Menu
Use when working on LeRobot workbench training, evaluation, serving, inference, dataset conversion, or robot policy workflows.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
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 | lerobot |
| description | Use when working on LeRobot workbench training, evaluation, serving, inference, dataset conversion, or robot policy workflows. |
LeRobot is the default robot policy training framework. It supports ACT, Diffusion Policy, and SmolVLA (and additional VLAs / world models in 0.6.0).
Use it as the data standard and policy interface layer, not as a managed-service competitor to Hugging Face.
| Version | Role | Image tag | Notes |
|---|---|---|---|
| 0.5.1 | Default | npa-lerobot:0.5.1 | Current golden-eval pin; keep for GR00T N1.5 / sim2real policy image parity |
| 0.6.0 | Additional | npa-lerobot:0.6.0 | Lean extras (training,evaluation,pusht,libero); --eval_freq → --env_eval_freq |
Select with --lerobot-version on deploy / serverless train, or override the image with --image .../npa-lerobot:0.6.0.
Canonical manifest: npa/src/npa/deploy/lerobot_version_manifest.json.
Upstream release notes: https://huggingface.co/blog/lerobot-release-v060
API:
POST /trainPOST /evalPOST /servePOST /inferGET /list-checkpointsCLI:
npa workbench lerobot deploy
npa workbench lerobot deploy --lerobot-version 0.6.0
npa workbench lerobot train
npa workbench lerobot train --runtime serverless --lerobot-version 0.6.0 ...
npa workbench lerobot eval
npa workbench lerobot serve
npa workbench lerobot infer
npa workbench lerobot list-checkpoints
Build both image tags:
npa/docker/workbench/lerobot/build.sh --all-versions
# or
npa/docker/workbench/lerobot/build.sh --version 0.6.0
Input format is LeRobotDataset in Hugging Face format. Use the SimToLeRobot adapter to convert Genesis or other simulation outputs.
Output is a policy checkpoint on S3.
npa-lerobot:0.6.0 and run the same golden env/functional smokes with NPA_LEROBOT_VERSION=0.6.0.