メニュー
Use when working on SONIC whole-body-control training, export, evaluation, serving, GPU routing, validation, or CUDA alignment.
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。
SOC 職業分類に基づく
Use when ingesting, validating, curating, or querying production sensor data as a versioned dataset-of-record, or wiring the dataset-ingest-curate workflow.
Use when generating adversarial scenarios via RL, ranking mined failures of a policy-under-test, or wiring the adversarial-scenario-hardening workflow.
Use when navigating the Cosmos3 integration in NPA or locating upstream Cosmos3 framework files, defaults, scripts, configs, recipes, and docs.
Use when Cosmos3 setup, fetch, inference, CUDA, uv, Docker, Hugging Face, GitHub, NGC, or checkpoint staging fails in NPA or in an upstream Cosmos framework checkout.
Use when setting up Cosmos3 access through NPA, checking source or Hugging Face reachability, staging the public Cosmos3 framework and checkpoint cache, or deciding which NPA workflow to use before inference.
Use for Claude Code reviews that need robotics, simulation, GPU-routing, sim-to-real, or BDD100K pipeline domain context.
| name | sonic |
| description | Use when working on SONIC whole-body-control training, export, evaluation, serving, GPU routing, validation, or CUDA alignment. |
Use this skill for NVIDIA GEAR-SONIC whole-body-control workbench changes, including standalone training, export, evaluation, serving, image routing, and workflow composition with retargeting or MJLab.
Confirm the current CLI surface before editing:
npa workbench sonic --help
Use train for policy training, export for export artifacts, eval for
evaluation, and serve for runtime serving. Use deploy, status, and
list for operational lifecycle.
Route first-party SONIC images through
npa/src/npa/deploy/sonic_image_manifest.json; do not hardcode image tags in
workflows or docs.
Keep S3 paths run-scoped so retraining and re-evaluation do not overwrite previous artifacts.
deploy, train, export, eval, serve, status, and list.npa/src/npa/workflows/skypilot/, including
sonic-train-standalone.yaml, sonic-export.yaml, sonic-eval.yaml,
sonic-export-eval.yaml, and sonic-locomotion-finetuning.yaml.npa-sonic:0.1.2 image for L40S VM targets.npa-sonic:0.1.2-k8s image for RTX PRO 6000 Blackwell
Kubernetes targets with NVIDIA GPU Operator mounted drivers.SONIC_GPU_TYPE and SONIC_IMAGE_VARIANT aligned with the image
manifest. Do not assume one image works across VM and Kubernetes targets.npa/.venv/bin/python -m pytest npa/tests/guardrails/test_skills_index.py -q
The smoke test invokes npa workbench sonic export --help and
npa workbench sonic serve --help so the skill cannot regress to the older
train/eval-only command list.