NVlabs

Use for the current YAM full demo, yam_demo.sh, bottle rack, KitKat handover/trash, bowl/can commands, and canonical saved-script commands.

Use for YAM DOF, coordinate directions, tabletop/rack/trash geometry, camera frames, gripper geometry, and contact/placement offsets.

Use for YAM object detection, grasp candidate generation, side/top-down/rim pickup choices, staged gripper close, contact evidence, lift-only checks, and pickup failures.

Use for YAM cuRobo planning/IK failures, no-motion vs real-robot planning mismatch, waypoint robustness sweeps, perturbation testing, and recovery after motion planner failures.

Use for YAM post-release retreat, gripper-open confirmation, home/open recovery, retreat after rack/bin placement, and safe recovery while holding an object after a failed run.

Use for YAM real-robot debugging: saved-script edits, physical runs, artifact inspection, autonomous patch-and-retry loops, and compact runtime context updates.

Use when inspecting YAM logs, videos, SAM3 overlays, observations, planner previews, function-call JSON, result files, or failure evidence.

Use for YAM arm, camera, perception, AnyGrasp, BundleSDF, SAM3, cuRobo, PyRoki, and provider server checks/restarts.

Run end-to-end supervised fine-tuning (SFT) of the Alpamayo-1.5 VLM action model on PAI (with navigation conditioning) or LingoQA (for visual question answering). The agent collects a small set of choices from the user up front (Stage-1 task — nav / vqa /…

Run end-to-end supervised fine-tuning (SFT) of the Alpamayo-1 VLM action model on the Physical AI AV (PAI) dataset. The agent collects a small set of choices from the user up front (PAI chunk range, CoC reasoning toggle, W&B preference, which stage(s) to run,…

Run end-to-end open-loop RL post-training of the Alpamayo VLM action model (Alpamayo 1 or 1.5) on the Physical AI AV (PAI) dataset using Cosmos-RL + GRPO. The agent collects a small set of choices from the user up front (Alpamayo version, reward mode —…

Front-door for COMPASS — training, evaluation, SAGE scene workflows (search / USD conversion / scene registration), and OSMO cloud submission. Use whenever the user mentions training a policy, adding a SAGE scene, evaluating a checkpoint, or running COMPASS…

Diagnose why COMPASS isn't working: container, GPU, activated shell, assets, Isaac Sim init, checkpoint validity. Use whenever the user reports vague COMPASS errors — "training won't start", "something's wrong", "why is this failing" — even without the word…

Onboard a new robot platform to COMPASS: generate robot ArticulationCfg + per-embodiment env_cfg, register in EmbodimentEnvCfgMap, smoke-test the spawn with --num_envs 1. Use whenever the user wants to add a new robot, register an embodiment, or extend…

Optimize AlpaSim Slurm topology throughput using persistent local Prometheus/Grafana telemetry and run artifacts. Use when tuning service GPU placement, replicas_per_container, runtime.nr_workers, endpoint n_concurrent_rollouts, NRE/physics cache sizes, or…

Reviews recent code changes and checks if documentation needs updates. Reads all MD files in root and docs/ to identify stale or missing documentation. Use when completing features, before pushing, or when asked to "check docs", "review documentation", or…

Generate RoboLab task files from natural language descriptions of robot manipulation goals. Use this skill when a user wants to create, write, or generate a new task definition, or asks how to define success conditions, terminations, subtasks, or instructions…

Generate USD scene files for RoboLab from natural language descriptions. Use this skill when a user wants to create a new scene with objects on a table, or asks to arrange objects for a robot manipulation task.

Consolidated ACE-RTL skill for running an iterative generator-reflector-coordinator RTL agent on CVDP. Use for CVDP official repo setup with native or Docker environments, no-cheating benchmark runs, role-based external LLM routing, unique outputs logging,…

Use when CVDP or ACE-RTL native runs need simulator, synthesis, coverage, or license setup before classifying EDA-tool failures as INFRA_SETUP.

Run and operate GraspGenX — a cross-embodiment foundation model for 6-DOF grasp generation. Use when installing GraspGenX (uv or Docker), running inference demos (segmented object point cloud, scene point cloud, or object mesh), choosing a gripper or planner…