メニュー
Get set up to build on the NVIDIA xr-ai stack (XR AI / DeviceIOHub). Use when a user asks to install, clone, or do initial setup of xr-ai; not for routine work in an already-set-up clone.
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/NVIDIA/xr-ai --skill getting-startedコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
Manage a user-provided inbox of NVIDIA XR-AI pull request reviews and provide convenient overall status. Use when the user sends multiple PRs to review, asks what reviews remain, requests a review-status summary, asks to check for new feedback or commits, resumes several in-flight reviews, or authorizes a batch of review comments. Track each PR independently from intake through re-review, refresh GitHub state, use bounded subagents for analysis, and apply the comment-only XR-AI review contract without ever approving automatically.
Review NVIDIA XR-AI pull requests with strict change-scope discipline and independent subagent verification. Use when inspecting, re-reviewing, drafting feedback for, or posting a review on an XR-AI PR. Verify the PR description, diff, surrounding code, tests, scope, and existing reviews; report only change-caused blockers and nits in one top-level comment; route pre-existing or unrelated problems to self-contained follow-up work; and never approve automatically.
SKILL.md を表示中
| name | getting-started |
| description | Get set up to build on the NVIDIA xr-ai stack (XR AI / DeviceIOHub). Use when a user asks to install, clone, or do initial setup of xr-ai; not for routine work in an already-set-up clone. |
Pointers only; the linked docs hold the procedures. Paths are relative to the repo root, so clone before following them.
Ask the user, then tailor the pointers below to the answers.
main. This should match the ref this skill was fetched from; re-fetch the
skill from the chosen ref if it does not. Releases that predate the skill
bank are not covered: with the user's OK, use main for both this skill
and the checkout. The answer selects both the git ref to check out and the
version of the docs site to read. Use
https://nvidia.github.io/xr-ai/main/ for main, or replace main with
the selected release tag. https://nvidia.github.io/xr-ai/ opens the
latest published release.https://nvidia.github.io/xr-ai/<ref>/getting_started/requirements.html,
including the VRAM table. Replace <ref> with main or the selected
release tag.docs/source/components/ai-services.md (section "Hosting models on
NVIDIA NIM") and docs/source/getting_started/credentials.md.git clone https://github.com/NVIDIA/xr-ai.git, then check out
the ref chosen above (latest release tag, run in the clone:
git tag --list 'v*' | python3 .github/scripts/select_latest_docs_release.py;
it prefers stable releases over prereleases, matching what the docs site
serves).AGENTS.md first. Every change must satisfy it,
and its canonical-references table routes deeper topics.docs/source/; published versioned site at
https://nvidia.github.io/xr-ai/.agent-samples/simple-vlm-example/, the one to study
and copy.docs/source/guides/adding-a-sample.md, full
boilerplate templates.https://nvidia.github.io/xr-ai/<ref>/getting_started/quickstart.html, with
<ref> replaced as above. Start agent-samples/model-servers and wait for
it to report readiness before starting agent-samples/simple-vlm-example
or another agent sample.