This repository also configures its own agents. See what nebius-physical-ai tells them →
Skill Claude CodeCodex
Use when running or modifying Cosmos3 inference through NPA, including Nano diffusion continuation/augmentation, framework generation, prompt/input handling, and effective guardrail or sampling arguments.
Skill Claude CodeCodex
Use when writing, validating, or submitting an npa.workflow/v0.0.1 YAML that runs Cosmos 3 generation (text2image / image2image / text2video / image2video / video2video) in the npa-cosmos3 container. This is the declarative npa.workflow spec, NOT the SkyPilot YAML.
Skill Claude CodeCodex
Use when planning, reviewing, or explaining Cosmos3 supervised fine-tuning and post-training in NPA, including upstream recipes, dataset/checkpoint preparation, and why NPA does not expose post-training as a fake skill command.
Skill Claude CodeCodex
Use when turning an architecture diagram plus a step-by-step write-up into a working npa.workflow/v0.0.1 YAML — parse boxes/arrows/decision-diamonds and numbered steps into states, loops, gates, and catalog toolRefs, then validate/plan until green. Generalizes across sim2real, AV perception, RL, and Cosmos pipelines.
Skill Claude CodeCodex needs its repo
Use on a fresh machine or a new Nebius project to get from zero to a first verified result — an ordered, gated path through install, configure, credential preflight, cheapest-proof workload, then cluster provisioning, with an explicit stop condition at every step.
Skill Claude CodeCodex
Use when inventing a new npa.workflow/v0.0.1 pipeline from the tool catalog — creative stage graphs, loops, gates, and reference YAML output.
Skill Claude CodeCodex
Use when reconstructing real sensor captures into renderable 3D scenes with NVIDIA Omniverse NuRec / the Neural Reconstruction Engine (NRE) on Nebius — COLMAP source conversion to NCore V4, existing NCore V4 input, 3DGUT Gaussian training, renderable USDZ, novel-view rendering, and the Rerun recording the NPA agent…
Skill Claude CodeCodex
Use when onboarding and containerizing a world model (learned action-conditioned simulator — Dreamer/Genie/Cosmos-style latent video prediction) into NPA as a multi-GPU BYOF registry candidate. Generalizes the Open Dreamer onboarding into a reusable playbook — containerize the repo, stage a real dataset, encode the…
Skill Claude CodeCodex needs its repo
Use when evaluating and onboarding an open-source Physical AI solution into the NPA registry/catalog with documented capabilities, BYOF packaging, smoke tests, and live Nebius validation.
Skill Claude CodeCodex
Use when authoring, running, submitting, or viewing the NVIDIA Physical AI Data Factory blueprint on Nebius + SkyPilot (no OSMO) — annotate → Cosmos Transfer augment → Cosmos Evaluator gate → re-label → Cosmos Curator + FiftyOne curate → Rerun visualize — implemented as an npa.workflow that composes existing workbench…
Skill Claude CodeCodex
Use when designing, reviewing, or operating sim-to-real workflows that move data through simulation, policy training, synthetic generation, evaluation, and loop control.
Skill Claude CodeCodex
Operate the compositional 14-stage Sim2Real npa.workflow on Kubernetes through the standard SkyPilot runtime, durable S3 resume ledger, real component images, and artifact audit.
Skill Claude CodeCodex
Use when planning, reviewing, or operating robot policy training across LeRobot, Isaac Lab, SONIC, and workflow YAMLs.
Skill Claude CodeCodex
Use when working on NPA reference workflow specs, runner scripts, cookbooks, customer-adaptable pipeline implementations, or the guarded examples that are not workflow authoring surfaces.
Skill Claude CodeCodex
Reproduce, operate, validate, or troubleshoot the fixed Cosmos3-Super eight-GPU benchmark or isolated single-H200 TP-1 validation through the immutable public vLLM-Omni image.
Skill Claude CodeCodex
Use to run RoboCasa kitchen-task simulation as a first-class NPA workbench tool — Gymnasium task registration, kitchen asset availability, headless EGL environment reset, and random rollouts with video artifacts, through the npa-robocasa service.
Skill Codex
Use when authoring, reviewing, or operating an NPA workflow whose real run outputs should become a reviewable Rerun .rrd recording with factual timelines, provenance, declared artifacts, and independent content validation.
Skill Claude CodeCodex
Write or review NPA contributions, including workbench agent changes, using the repository's readability, documentation, and anti-pattern rules.
Skill Claude CodeCodex
Use when running, validating or reviewing NVIDIA cuRobo V2 Franka pose planning and complete MotionBenchMaker/MPiNets benchmarks on CUDA, with factual joint/FK Rerun artifacts.
Skill Claude CodeCodex
Run or review the native Ray Train synthetic distributed CUDA reference, its S3 checkpoints, optimizer recovery, and factual Rerun metrics.
Skill Claude CodeCodex
Choose and operate the supported Ray paths in Nebius Physical AI: native Jobs/Core development, guarded Train V2, Cosmos3 native Serve, or Fleet KubeRay.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: