jetson-quick-start
Entry skill for Jetson / IGX BSP customization. Asks one core click-to-select setup questionnaire and passes prefilled answers to downstream setup skills.
npx skills add NVIDIA/skills --skill jetson-quick-start --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Jetson-quick-start acts as an intake form and dispatcher for BSP customization. It does not perform download, extraction, or materialization itself. It selects a downstream setup path, gathers core answers through a core questionnaire, and forwards prefilled answers to downstream skills that perform the actual work.
How it works
- It defines Modes (Auto Setup, Guided Setup, Use Existing Workspace) and a separate exit option (cancel).
- It prints a disclaimer block exactly once, then shows an AskUserQuestions disclaimer form requiring acceptance.
- After disclaimer acceptance, it opens the core AskUserQuestions questionnaire to obtain a single gate of routing-critical fields: mode, active_platform, bsp_release, and custom_carrier.
- It inspects target profiles and catalogs to present platform choices, but requires user submission before downstream operations.
- It normalizes submitted answers into a quick_start_prefill bundle, containing mode, target (active_platform, custom_carrier), and download (bsp_release).
- It builds a downstream plan from quick_start_prefill and passes the relevant subset to each downstream skill, which then handles its own inputs and validation.
- For Use Existing Workspace, it performs checks on workspace paths and preconditions before dispatch.
- It prints a non-blocking execution plan summary prior to invoking downstream skills.
- It may print a Next steps — I/O customization list if carrier-board docs are bound, and then outlines suggested downstream customization skills.
When to use it
Use this skill as the entrypoint for Jetson BSP customization when you want a single, guided questionnaire to determine which downstream setup path to run and to collect core prefill data for downstream skills.
What it can touch
- Downstream skills receive their quick_start_prefill subsets plus the top-level mode. The skill touches downstream planes such as
/jetson-download-bsp,/jetson-init-image,/jetson-init-source,/jetson-link-docs,/jetson-generate-kb, and optional/jetson-derive-carrierdepending on the mode. - It may reference platform lists and BSP release candidates from the catalog as part of the questionnaire process, but does not itself perform downloads or file materialization.
Caveats
- It is explicitly described as a dispatcher/intake form, not a downloader or builder.
- It requires user interaction through the AskUserQuestions UI and does not proceed without a submitted form.
- The text enforces careful handling of disclaimers and routing decisions; it does not bypass gating questions or downstream validation.
- Licensing and authorship are stated as Apache-2.0 and Jetson Team, respectively.
# Quick Start — BSP customization entrypoint `jetson-quick-start` is a dispatcher and intake form. It does not download, extract, materialize sources, bind documents, or derive carrier files. It chooses the setup path, gathers core answers, then hands those answers to the skills that own the actual work. ## Modes Do not ask setup mode in a separate prompt. Include it as the first field in the core
What does the jetson-quick-start skill do?
Entry skill for Jetson / IGX BSP customization. Asks one core click-to-select setup questionnaire and passes prefilled answers to downstream setup skills.
How do I install it?
Run `npx skills add NVIDIA/skills --skill jetson-quick-start --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From NVIDIA/skills, a repository with 2,789 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.