Create and modify NeMo AutoModel training and evaluation recipes, including YAML structure, builders, and execution flow.

Test system for Megatron-LM. Covers test layout, recipe YAML structure, adding and running unit and functional tests, golden values, marker filters, and CI parity.

Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.

Linting and formatting for Megatron-LM. Covers running autoformat.sh, tools (ruff, black, isort, pylint, mypy), and code style rules.

Add EAGLE-3 or draft-model speculative decoding to a Jetson vLLM server when TPOT is the bottleneck.

Use when you need to print Jetson device info (module model, L4T version, kernel, OS version, current power mode) from a running Jetson target. This is an example skill.

Bind pre-downloaded Jetson reference docs (developer guide, design guide, pinmux, schematics) into the active profile documents block. Use after staging docs on disk; not for downloading.

Author a new Jetson target-platform profile (reference_devkit + optional custom_carrier) and update the active pointer. Use to create a target; not for switching existing profiles.

Plan and apply safe Jetson headless-mode changes to reclaim GUI and daemon memory.

Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.

Enable/disable Jetson USB2/USB3 SS ports via kernel-DT overlay. Do NOT use for UPHY lane allocation or ODMDATA edits.

Use when you need to add, remove, edit, list, or change the boot default of an nvfancontrol fan profile on a Jetson/Tegra (Orin, Thor) target. Triggers: edit fan profile, tune fan curve.

Verify host requirements and run `workflows/agentic/setup.sh`. Use when asked to set up, install, or bootstrap the agentic workflow, or hits missing `.venv`, third-party checkout, or engine errors.

Edit an env's scene in place — objects, cameras, task, success bounds, randomization. Use when asked to edit a scene or launch/run/open an env in edit mode (`--bridge`), incl. a just-created env.

Replay a recorded HDF5 episode inside Isaac Sim for visual verification. Use when the user asks to replay, play back, or step through an HDF5 recording.

Expand an HDF5 recording by cloning trajectories with action/state noise. Use when asked to mimic, expand, or augment a dataset; not for recording new demos (use [[i4h-workflow-dataset-teleop]]).

Convert an agentic HDF5 recording into a LeRobot dataset (parquet, meta, videos). Use when asked to convert HDF5, prepare for training, or export to LeRobot; not for viewing — use [[i4h-lerobot-viz]].

Use a VLM to verify whether each episode satisfies the env's task description. Use when the user asks to annotate, label episodes, filter demos, or gate finetuning on a success classifier.

Create a new agentic env by forking an existing env. Use for new env/task scaffolding, not scene edits or baking.

Launch the interactive Slang fluoroscopy viewport with XPBD catheter physics. Use when asked to open the viewport, teleop a catheter, or demo fluoro navigation.