New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Onboard Jetpack5 Inference Backends

by EGalahad in EGalahad/sim2real

Install, convert, debug, and benchmark sim2real ONNX GPU and TensorRT inference backends on onboard JetPack 5 Orin hosts such as g1-cable.

No licenceAuto-check passedAI & LLM Engineering

Install Onboard Jetpack5 Inference Backends

skills CLI
$ npx skills add EGalahad/sim2real --skill onboard-jetpack5-inference-backends -a claude-code

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

GitHub CLI
$ gh skill install EGalahad/sim2real onboard-jetpack5-inference-backends --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/EGalahad/sim2real.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/onboard-jetpack5-inference-backends .claude/skills/onboard-jetpack5-inference-backends && 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
onboard-jetpack5-inference-backends
GitHub stars
146
Token cost
~1.1k tokens
SKILL.md length
405 words
Files
4 (incl. scripts, references)
Skills in repo
3
Repo updated
First seen
Licence
None found

At a glance

Install, convert, debug, and benchmark sim2real ONNX GPU and TensorRT inference backends on onboard JetPack 5 Orin hosts such as g1-cable.

  • Works in 8 steps: Confirm the host is JetPack 5 → Keep the default project uv env… → Use the Python 3.8 compatibility source… → …
  • A task mentions JetPack 5
  • SKILL.md covers Workflow, Backend Choice, Conversion Commands and Benchmark Commands, plus 1 more section
  • Runs Python scripts from its folder; calls python, python3 and rsync; reaches github.com

What it does

Onboard Jetpack5 Inference Backends is an agent skill from EGalahad/sim2real. Install, convert, debug, and benchmark sim2real ONNX GPU and TensorRT inference backends on onboard JetPack 5 Orin hosts such as g1-cable. Use when a task mentions JetPack 5, L4T R35, onboard Orin, onnx-gpu, CUDAExecutionProvider, TensorRT 8.5, policy ONNX conversion, or sim2real inference benchmark failures on the robot computer.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including scripts and reference files (for example `agents/openai.yaml`, `references/install-and-convert.md` and `scripts/prepare_jetpack5_onnx.py`).

It sits in AI & LLM Engineering, covering LLM inference and serving. It works with NVIDIA AI Platform, ONNX and Python.

When your agent uses it

  • A task mentions JetPack 5
  • CUDAExecutionProvider
  • Policy ONNX conversion
  • Sim2real inference benchmark failures on the robot computer

Example prompts

  • “/onboard-jetpack5-inference-backends”

Requirements

  • Python 3

Workflow steps

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

  1. Confirm the host is JetPack 5
  2. Keep the default project uv env separate. JetPack 5 GPU inference uses a
  3. Use the Python 3.8 compatibility source branches for runtime code
  4. Do not spend time trying to force the JetPack 5 NVIDIA inference stack into
  5. For install details, read references/install-and-convert.md.
  6. For ONNX conversion, run scripts/prepare_jetpack5_onnx.py from this skill.
  7. Benchmark with scripts/test_policy_inference.py on the onboard host.
  8. If deployment scripts sync to the robot, protect .venv*/, .plan, and

What it can do on your machine

Read from SKILL.md and the folder at commit 73b3bec. 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

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python
    • python3
    • rsync

    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:

    • github.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

Onboard Jetpack5 Inference Backends loads about 1.1k tokens when it runs, and up to ~2.9k if it reads all its reference files. Until then it costs about 92 tokens; SKILL.md has 405 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~92
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.9k

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); the scripts in this folder are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 405 words (~1,092 tokens).

“Use this skill for sim2real policy inference work on JetPack 5 / L4T R35 onboard Orin machines.”

— opening of SKILL.md by EGalahad
name
onboard-jetpack5-inference-backends

Read the full SKILL.md on GitHub

Files

SKILL.md and 3 other files (scripts, references) in .agents/skills/onboard-jetpack5-inference-backends of EGalahad/sim2real.

  • SKILL.md
  • agents/openai.yaml
  • references/install-and-convert.md
  • scripts/prepare_jetpack5_onnx.py

Open the folder on GitHubat commit 73b3bec

Compare with similar skills

Onboard Jetpack5 Inference Backends 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.

Onboard Jetpack5 Inference Backends compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Onboard Jetpack5 Inference Backends this skillEGalahad/sim2real146—~1.1kAutomated safety check: PassNone
Dstack Prototypingdstackai/dstack2.3k—~1.6kAutomated safety check: PassMPL-2.0
TensorRT-LLM InferenceOrchestra-Research/AI-Research-SKILLs13k4 repos~1.3kAutomated safety check: PassMIT
Gguf QuantizationOrchestra-Research/AI-Research-SKILLs13k3 repos~2.6kAutomated safety check: PassMIT
Engine Performancescragnog/HOT-Step-CPP174—~4.9kAutomated safety check: PassMIT
SGLang Structured ServingOrchestra-Research/AI-Research-SKILLs13k2 repos~2.9kAutomated safety check: PassMIT

Similar skills

  • Dstack Prototyping

    dstackai/dstack

    Use with the dstack skill for model-serving work when the image, serving command, resources, backend/fleet choice, or service behavior is not proven.

    2.3k GitHub stars~1.6k tokensUpdated 2 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

  • Gguf Quantization

    Orchestra-Research/AI-Research-SKILLs

    GGUF format and llama.cpp quantization for efficient CPU/GPU inference.

    13k GitHub starsUsed in 3 repos~2.6k tokens
    AI & LLM EngineeringAuto-check passed

  • Engine Performance

    scragnog/HOT-Step-CPP

    Explains where HOT-Step generation time goes (LM/DiT/VAE), how the TensorRT paths activate, how to benchmark from logs, and which knobs trade quality for speed.

    174 GitHub stars~4.9k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed

  • SGLang Structured Serving

    Orchestra-Research/AI-Research-SKILLs

    Covers serving LLMs with SGLang, whose RadixAttention reuses cached prefixes, and constraining output to JSON, regex or grammar for agent and tool-calling workloads.

    13k GitHub starsUsed in 2 repos~2.9k tokens
    AI & LLM EngineeringAuto-check passed

  • Vllm Deploy Simple

    vllm-project/vllm-skills

    Quick install and deploy vLLM, start serving with a simple LLM, and test OpenAI API.

    102 GitHub stars~1.6k tokensUpdated 6 mo ago
    AI & LLM EngineeringAuto-check passed

More from EGalahad/sim2real

  • Configure G1 Sim2real

    EGalahad/sim2real

    Install, repair, and verify sim2real on G1 robot computers. An agent skill from EGalahad/sim2real.

    146 GitHub stars~1.5k tokensUpdated 13 days ago
    Auto-check passed

  • Adapt Policy To Sim2real

    EGalahad/sim2real

    Adapt a policy trained in any external codebase into the sim2real codebase for integrated sim2sim/deploy by tracing the training observation/action implementation, exporting one complete ONNX…

    146 GitHub stars~3.4k tokensUpdated 13 days ago
    Auto-check passed

Works with

Categories

Questions about Onboard Jetpack5 Inference Backends

What does Onboard Jetpack5 Inference Backends do?

Install, convert, debug, and benchmark sim2real ONNX GPU and TensorRT inference backends on onboard JetPack 5 Orin hosts such as g1-cable. Onboard Jetpack5 Inference Backends is an agent skill from EGalahad/sim2real. Install, convert, debug, and benchmark sim2real ONNX GPU and TensorRT inference backends on onboard JetPack 5 Orin hosts such as g1-cable.

When should I use Onboard Jetpack5 Inference Backends?

Onboard Jetpack5 Inference Backends fits situations like: A task mentions JetPack 5; CUDAExecutionProvider; policy ONNX conversion; sim2real inference benchmark failures on the robot computer.

How do I install Onboard Jetpack5 Inference Backends in Claude Code?

Run `npx skills add EGalahad/sim2real --skill onboard-jetpack5-inference-backends -a claude-code`. Or copy the skill folder (.agents/skills/onboard-jetpack5-inference-backends in EGalahad/sim2real) into .claude/skills/onboard-jetpack5-inference-backends in your project. Claude Code loads it when a task matches its description.

How do I install Onboard Jetpack5 Inference Backends in Codex?

Run `npx skills add EGalahad/sim2real --skill onboard-jetpack5-inference-backends -a codex`. Or copy the skill folder (.agents/skills/onboard-jetpack5-inference-backends in EGalahad/sim2real) into .agents/skills/onboard-jetpack5-inference-backends in your project. Codex loads it when a task matches its description.

Can I use Onboard Jetpack5 Inference Backends 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 EGalahad/sim2real --skill onboard-jetpack5-inference-backends -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/onboard-jetpack5-inference-backends, .gemini/skills/onboard-jetpack5-inference-backends, .github/skills/onboard-jetpack5-inference-backends and .opencode/skills/onboard-jetpack5-inference-backends in your project.

What does Onboard Jetpack5 Inference Backends need to run?

Going by SKILL.md and its folder, Onboard Jetpack5 Inference Backends needs Python for the scripts in its folder and the command-line tools its instructions call (python, python3 and rsync). Our summary lists: Python 3.

Does Onboard Jetpack5 Inference Backends access the network?

SKILL.md names 1 domain. In commands or code: github.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Onboard Jetpack5 Inference Backends 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Onboard Jetpack5 Inference Backends use?

No licence was found for Onboard Jetpack5 Inference Backends or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Onboard Jetpack5 Inference Backends use?

About 1.1k tokens (SKILL.md is roughly 4.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.8k tokens, read only when the agent opens those files.

What are the alternatives to Onboard Jetpack5 Inference Backends?

Skills that share tags, products or a category with Onboard Jetpack5 Inference Backends: Dstack Prototyping (dstackai/dstack, 2.3k stars), TensorRT-LLM Inference (Orchestra-Research/AI-Research-SKILLs, 13k stars), Gguf Quantization (Orchestra-Research/AI-Research-SKILLs, 13k stars) and Engine Performance (scragnog/HOT-Step-CPP, 174 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Onboard Jetpack5 Inference Backends?

EGalahad (a GitHub user) maintains it in EGalahad/sim2real, which has 146 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on September 28, 2026.

Source: EGalahad/sim2real on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.