Use when asked to run deep research or AI-Q research through a reachable NVIDIA AI-Q Blueprint backend.
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.
Set up the BSP source workspace: Linux_for_Tegra overlay tracker, bsp_sources, Crosstool-NG toolchain. Use after jetson-init-image; not for fetching inputs.
Code instrumentation for timing workloads. Two scenarios: (1) Training loop — inject manual timing to report per-iteration latency, throughput (samples/sec), and data load time.
Use to call the VIOS REST API (sensor list, timelines, clip extraction, snapshots, add/delete sensors and streams). Not for VLM inference or search.
Build Holoscan SDK from source via the in-tree ./run script. Use only when published packages don't meet the user's needs.
Audit Warp CHANGELOG.md before a release: recover lost entries, sort by user impact, refine entry language, line-wrap, and (release-branch mode) bump compare refs.
Use when executing and verifying Jetson Video Codec SDK or PyNvVideoCodec encode/decode, transcode, segmentation, container decode, AV1, or acceptance workflows with exact…
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,…
Guide for adding a new sink to PhysicsNeMo Curator. Covers discovery questions, implementation patterns (simple writer, append-based, split-based), output naming, parallel…
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
中文优先：用于智能体支付x402相关任务，帮助识别、设计、实现或验证对应工作流。English keywords: Add x402 payment execution to AI agents — per-task budgets, spending controls, and non-custodial wallets via MCP tools.
Domain knowledge for the nightly main-to-dev sync workflow. Covers merge strategy, CI architecture, failure investigation, and known issues.
Brev managed GPU instances with Docker support. Use when running TAO training, evaluation, or inference on
Install Holoscan SDK natively on Ubuntu via apt. Use for C++ installs on Ubuntu; pair with /holoscan-install-wheel for Python.
Generates BYO custom safety policies for NVIDIA Nemotron content-safety guardrails — Nemotron-Content-Safety-Reasoning-4B (text) and multimodal Nemotron-3-Content-Safety.
Guide for adding a new data source to PhysicsNeMo Curator. Use when adding a remote dataset (HuggingFace, S3, etc.) or local file-based source.
External NeMo-RL end-to-end validation workflow for Megatron-Bridge model/provider changes, including downstream compatibility checks, external RL lifecycle behavior, Megatron…
Use when debugging a Nemo Gym run or reward profiling job. Covers rollout collection failures, empty or partial JSONL outputs, stale materialized inputs, verifier/schema errors,…
CLIP vision-language model for image-text retrieval, zero-shot classification, embedding extraction, ONNX
Create custom LLM evaluation benchmarks using the BYOB decorator framework. Use when the user wants to (1) create a new benchmark from a dataset, (2) pick or write a scorer, (3)…
Systematic workflow for MoE training optimization in Megatron Bridge, based on the Megatron-Core MoE paper.
Numerical optimization (LP, MILP, QP) — concepts, problem-text parsing, and formulation patterns. What LP, MILP, and QP are, required formulation questions, modeling elements,…
DGX Cloud Lepton managed GPU compute platform with run/status/cancel interface. Use when submitting TAO jobs
Coordinate the end-to-end CAD/source-asset to SimReady workflow. Use for broad requests such as CAD to SimReady, source asset to simulation-ready USD, or prop packaging that…
OneFormer for universal image segmentation. Unifies panoptic, instance, and semantic segmentation with a
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,…
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.
Real-time stereo depth estimation using FastFoundationStereo (FFS), the distilled bp2 commercial variant of
How to launch distributed Megatron-LM training jobs on a SLURM cluster. Covers a minimal sbatch skeleton, environment-variable setup for torch.distributed.run, CUDA_DEVIC — from…
CenterPose for keypoint / pose estimation. Detects object centers and regresses keypoint locations for 6-DoF
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…
SegFormer for semantic segmentation. Lightweight transformer-based architecture with hierarchical feature
Mask2Former for universal image segmentation (panoptic, instance, and semantic). Transformer-based with
Run end-to-end calibration on the shipped sample dataset (sdg_08_2_sample_data_010926.zip) against a running AMC microservice.
Use only to generate or update a governance skill card for a specified existing agent skill directory.
Validate and analyze TensorRT performance data from paired layer-info JSON and profile/latency JSON files.
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.
Use to deploy, run, debug, or tear down the RTVI-CV 2D detection / tracking microservice and call its REST API. Not for VLM, embedding, or analytics — use the matching vss-* skill.
Orchestration skill for NVIDIA Nemotron Speech (Riva) / NeMo ASR domain and language adaptation. Given a goal like "improve/fine-tune ASR for my domain or language", it scopes the…
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps.
Translates a HuggingFace model into a prefill-only AutoDeploy custom model using reference custom ops, validates with hierarchical equivalence tests.
Local Docker execution for TAO SDK job containers using the host Docker daemon and NVIDIA GPU runtime. Use
Deploy, operate, and integrate the VSS 3.2 GA RT-Embed Video Embedding microservice. Covers Docker Compose bring-up, GPU and storage prerequisites, the `/v1` REST API (file…
Visual ChangeNet for binary image classification and segmentation in AOI defect detection. Use when training,
Generate sandbox security policies from plain-language requirements and optional REST API documentation.
Performance benchmarking for a deployed NVIDIA RAG Blueprint server: profiling pass + aiperf load test driven by a single YAML config.
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
Use to deploy the vss-behavior-analytics service standalone (entrypoint, config-source, optional calibration). Not for the full warehouse deploy.
Use when running people attribute search (PAS) image augmentation and auto-labeling workflows on OSMO: flow selection, preflight, submit-time interpolation, monitoring, and output…
Build and verify a TensorRT engine from a Hugging Face model ID or ONNX file, with numerical parity checked against ONNX Runtime.
Guide for adding a new filter to PhysicsNeMo Curator. Covers discovery questions, implementation patterns (pass-through, stateful, in-place), generator semantics, flush/artifacts,…
Performance optimization coordination playbook. Contains specialist routing table, TileIR two-step pipeline, kernel generation specialist selection, prioritization criteria, and…
Techniques for reducing peak GPU memory in Megatron Bridge — expandable segments, parallelism resizing, activation recompute, CPU offloading constraints, and common OOM f — from…
Systematic approach to exploring the TensorRT-LLM codebase before implementing new features or optimizations.
Performs deep Root Cause Analysis (RCA) on NVIDIA TAO Visual ChangeNet classification experiments with
Masked Auto-Encoder (MAE) for self-supervised pretraining and fine-tuning. Masks random patches and reconstructs
Build deterministic forecast scripts with Earth2Studio (model, data source, IO, inference). Do NOT use for ensemble, diagnostics, data-only fetch, or install.
Base rules for end users calling NVIDIA cuOpt (routing/LP/MILP/QP/install/server). Not for cuOpt internals — use cuopt-developer for those.
ONLY for OpenAI Triton (@triton.jit) kernel development. NEVER use for CUDA C++ kernels, TileIR, or profiling tools (ncu, nsys). The user's request must involve Triton explicitly.