tarballs; rely on /jetson-download-bsp or hand-stage the inputs.

Troubleshooting

  • apply_binaries.sh exits non-zero — re-read its console output; most failures are missing sudo, missing rootfs tarball, or wrong GPU stack flag for the SoC generation.
  • nv_tegra_release absent after extract — extraction stopped early; verify tarball integrity and rerun.
  • Recorded version disagrees with the tarball filename — the tarball was renamed; trust the value parsed from Linux_for_Tegra/nv_tegra_release over filenames.
  • Different recorded root_path already in profile — refuse and ask the user to confirm before overwriting.

References

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Jetson Init Image AI skill do?

Extract Jetson Linux + sample-rootfs tarballs and run apply_binaries.sh for the active target, then record bsp_image in the profile. Use after jetson-init-target; not for source-tree setup.

Why use Jetson Init Image on TypingMind?

Because you install it once and use it with any model. Jetson Init Image 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 Jetson Init Image in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/NVIDIA-AI-IOT/jetson-bsp-skills/tree/main/skills/jetson-init-image. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Jetson Init Image?

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 Jetson Init Image?

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

Is the Jetson Init Image AI skill free?

Yes. It is published on GitHub by NVIDIA-AI-IOT under the Apache-2.0 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 👇