Source

nvidia/skills

447 skills · 412.4K combined installs

Skills from this source

#

Skill

Source

8W Activity

Installs

rag-blueprint Official NVIDIA RAG Blueprint — deploy, configure, troubleshoot, and manage.

accelerated-computing-cudf Official Official NVIDIA-authored guidance for NVIDIA cuDF GPU DataFrames, pandas acceleration, dask-cuDF, ETL, joins, groupby…

aiq-research Official Use when asked to run deep research or AI-Q research through a reachable NVIDIA AI-Q Blueprint backend.

cuopt-developer Official Modify, build, test, debug, and contribute to NVIDIA cuOpt (C++/CUDA, Python, server, CI). Use for solver internals, …

aiq-deploy Official Use when asked to install, deploy, run, validate, troubleshoot, or stop NVIDIA AI-Q Blueprint infrastructure.

cuopt-install Official Install cuOpt for Python, C, or server via pip, conda, or Docker; verify the install. For building cuOpt from source,…

cudaq-guide Official CUDA-Q onboarding guide for installation, test programs, GPU simulation, QPU hardware, and quantum applications.

data-designer Official Use when the user wants to create a dataset, generate synthetic data, or build a data generation pipeline.

deepstream-dev Official NVIDIA DeepStream SDK development with Python pyservicemaker API. Use when building video analytics pipelines, GStrea…

rag-eval Official >- Filesystem RAG benchmarks: corpus/, train.json, evaluate_rag.py (RAGAS quality). Not for prod monitoring, latency/…

nemo-retriever Official Use when the user wants to search, query, extract, transcribe, describe, quote, filter, or aggregate across documents…

omniverse-cad-to-simready Official Coordinate the end-to-end CAD/source-asset to SimReady workflow.

omniverse-usd-performance-tuning Official Top-level workflow skill for USD performance diagnosis and optimization. Handles slow loading, high memory, low FPS, …

deepstream-import-vision-model Official Use this skill to bring a supported object-detection vision model from HuggingFace or NVIDIA NGC into an NVIDIA DeepS…

cuopt-routing-api-python Official Vehicle routing (VRP, TSP, PDP) with cuOpt — Python API only. Use when the user is building or solving routing in Pyt…

skill-card-generator Official Use only to generate or update a governance skill card for a specified existing agent skill directory. Do not use for…

omniverse-realtime-viewer Official Use as the top-level router for Omniverse Realtime Viewer USD app requests and focused viewer reference documents.

dynamo-recipe-runner Official Select, validate, patch, and deploy existing NVIDIA Dynamo Kubernetes recipes. Use for model/backend/GPU/deployment-m…

rag-perf Official >- Performance benchmarking for a deployed NVIDIA RAG Blueprint server: profiling pass + aiperf load test driven by a…

cuopt-numerical-optimization-formulation Official LP, MILP, QP — concepts, problem-text parsing, and formulation patterns (parameters, constraints, decisions, objectiv…

cuopt-server-api-python Official cuOpt REST server — start server, endpoints, Python/curl client examples. Use when the user is deploying or calling t…

physical-ai-neural-reconstruction Official Router for NVIDIA NuRec/NRE: USDZ rendering, NCore conversion, 3DGS, gRPC sensor sim, carline adaptation, PhysicalAI …

nemotron-customize Official Plan, configure, and chain repo-native Nemotron customization steps into single-step or multi-step pipelines: curatio…

dali-dynamic-mode Official DALI imperative dynamic mode (`nvidia.dali.experimental.dynamic`, ndd): use when working on ndd code or migrating pip…

nemo-rl-session-memory Official Manage durable working-session memory for coding agents.

nemotron-speech Official Routes NVIDIA Nemotron Speech (Riva) NIM tasks — deploys, runs, and tests ASR, TTS, and NMT NIMs on build.nvidia.com …

physical-ai-infrastructure-setup-and-resilient-scaling Official >- Use when the user wants to set up, scale, validate, or harden NVIDIA physical AI infrastructure for synthetic data…

nemotron-retrieval-recipes Official Use when planning, debugging, tuning, evaluating, exporting, or deploying public Nemotron `embed`/`rerank` retrieval …

cupynumeric-install Official Install and verify cuPyNumeric for Python — requirements, commands, verification. Source builds are out of scope.

physical-ai-video-data-augmentation Official >- Use when running video data augmentation and auto-labeling workflows on OSMO: flow selection, preflight, submit-ti…

physical-ai-defect-image-generation Official >- Use when the user wants to orchestrate defect image generation with NVIDIA Cosmos AnomalyGen (Cosmos-Predict2-deri…

nemo-automodel-distributed-training Official Guide for selecting and configuring distributed training strategies in NeMo AutoModel, including FSDP2, Megatron FSDP…

vss-summarize-video Official Use to summarize a recorded video via the LVS summarization microservice (HITL-gated) with a VLM fallback. Not for re…

nemo-automodel-recipe-development Official Create and modify NeMo AutoModel training and evaluation recipes, including YAML structure, builders, and execution f…

cupynumeric-migration-readiness Official Pre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when th…

nemo-automodel-model-onboarding Official Guide for onboarding new model architectures into NeMo AutoModel, including architecture discovery, implementation pa…

dynamo-router-starter Official Start or patch Dynamo router modes and run router endpoint smoke checks. Use for round-robin, KV-aware, least-loaded,…

vss-ask-video Official Use this skill to ask the VSS agent's video_understanding tool a fresh visual question about a recorded clip. Not for…

cupynumeric-parallel-data-load Official Load a sharded, on-disk dataset (sharded .npy, Parquet/Arrow, raw binary, sharded HDF5, custom layouts) into a distri…

physicsnemo-discover Official Official NVIDIA-authored guidance for navigating PhysicsNeMo — pick the model, datapipe, or example for a SciML/AI4Sc…

nemo-rl-auto-research Official Autonomous NeMo-RL research agent workflow for directed hypothesis testing and open-ended discovery.

nemo-automodel-launcher-config Official Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.

dynamo-troubleshoot Official Diagnose failed or unhealthy Dynamo deployments. Use when pods, model-cache jobs, PVCs, workers, frontend/router heal…

cupynumeric-hdf5 Official >- Read and write large cuPyNumeric arrays to HDF5 with Legate's parallel, distributed HDF5 I/O (legate.io.hdf5: to_f…

dicom-metadata-extract Official Used for extracting selected metadata from one DICOM file and flagging standard-tag PHI presence. Not for anonymizati…

nemo-mbridge-perf-cuda-graphs Official Validate and use CUDA graph capture in Megatron Bridge, including local full-iteration graphs and Transformer Engine …

nemo-mbridge-perf-memory-tuning Official Techniques for reducing peak GPU memory in Megatron Bridge — expandable segments, PEFT + SP input re-gather, parallel…

dynamo-interconnect-check Official Validate that a Dynamo deployment's NIXL/UCX/NCCL interconnect is ready for disaggregated serving over RDMA/NVLink.

dicom-series-preflight Official Used for header-only preflight of one DICOM series folder before conversion or inference. Not for de-identification o…

vss-search-archive Official Use this skill to run top-level VSS fusion search on archived video, or to ingest video files / RTSP streams for sear…