Physical AI Context

SkillAI & models

Use for Claude Code reviews that need robotics, simulation, GPU-routing, sim-to-real, or BDD100K pipeline domain context.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the Physical AI Context skill

What this skill tells your AI

The instructions your AI receives, as published by nebius/nebius-physical-ai in skills/atomic/physical-ai-context/SKILL.md and read by ahel’s review.

Sim-to-real pipeline:

  1. RL teacher policy in Genesis.
  2. Visual demos.
  3. SimToLeRobot adapter.
  4. Student policy in LeRobot.
  5. Evaluation in Genesis.

Isaac Lab requires RT cores: L40S or RTX Pro 6000. H100 and H200 do not have RT cores.

Genesis serverless RL teacher training works. Visual demo generation is blocked on EGL/DRI device access in containers.

LeRobot is Tier 1 validated on B300. SONIC, GR00T, Isaac Lab, and Cosmos are vendor-paced on NVIDIA CUDA 13 alignment.

Route SONIC to H100; L40S on-demand capacity is effectively zero for the required preset.

The BDD100K demo pipeline is the reference end-to-end workflow. workflows/testing/bdd100k-pipeline.yaml is the canonical YAML.

Key claim: one YAML file describes a full Physical AI pipeline; SkyPilot orchestrates it on Nebius; results complete in about 30 minutes on a single H100.

Signals

GitHub stars
28
Forks
15
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
physical-ai-context
Source
github.com/nebius/nebius-physical-ai