promptingcompany/nv-skills

1

nemoclaw-user User-facing NemoClaw guidance for installing, configuring, operating, securing, monitoring, and troubleshooting NemoC…

promptingcompany/nv-skills

46

2

nemo-mbridge-recipe-recommender Recommend and customize Megatron Bridge recipes for a user's model, GPU count, and training goal. Indexes library rec…

promptingcompany/nv-skills

42

3

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

promptingcompany/nv-skills

41

4

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

promptingcompany/nv-skills

41

5

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

promptingcompany/nv-skills

40

6

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

promptingcompany/nv-skills

40

7

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

promptingcompany/nv-skills

40

8

digital-health-clinical-asr-finetune Stage 4 of the Clinical ASR Flywheel. Use when priority KER is above 0.3 to run stock NeMo SFT on Parakeet TDT v2 and…

promptingcompany/nv-skills

40

9

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

promptingcompany/nv-skills

40

10

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

promptingcompany/nv-skills

40

11

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

promptingcompany/nv-skills

40

12

earth2studio-data-fetch Fetch weather/climate data via Earth2Studio data sources for specific variables and times. Do NOT use for inference p…

promptingcompany/nv-skills

40

13

nemo-retriever Use this to pull a specific figure, fact, quote, or table value out of a collection of documents and cite the exact s…

promptingcompany/nv-skills

40

14

nv-generate-ct-rflow Used for generating synthetic CT volumes and masks with NV-Generate-CTMR rflow-ct. Not for production training data w…

promptingcompany/nv-skills

40

15

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

promptingcompany/nv-skills

40

16

physical-ai-neural-reconstruction Router for NVIDIA NuRec/NRE: USDZ rendering, NCore conversion, 3DGS, gRPC sensor sim, PhysicalAI HF datasets. Do NOT …

promptingcompany/nv-skills

40

17

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

promptingcompany/nv-skills

40

18

tao-run-on-kubernetes Kubernetes execution platform — submits TAO container jobs as single-pod k8s Jobs with NVIDIA GPU scheduling. Use whe…

promptingcompany/nv-skills

40

19

tao-train-pose-classification Pose classification using ST-GCN (Spatial Temporal Graph Convolutional Network). Classifies skeleton sequences into a…

promptingcompany/nv-skills

40

20

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

promptingcompany/nv-skills

39

21

cufolio Use when a user asks to build, optimize, backtest, rebalance, or analyze a stock portfolio with Mean-CVaR, efficient …

promptingcompany/nv-skills

39

22

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

promptingcompany/nv-skills

39

23

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

promptingcompany/nv-skills

39

24

cuopt-numerical-optimization-api-c LP, MILP, and QP (beta) with cuOpt — C API only. Use when the user is embedding LP, MILP, or QP in C/C++.

promptingcompany/nv-skills

39

25

cuopt-numerical-optimization-api-cli LP, MILP, and QP (beta) with cuOpt — CLI only (MPS files, cuopt_cli). Use when the user is solving LP, MILP, or QP fr…

promptingcompany/nv-skills

39

26

cuopt-numerical-optimization-api-python Solve LP, MILP, QP (beta) with cuOpt Python API — linear/quadratic objectives, integer variables, scheduling, portfol…

promptingcompany/nv-skills

39

27

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

promptingcompany/nv-skills

39

28

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

promptingcompany/nv-skills

39

29

cuopt-routing-formulation Vehicle routing (VRP, TSP, PDP) — problem types and data requirements. Domain concepts; no API or interface.

promptingcompany/nv-skills

39

30

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

promptingcompany/nv-skills

39

31

cuopt-server-common cuOpt REST server — what it does and how requests flow. Domain concepts; no deploy or client code.

promptingcompany/nv-skills

39

32

cuopt-skill-evolution After solving a non-trivial problem, detect generalizable learnings and propose skill updates. Always active — applie…

promptingcompany/nv-skills

39

33

cuopt-user-rules Base rules for end users calling NVIDIA cuOpt (routing/LP/MILP/QP/install/server). Not for cuOpt internals — use cuop…

promptingcompany/nv-skills

39

34

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

promptingcompany/nv-skills

39

35

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

promptingcompany/nv-skills

39

36

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

promptingcompany/nv-skills

39

37

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

promptingcompany/nv-skills

39

38

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

promptingcompany/nv-skills

39

39

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

promptingcompany/nv-skills

39

40

deepstream-dev NVIDIA DeepStream SDK 9.0 development with Python pyservicemaker API. Use when building video analytics pipelines, GS…

promptingcompany/nv-skills

39

41

deepstream-import-vision-model Use this skill to bring any vision model from HuggingFace or NVIDIA NGC into an NVIDIA DeepStream pipeline with end-t…

promptingcompany/nv-skills

39

42

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

promptingcompany/nv-skills

39

43

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

promptingcompany/nv-skills

39

44

dicom-series-to-volume Used for converting one CT DICOM series folder to a HU NIfTI volume with affine evidence. Not for multi-frame DICOM o…

promptingcompany/nv-skills

39

45

digital-health-clinical-asr-build Stage 2 of the Clinical ASR Flywheel. Use when curating clinical terms, tagging IPA, and synthesizing a NeMo manifest…

promptingcompany/nv-skills

39

46

digital-health-clinical-asr-eval Stage 3 of Clinical ASR Flywheel. Score a NeMo manifest, produce the five-section KER leaderboard (by-ipa_source diag…

promptingcompany/nv-skills

39

47

digital-health-clinical-asr-setup Stage 1 of Clinical ASR Flywheel. Use when bootstrapping a cycle: NVCF+MW disclosure, NVIDIA_API_KEY check, deps inst…

promptingcompany/nv-skills

39

48

earth2studio-deterministic-forecast Build deterministic forecast scripts with Earth2Studio (model, data source, IO, inference). Do NOT use for ensemble, …

promptingcompany/nv-skills

39

49

earth2studio-discover Find Earth2Studio models, data sources, and examples for a weather/climate use case. Do NOT use for writing inference…

promptingcompany/nv-skills

39

50

earth2studio-install Guide installing Earth2Studio via uv or pip, selecting model extras, and configuring the environment. Do NOT use for …

promptingcompany/nv-skills

39