Router for NVIDIA NuRec/NRE: USDZ rendering, NCore conversion, 3DGS, gRPC sensor sim, PhysicalAI HF datasets. Do NOT use for SimReady or infra setup.
Deformable DETR for 2D object detection. Uses deformable attention for efficient multi-scale feature processing,
Use when installing, repairing, probing, or verifying native NVIDIA Video Codec SDK or PyNvVideoCodec on Jetson with official encode-to-decode samples, including…
cuOpt REST server — start server, endpoints, Python/curl client examples. Use when the user is deploying or calling the REST API.
Use for VSS alert workflows — real-time monitoring, Alert-Bridge subscriptions, Slack notifications, incident queries, camera onboarding. Not for non-alert analytics.
Use for NVIDIA-related requests where an NVIDIA skill might help, even if the user did not ask for a skill.
Shared launch intake for any TAO workflow or action. Use when the user wants to run TAO AutoML, train, evaluate, infer, export, generate TensorRT engines, or launch DEFT/workflow…
Start here. Introduces what NemoClaw is, what agent skills are available, and which skill to use for a given task.
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…
Create and modify NeMo AutoModel training and evaluation recipes, including YAML structure, builders, and execution flow.
Use to run top-level VSS fusion search on archived video, or to ingest video files / RTSP streams for search. Not for ad-hoc Q&A or live captioning.
Routes NVIDIA Nemotron Speech (Riva) NIM tasks — deploys, runs, and tests ASR, TTS, and NMT NIMs on build.nvidia.com or self-hosted.
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…
Run CPU-only fluorosim smoke tests (imports, preprocessing, CLI parsers). Use when asked to smoke-test catheter navigation in CI or without a GPU.
Validate and use CUDA graph capture in Megatron Bridge, including local full-iteration graphs and Transformer Engine scoped graphs for attention, MLP, and MoE modules.
Dev environment setup for Megatron Bridge — container-based development, uv package management, lockfile regeneration, adding dependencies, Slurm container usage, and common build…
Load a sharded, on-disk dataset (sharded .npy, Parquet/Arrow, raw binary, sharded HDF5, custom layouts) into a distributed cuPyNumeric ndarray via a manual partition + leaf @task…
Install Holoscan SDK v4.3+ via Conda in a CUDA 13 environment. Use for Conda installs; redirect CUDA 12 hosts to container/wheel.
Four-step image referring-expression pipeline: turns images plus KITTI bounding-box labels into region
Choose the right MoE token dispatcher (`alltoall`, DeepEP, or HybridEP) for the hardware, EP degree, and optimization stage.
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.
Validate, evaluate, or run i4h envs. Use for policy/checkpoint rollouts and scripted state-machine smoke runs.
NVPanoptix3D for panoptic 3D scene reconstruction from posed RGB images. Produces 3D panoptic segmentation
Modify, build, test, debug, and contribute to NVIDIA cuOpt (C++/CUDA, Python, server, CI). Use for solver internals, PRs, DCO, and code conventions.
Given a GitHub issue, review the issue for security implications. You'll make a determination if the claim in the issue is legitimate and should be addressed or will be a "won't…
Validate and use selective and full activation recompute in Megatron Bridge to reduce GPU memory usage at the cost of extra compute. — from NVIDIA/skills
Add EAGLE-3 or draft-model speculative decoding to a Jetson vLLM server when TPOT is the bottleneck.
Performs a comprehensive security review of code changes in a GitHub PR or issue. Checks out the branch, analyzes changed files against a 9-category security checklist, and…
Analyze ncu (NVIDIA Nsight Compute) profiling output: SOL% bottleneck classification, roofline analysis, occupancy diagnosis, memory hierarchy analysis, warp stall analysis,…
Validate and use packed sequences and long-context training in Megatron-Bridge, distinguishing offline packed SFT for LLMs from in-batch packing for VLMs, and applying th — from…
Use to lock/cap Jetson CPU/GPU/EMC clocks, toggle EMC/CPU DVFS, or change cpufreq governors by editing BPMP DTB and nvpower.sh pre-flash.
Used for running NV-Segment-CT VISTA3D on CT NIfTI volumes and recording label-map evidence.
Used for converting one CT DICOM series folder to a HU NIfTI volume with affine evidence. Not for multi-frame DICOM or clinical use.
Use when asked to install, deploy, run, validate, troubleshoot, or stop NVIDIA AI-Q Blueprint infrastructure.
Integrate a HuggingFace Computer Vision model into the NVIDIA TAO Toolkit ecosystem (tao-core config, tao-pytorch trainer, tao-deploy TensorRT pipeline).
Cherry-pick merged PRs labeled for a release branch into that branch, then open a PR and apply the cherry-pick-done label.
Describes the NemoClaw plugin and blueprint architecture and how they orchestrate the OpenClaw sandbox. Use when looking up architecture, plugin structure, or blueprint design.
Converts cuTile GPU kernels (@ct.kernel) to Triton (@triton.jit). Handles standard in-repo conversion, debugging (cudaErrorIllegalAddress, shape mismatch, numerical misma — from…
Host setup for TAO GPU backends. Checks and, after user approval, installs NVIDIA driver branch 580, CUDA Toolkit 13.0, and NVIDIA Container Toolkit 1.19.0 for Docker/local-Docker…
Enable/disable Jetson USB2/USB3 SS ports via kernel-DT overlay. Do NOT use for UPHY lane allocation or ODMDATA edits.
Investigate a failing GitHub Actions run or job and create a GitHub issue for the failure.
Investigate a plain-language problem description by deeply exploring the codebase, then create a structured GitHub issue with technical findings.
Install and configure NVIDIA NemoClaw (sandboxed OpenClaw agent platform) on Linux. Handles cloudflared tunnels, Docker cgroup fixes, OpenShell, sandbox creation, remote access…
Operational guide for enabling hierarchical context parallelism in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification. — 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
Adds, removes, or modifies allowed endpoints in the sandbox policy. Use when customizing network policy, changing egress rules, or configuring sandbox endpoint access.
Used for header-only preflight of one DICOM series folder before conversion or inference. Not for de-identification or clinical clearance.
How to swap the DeepStream CV detection model in the VSS Alerts Blueprint verification (2d_cv) mode - covers ONNX export, custom bbox parsers, compose mount gotchas, nvinfer…
External verl end-to-end validation workflow for Megatron-Bridge model/provider changes. Covers running a small verl Megatron backend job from a Bridge checkout, choosing LoRA/DDP…
Autonomous NeMo-RL research agent workflow for directed hypothesis testing and open-ended discovery. Guides agents through the full experiment lifecycle: understanding re — from…
LP, MILP, and QP (beta) with cuOpt — C API only. Use when the user is embedding LP, MILP, or QP in C/C++.
Vehicle routing (VRP, TSP, PDP) with cuOpt — Python API only. Use when the user is building or solving routing in Python.
Use when working on the Evaluator plugin CLI, jobs, SDK-backed specs, or plugin-owned Evaluator skills.
Used for smoke or dataset finetuning of NV-Segment-CT VISTA3D on CT NIfTI labels. Not for clinical validation.
Review, design, and refactor TensorRT-LLM PyTorch MoE code for architecture fit, clean code, maintainability, and testability.
Long-context MoE training guidance for Megatron Bridge. Covers CP sizing, selective recompute, dispatcher choices, and practical patterns from DSV3, Qwen3, and Qwen3-Next — from…
Scaffold a standalone RTVI CV microservice that plugs into VSS Search and Alerts profiles via Kafka mdx-raw.
Run and operate the DeepStream Multi-View 3D Tracking reference app, also known as MV3DT. Use when the user asks to set up prerequisites, run shipped MV3DT samples, run Multi-View…
Claude Code skill (trtllm-agent-toolkit): implement or extend TensorRT-LLM AutoDeploy fusion transforms under transform/library/ in a TensorRT-LLM checkout.
Record episodes for an agentic env via teleoperation (keyboard, SO-ARM leader, or VR) into HDF5. Use when the user wants to teleop or record human demos.