Create and validate Earth2Studio data source wrappers (DataSource, ForecastSource, DataFrameSource, ForecastFrameSource) from remote stores.
Create Earth2Studio diagnostic model wrappers for single-step data transformations, including simple derived diagnostics, packaged AutoModel diagnostics, and generative or…
Create Earth2Studio prognostic (time-stepping forecast) model wrappers. Do NOT use for diagnostic models, data sources, or installation.
Use when you need to rebuild the BSP overlay — DT, OOT modules, or kernel — from changes under bsp_sources/. Triggers: build bsp, rebuild dtb, rebuild kernel.
Reclaim DRAM by disabling unused subsystems across MB1 BCT, MB2 BCT, kernel reserved-memory, and SWIOTLB.
Use when the user wants to create a dataset, generate synthetic data, or build a data generation pipeline.
Enforce Input/Output Guardrails at the LLM Gateway layer — PII redaction, Prompt Injection defense, Jailbreak detection, Toxicity filter, and Tool Allow-list.
NVIDIA RAG Blueprint — deploy, configure, troubleshoot, and manage. Handles any RAG action: deploy, install, start, enable, disable, toggle, change, configure, troubleshoot,…
LP, MILP, and QP (beta) with cuOpt — CLI only (MPS files, cuopt_cli). Use when the user is solving LP, MILP, or QP from MPS via command line.
Integrate TileGym kernels into Hugging Face `transformers` models by replacing the library's submodule(s) and certain class(es)' implementations, and patching certain cla — from…
Add a new cuTile GPU kernel operator to TileGym. Covers dispatch registration in ops.py, cuTile backend implementation, __init__.py exports, test creation, and benchmark — from…
Launch the interactive Slang fluoroscopy viewport with XPBD catheter physics. Use when asked to open the viewport, teleop a catheter, or demo fluoro navigation.
Operational guide for enabling Megatron FSDP in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification. — from NVIDIA/skills
Techniques for reducing peak GPU memory in Megatron Bridge — expandable segments, parallelism resizing, activation recompute, CPU offloading constraints, and common OOM f — from…
Summarize a video by calling the VLM NIM or the Long Video Summarization (LVS) microservice directly.
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.
Nsight Systems (nsys) CLI for system-level timeline profiling. Use when the user wants to run nsys profile, analyze .nsys-rep reports, use nsys stats/analyze/recipe commands,…
Use to help users get started with Nemo Gym reward profiling. Covers the basic ng_run, ng_collect_rollouts, and ng_reward_profile workflow, repeated rollouts, materialized inputs,…
PointPillars for 3D object detection from LiDAR point clouds. Encodes point clouds into a pseudo-image via a
Cut a new semver release — bump all version strings via bump-version.ts, open a release PR, and after merge tag main and push.
Run, monitor, analyze, and debug LLM evaluations via nemo-evaluator-launcher. Covers running evaluations, checking status and live progress, debugging failed runs, exporting…
Bind pre-downloaded Jetson reference docs (developer guide, design guide, pinmux, schematics) into the active profile documents block.
Compile a PyTorch model to a TensorRT engine via Torch-TensorRT — AOT or JIT — under the new strong-typing default.
Enable MIPI/GMSL camera sensors on a Jetson Thor or Orin custom carrier by rendering a kernel-DT overlay from the in-tree sensor DTSI.
Routes NVIDIA Nemotron Speech (Riva) NIM tasks — deploys, runs, and tests ASR, TTS, and NMT NIMs on build.nvidia.com or self-hosted.
PyTorch-based TAO image classification. Supports a wide range of backbones (FAN, EfficientNet, ResNet, etc.)
Manage durable working-session memory for coding agents. Use when a user asks to preserve or recover agent context across disconnects, VS Code restarts, long-running work,…
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…
Fine-tune any HuggingFace CV / VLM / LLM model on local NVIDIA GPUs inside an NGC PyTorch container. Use when the user wants to fine-tune a HuggingFace model (full or LoRA), train…
Validate that a Dynamo deployment's NIXL/UCX/NCCL interconnect is ready for disaggregated serving over RDMA/NVLink.
Start up, tear down, and configure the local Kubernetes development environment for OpenShell. Uses k3d (Docker-backed k3s) + Skaffold + Helm.
Use when turning a Jetson encoder use case into one validated surface-neutral recipe with native and PyNvVideoCodec projections for codec, preset, rate control, bitrate, latency,…
Debug AutoDeploy accuracy regressions vs a reference score (PyTorch backend or published baseline). Use when an AutoDeploy model's eval score is significantly below the reference…
Inspects sandbox health, traces agent behavior, and diagnoses problems. Use when monitoring a running sandbox, debugging agent issues, or checking sandbox logs.
Explains how OpenClaw, OpenShell, and NemoClaw form the ecosystem, NemoClaw's position in the stack, what NemoClaw adds beyond the community sandbox, and when to prefer NemoClaw…
Standard single-step train/eval/export workflow for any TAO model. Use when training a TAO model on a dataset
Visual ChangeNet for binary image classification and segmentation in AOI defect detection. Use when training,
Use to deploy the vss-video-analytics-api REST service standalone (config-source, data-log bind, Elasticsearch, optional Kafka). Not for full warehouse deploy.
Recommend and customize Megatron Bridge recipes for a user's model, GPU count, and training goal. Indexes library recipes (pretrain/SFT/PEFT) and performance recipes.
Action recognition from video sequences. Supports RGB, optical flow, and joint (multi-stream) input types for
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
Validate and use MoE expert-parallel communication overlap in Megatron-Bridge, including overlap_moe_expert_parallel_comm, delay_wgrad_compute, and flex dispatcher backen — from…
Pose classification using ST-GCN (Spatial Temporal Graph Convolutional Network). Classifies skeleton sequences
Iteratively optimize cuTile kernel performance through systematic profiling, bottleneck analysis, IR comparison, and targeted tuning.
Run the full end-to-end agentic pipeline (record → mimic → annotate → replay → convert → visualize → finetune → validate).
Calibrate a new dataset from live RTSP camera streams via the AutoMagicCalib REST API. Use when the user provides RTSP URLs or asks to calibrate live cameras; VIOS records clips,…
Numerical optimization (LP, MILP, QP) — concepts, problem-text parsing, and formulation patterns. What LP, MILP, and QP are, required formulation questions, modeling elements,…
Four-step image referring-expression pipeline: turns images plus KITTI bounding-box labels into region
Deformable DETR for 2D object detection. Uses deformable attention for efficient multi-scale feature processing,
Techniques for reducing peak GPU memory in Megatron Bridge — expandable segments, parallelism resizing, activation recompute, CPU offloading constraints, and common OOM f — from…
Benchmark Jetson LLM/VLM serving performance across vLLM, llama.cpp, and Ollama with structured JSON output.
Start, query, and stop a network-specific TAO inference microservice ({network_arch}-inference-microservice) by delegating container execution to the appropriate platform skill.
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…
Use when executing and verifying Jetson Video Codec SDK or PyNvVideoCodec encode/decode, transcode, segmentation, container decode, AV1, or acceptance workflows with exact…
MoE expert-parallel communication overlap in Megatron Bridge. Covers dispatch/combine overlap, flex dispatcher backends, and expert wgrad scheduling. — from NVIDIA/skills
Resiliency features in Megatron Bridge including fault tolerance, straggler detection, in-process restart, preemption, and re-run state machine. — from NVIDIA/skills
Extract false-positive and false-negative gaps from VLM binary-classification-question (BCQ, yes/no) predictions.
Vehicle routing (VRP, TSP, PDP) — problem types and data requirements. Domain concepts; no API or interface. — from NVIDIA/skills
Runs the DEFT embed-then-mine workflow for VCN AOI iterations — embeds the gap-analysis target parquet, embeds
Evaluate whether an existing hot path is a credible NVIDIA Warp candidate. Use for irregular or spatial queries, particle or geometry simulation, branch-heavy loops, many small…