Official agent skill

Jetson Download Bsp

by NVIDIA in NVIDIA/skills

Download NVIDIA Jetson Linux BSP artifacts (BSP tarball, sample rootfs, publicsources, x-tools, guides) for the active target.

OfficialApache-2.0Auto-check passedAI & LLM Engineering

Install Jetson Download Bsp

skills CLI
$ npx skills add NVIDIA/skills --skill jetson-download-bsp -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install NVIDIA/skills jetson-download-bsp --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/NVIDIA/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/jetson-download-bsp .claude/skills/jetson-download-bsp && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
jetson-download-bsp
GitHub stars
3.6k
Token cost
~3k tokens
SKILL.md length
1,344 words
Files
5
Skills in repo
390
Repo updated
First seen
Licence
Apache-2.0

At a glance

Download NVIDIA Jetson Linux BSP artifacts (BSP tarball, sample rootfs, publicsources, x-tools, guides) for the active target.

  • Works in 3 steps: Focused prompt — artifact name + file… → Verbatim link dump on the same URL —… → Verbatim dump on a sibling page — Jetson…
  • Not for extraction
  • SKILL.md covers When to invoke, Inputs and outputs, Procedure and Finish, plus 6 more sections
  • Calls curl; reaches docs.nvidia.com

What it does

Jetson Download Bsp is an agent skill from NVIDIA/skills, published by the product's own GitHub organization. Download NVIDIA Jetson Linux BSP artifacts (BSP tarball, sample rootfs, publicsources, x-tools, guides) for the active target. Use for Auto Setup; not for extraction or profile edits.

Its SKILL.md is about 3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files (for example `BENCHMARK.md`, `evals/evals.json` and `skill-card.md`).

It sits in AI & LLM Engineering, covering GPU and accelerator computing. It works with NVIDIA AI Platform and Linux. The repository describes itself as: Agent Skills for NVIDIA products — install into Claude Code, Codex, and other coding agents to run Physical AI, robotics, simulation, CUDA, and RAG workflows end to end. The licence is Apache-2.0.

When your agent uses it

  • Not for extraction
  • Tasks that involve GPU and accelerator computing

Example prompts

  • “/jetson-download-bsp”

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Focused prompt — artifact name + file type.
  2. Verbatim link dump on the same URL — *"list every hyperlink, text
  3. Verbatim dump on a sibling page — Jetson Linux archive, JetPack

What it can do on your machine

Read from SKILL.md and the folder at commit 14a98ae. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • curl

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • docs.nvidia.com

    Also links to:

    • developer.nvidia.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Jetson Download Bsp loads about 3k tokens when it runs. Until then it costs about 51 tokens; SKILL.md has 1,344 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~51
When it runs · the whole SKILL.md, loaded when a task matches
~3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from NVIDIA/skills at commit 14a98ae, republished under its Apache-2.0 licence (© NVIDIA). 1,344 words, ~2,951 tokens.

Download SKILL.mdSave it as .claude/skills/jetson-download-bsp/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
jetson-download-bsp
description
Download NVIDIA Jetson Linux BSP artifacts (BSP tarball, sample rootfs, public_sources, x-tools, guides) for the active target. Use for Auto Setup; not for extraction or profile edits.
version
0.0.1
license
Apache-2.0
metadata.data-classification
public
metadata.author
Jetson Team
metadata.tags
setup, bootstrap, download
metadata.domain
setup

Download BSP Artifacts

jetson-download-bsp owns network fetches for the Auto Setup path. It does not extract archives, initialize source trees, register documents, or edit the active target profile. Those remain owned by jetson-init-image, jetson-init-source, and jetson-link-docs.

When to invoke

  • /jetson-quick-start selected Auto Setup.
  • The user wants NVIDIA BSP artifacts downloaded into the current workspace before running setup skills.

Inputs and outputs

Resolve the active profile per ../../context/target-platform-contract.md. Refuse if no active profile exists.

Follow the shared quick_start_prefill contract. When invoked by /jetson-quick-start, this skill consumes quick_start_prefill.mode and quick_start_prefill.download.bsp_release as the requested release when present. Missing or invalid prefilled values are not fatal, but a concrete release is required before any download starts.

Use the workspace root as the parent of target-platform/. Place files where downstream setup skills already search:

ArtifactDestination
Jetson Linux BSP tarball<bsp_image.root_path or workspace/Image>/Jetson_Linux_R<ver>_aarch64.tbz2
Sample rootfs tarball<bsp_image.root_path or workspace/Image>/Tegra_Linux_Sample-Root-Filesystem_R<ver>_aarch64.tbz2
public_sources.tbz2<workspace>/Downloads/public_sources.tbz2
x-tools.tbz2<workspace>/Downloads/x-tools.tbz2
Developer Guide<documents.root_path or workspace/Documents>/
User Guide<documents.root_path or workspace/Documents>/

Do not write bsp_image:, source:, or documents: blocks. The next setup skills will register derived metadata after extraction or user confirmation.

Procedure

Resolve target release

Fetch the release list from: https://developer.nvidia.com/embedded/jetson-linux-archive

From the archive and linked release pages, list concrete releases that explicitly support the active platform. Let the user choose a concrete Jetson Linux / L4T release token (R36.4.4, 36.4.4, 38.2, 38.2.1, 38.4, etc.); do not proceed with a family placeholder such as R38.x. A concrete release token is an optional leading R followed by two or three numeric dotted components. Preserve the token exactly as the official page presents it; do not add .0, remove a patch component, or otherwise normalize it. Sort release choices by dotted numeric order descending (newest first), comparing the components that are present; keep source-provided recommendations in descriptions.

Resolve quick_start_prefill.download.bsp_release as follows:

  • Concrete and supported: continue with that release.
  • Missing, skip, blank, or a family placeholder (R38.x, 38.x): show supported concrete releases and ask the user to choose one.
  • Concrete but unsupported or ambiguous: stop before artifact discovery and show the active platform, requested BSP release, supported concrete releases, and source archive or release page.

Never auto-substitute the requested release with a supported release, even when there is only one supported option.

For unsupported or ambiguous prefill, ask with the shared User input prompt style, to choose exactly one click-to-select action:

  • pick_supported_release — user selects one supported concrete release.
  • confirm_override — user confirms the incompatible release and enters an override reason.
  • cancel — stop with no downloads.

Do not continue to "Locate release artifacts" until the selected release is concrete and supported, or the user explicitly confirms override. Record any override reason in the final summary. If the user cancels, stop with no downloads. Do not claim support unless the archive or linked release page explicitly lists the active platform.

Discovery retries

For every artifact WebFetch in "Resolve target release" and "Locate release artifacts" (BSP, rootfs, public_sources.tbz2, x-tools.tbz2, Developer Guide, User Guide), try 3 attempts before marking it missing:

  1. Focused prompt — artifact name + file type.
  2. Verbatim link dump on the same URL — "list every hyperlink, text and href, no filtering". Accept product-specific names and .html indexes.
  3. Verbatim dump on a sibling page — Jetson Linux archive, JetPack downloads, or https://docs.nvidia.com/jetson/archives/r<ver>/.

Only after all 3 fail, route to user-paste / skip. Never fabricate URLs.

Locate release artifacts

Follow links from the selected release page. Never construct NVIDIA download URLs by string concatenation.

Required artifacts:

  • Jetson Linux BSP image tarball.
  • Tegra Linux sample root filesystem tarball.
  • public_sources.tbz2.
  • x-tools.tbz2 / Crosstool-NG Toolchain gcc matching the selected BSP release.
  • Developer Guide.
  • User Guide.

If a guide is not available as a direct file link, accept the release documentation URL as the artifact and record it in the final summary. If the toolchain is listed on a JetPack downloads page instead of the release page, follow the official page link and match the selected BSP release; do not synthesize the URL from a release number. Do not proceed until each required artifact is downloaded, already present at its destination, represented by a URL, or explicitly skipped by the user.

Show the fetch plan

Before changing the workspace, print a plan with:

  • selected release and release page URL;
  • active platform summary (reference_devkit.name, optional custom_carrier.name, and flash_config);
  • source URL and destination path, or documentation URL, for every artifact;
  • any existing destination file that will be reused;
  • any artifact that requires browser/EULA handling instead of curl.

Default to Download all. Do not ask an extra confirmation when every required artifact is downloadable, already present for reuse, or a documentation URL to record. Print the plan and continue to disk-space verification.

Still stop and ask before side effects in any of these cases:

  • the release required an incompatibility override;
  • a required artifact is missing and needs user-paste / skip;
  • a destination file would be overwritten rather than reused;
  • the artifact requires browser/EULA handling;
  • disk-space verification fails or cannot be computed safely.
Show full SKILL.md (532 more words)Show less
Verify disk space

Sum Content-Length across artifacts to download (curl -sI <url>); refuse if df -B1 --output=avail <workspace> headroom < sum × 1.2. Skip URL-only artifacts.

Download safely

Create destination directories as needed. For direct file links, use a temporary .part path and rename only after success:

bash
mkdir -p "<destination-dir>"
curl -fL --retry 3 --retry-all-errors --retry-delay 5 -o "<destination>.part" "<artifact-url>"
mv "<destination>.part" "<destination>"

If a destination file already exists and is non-empty, reuse it by default after showing its path. Ask before overwriting. If an artifact download fails due to 404, 401/403, EULA/browser authentication, or a network error, stop and show the artifact URL plus expected destination path. Ask the user to download the file manually, skip that artifact, or cancel. Do not synthesize alternate NVIDIA URLs.

Validate filenames

Before finishing, verify the BSP and rootfs tarball filenames contain the exact R<ver> token from the official artifact URL or filename discovered in Step 2. <ver> may have two or three numeric components (R38.2, R38.2.1, R38.4, etc.). Do not infer R38.2.0 from R38.2, and do not assume that a selected two-component release maps to a three-component tarball name:

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

Verify public_sources.tbz2 is a bzip2 tarball when it exists locally:

bash
file -b "<workspace>/Downloads/public_sources.tbz2" | grep -q "bzip2 compressed"

Verify x-tools.tbz2 the same way when it exists locally:

bash
file -b "<workspace>/Downloads/x-tools.tbz2" | grep -q "bzip2 compressed"

Warn, but do not fail, if document filenames differ from the release version; NVIDIA documentation naming is less consistent than tarballs.

Finish

Report the selected release, downloaded/reused/skipped artifacts, and exact local paths. Then hand back to the caller with:

  1. /jetson-init-image
  2. /jetson-init-source
  3. /jetson-link-docs

Gotchas

  • Keep this skill download-only; extraction belongs to jetson-init-image and jetson-init-source.
  • Put image tarballs in the image root, not Downloads/, because jetson-init-image searches the image root, workspace root, and current directory.
  • Put public_sources.tbz2 in Downloads/ because jetson-init-source auto-discovers that path for Branch A.
  • Put x-tools.tbz2 in Downloads/ because jetson-init-source auto-extracts that path and writes the resulting source.toolchain prefix.
  • The User Guide maps to documents.bsp_user_guide in the profile schema (alongside bsp_developer_guide). jetson-link-docs writes it when the user confirms; this skill only stages the file or URL.

Purpose

Stage the four NVIDIA-shipped artifacts (BSP, sample rootfs, public_sources, x-tools) plus the Developer / User Guides at the exact paths the Setup skills look in, so /jetson-init-image, /jetson-init-source, and /jetson-link-docs can run offline once this skill is done.

Prerequisites

  • Active target profile resolved per ../../context/target-platform-contract.md.
  • Network access to developer.nvidia.com and the Jetson Linux archive page.
  • Workspace layout with the expected Image/, Source/, Downloads/, and Documents/ roots (default workspace shape).

Limitations

  • Download-only; never extracts, runs apply_binaries.sh, mounts sources, registers documents, or mutates the active profile.
  • Release selection is bounded to entries published on the official Jetson Linux archive; pre-release or internal builds are out of scope.
  • No retry / mirror logic — failures are surfaced to the user, not silently retried.

Troubleshooting

  • Release page not reachable — check VPN / proxy; do not invent fallback URLs. Stop and report.
  • Archive name mismatch with active platform — verify the release declares the active reference devkit; if not, ask the user to pick a supported release or switch target via /jetson-set-target.
  • public_sources.tbz2 missing on archive — some releases ship it as a separate page; follow the release-page link rather than guessing the URL.
  • Existing files in the destination — refuse to overwrite without confirmation; downloads must be idempotent at the user's discretion.

References

© NVIDIA, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 4 other files in skills/jetson-download-bsp of NVIDIA/skills.

  • SKILL.md
  • BENCHMARK.md
  • evals/evals.json
  • skill-card.md
  • skill.oms.sig

Open the folder on GitHubat commit 14a98ae

Compare with similar skills

Jetson Download Bsp next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Jetson Download Bsp compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Jetson Download Bsp this skillNVIDIA/skills3.6k—~3kAutomated safety check: PassApache-2.0
Graphsignalgraphsignal/graphsignal257—~6.3kAutomated safety check: PassApache-2.0
LLM Torch Profiler Trace AnalysisBBuf/AI-Infra-Auto-Driven-SKILLS938—~2.8kAutomated safety check: PassNone
Cv DeployLMIXR/CV_Deployment_skill188—~547Automated safety check: PassNone
TensorRT-LLM InferenceOrchestra-Research/AI-Research-SKILLs13k4 repos~1.3kAutomated safety check: PassMIT
Triton SkillslowlyC/agent-gpu-skills169—~1.3kAutomated safety check: PassMIT

Similar skills

  • Graphsignal

    graphsignal/graphsignal

    Profile AI inference workloads (vLLM, SGLang, TensorRT-LLM, PyTorch, any GPU application) with the Graphsignal profiler and read the results from its local /signals JSON endpoint.

    257 GitHub stars~6.3k tokensUpdated today
    AI & LLM EngineeringAuto-check passed
  • LLM Torch Profiler Trace Analysis

    BBuf/AI-Infra-Auto-Driven-SKILLS

    Analyzes Torch Profiler traces from SGLang, vLLM and TensorRT-LLM servers into kernel attribution, overlap and fusion tables.

    938 GitHub stars~2.8k tokensUpdated 5 days ago
    AI & LLM EngineeringAuto-check passed
  • Cv Deploy

    LMIXR/CV_Deployment_skill

    基于 helpfile 工程经验,协助 agent 配置 CV 主机和边缘设备环境、编译视觉与推理依赖、接入摄像头视频并打包部署服务。适用于 Ubuntu、CentOS、Windows、macOS、Jetson、树莓派和 RK3399 的 CV 工程实施与故障排查,以及相关移动端配套工具;模型训练和纯算法设计不属于本技能主线。

    188 GitHub stars~547 tokensUpdated 11 days ago
    AI & LLM EngineeringAuto-check passed
  • TensorRT-LLM Inference

    Orchestra-Research/AI-Research-SKILLs

    Optimizes and serves LLMs on NVIDIA GPUs with TensorRT-LLM, covering quantization, in-flight batching, multi-GPU parallelism and the trtllm-serve command.

    13k GitHub starsUsed in 4 repos~1.3k tokens
    AI & LLM EngineeringAuto-check passed
  • Triton Skill

    slowlyC/agent-gpu-skills

    Write, debug, and optimize Triton and Gluon GPU kernels from local upstream tutorials, production kernels, language definitions, and compiler source.

    169 GitHub stars~1.3k tokensUpdated 2 mo ago
    AI & LLM EngineeringAuto-check passed
  • Megatron-Core LLM Training

    Orchestra-Research/AI-Research-SKILLs

    Sets up large-scale LLM training with NVIDIA Megatron-Core, choosing tensor, pipeline, data, context and expert parallelism for a given model size and GPU count.

    13k GitHub starsUsed in 2 repos~2.4k tokens
    AI & LLM EngineeringAuto-check passed

More from NVIDIA/skills

All 390 skills in this repo
  • Official

    A skill your agent uses when the user wants to deploy, run, debug, tear down, or call the REST API of the RTVI-CV 2D detection / tracking microservice.

    3.6k GitHub starsUsed in 1 repo~4.5k tokens
    Auto-check passed
  • Official

    Generates, validates, compares and explains HOLOLINK_def.svh macro files for the HSB IP, using bundled Python scripts and asking before it writes anything.

    3.6k GitHub stars~2.9k tokensUpdated today
    Auto-check passed
  • Official

    Runs and validates an end-to-end Mission Control demo in a locally installed Isaac Sim, with a Nova Carter robot driven through a Python server.

    3.6k GitHub stars~4.8k tokensUpdated today
    Auto-check passed
  • Orchestrates defect image generation for PCBA, metal surface and glass inspection with NVIDIA Cosmos AnomalyGen on OSMO, from cold-start Day 0 to real-photo Day 1 labeling.

    3.6k GitHub stars~5k tokensUpdated today
    Auto-check: notes
  • Orchestrates video data augmentation and auto-labeling workflows on OSMO, from flow selection and preflight checks to submission, monitoring and output download.

    3.6k GitHub stars~4.7k tokensUpdated today
    Auto-check: notes
  • Official

    Runs NVIDIA TAO Data Services KPI analysis on object detection results, comparing predictions to ground truth and writing per-class precision, recall and AP to a CSV.

    3.6k GitHub stars~2.7k tokensUpdated today
    Auto-check: notes

Questions about Jetson Download Bsp

What does Jetson Download Bsp do?

Download NVIDIA Jetson Linux BSP artifacts (BSP tarball, sample rootfs, publicsources, x-tools, guides) for the active target. Jetson Download Bsp is an agent skill from NVIDIA/skills, published by the product's own GitHub organization. Download NVIDIA Jetson Linux BSP artifacts (BSP tarball, sample rootfs, publicsources, x-tools, guides) for the active target.

When should I use Jetson Download Bsp?

Jetson Download Bsp fits situations like: not for extraction; tasks that involve GPU and accelerator computing.

How do I install Jetson Download Bsp in Claude Code?

Run `npx skills add NVIDIA/skills --skill jetson-download-bsp -a claude-code`. Or copy the skill folder (skills/jetson-download-bsp in NVIDIA/skills) into .claude/skills/jetson-download-bsp in your project. Claude Code loads it when a task matches its description.

How do I install Jetson Download Bsp in Codex?

Run `npx skills add NVIDIA/skills --skill jetson-download-bsp -a codex`. Or copy the skill folder (skills/jetson-download-bsp in NVIDIA/skills) into .agents/skills/jetson-download-bsp in your project. Codex loads it when a task matches its description.

Can I use Jetson Download Bsp in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add NVIDIA/skills --skill jetson-download-bsp -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/jetson-download-bsp, .gemini/skills/jetson-download-bsp, .github/skills/jetson-download-bsp and .opencode/skills/jetson-download-bsp in your project.

What does Jetson Download Bsp need to run?

Going by SKILL.md and its folder, Jetson Download Bsp needs the command-line tools its instructions call (curl).

Does Jetson Download Bsp access the network?

SKILL.md names 2 domains. In commands or code: docs.nvidia.com; the agent is likely to contact it when it follows the instructions. As links in the text: developer.nvidia.com. This is read from the text; nothing was executed.

Is Jetson Download Bsp safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Jetson Download Bsp use?

Jetson Download Bsp is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Jetson Download Bsp use?

About 3k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Jetson Download Bsp?

Skills that share tags, products or a category with Jetson Download Bsp: Graphsignal (graphsignal/graphsignal, 257 stars), LLM Torch Profiler Trace Analysis (BBuf/AI-Infra-Auto-Driven-SKILLS, 938 stars), Cv Deploy (LMIXR/CV_Deployment_skill, 188 stars) and TensorRT-LLM Inference (Orchestra-Research/AI-Research-SKILLs, 13k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Jetson Download Bsp?

NVIDIA (a GitHub organization, an official publisher) maintains it in NVIDIA/skills, which has 3,555 GitHub stars. The repository holds 390 skills in this directory. The repository was last updated on October 9, 2026.

Source: NVIDIA/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.