NVIDIA/skills

AIQ Deploy installs, runs, validates, and stops a local or self-hosted NVIDIA AI-Q Blueprint server. Use it when asked to deploy, troubleshoot, or shut down AI-Q infrastructure for the aiq-research skill.

AIQ Research runs deep research requests through a reachable NVIDIA AI-Q Blueprint backend. Use it for research-shaped queries like "deep research on..." or "ask AI-Q about...", and to poll, resume, or follow up on AI-Q research reports.

AMC RTSP Calibration records clips from live RTSP camera streams and runs AutoMagicCalib calibration via its REST API. Use it when a user provides RTSP URLs or asks to calibrate live cameras.

AMC Setup Calibration Stack launches the AutoMagicCalib microservice and web UI from NGC release images via Docker Compose. Use when deploying auto calibration, launching AMC, starting MS+UI, or setting up auto-magic-calib with an NGC API key.

CUDA-Q Guide walks users through installing CUDA-Q, writing quantum kernels, GPU-accelerated simulation, connecting to QPU hardware, and exploring built-in quantum applications.

Calibrate Sample Dataset runs end-to-end calibration on the bundled sample dataset against a running AutoMagicCalib (AMC) microservice to verify a fresh AMC stack. Use it when the user asks to test the sample dataset, run sample calibration, or verify the AMC install.

CuOpt Developer guides contributions to the NVIDIA cuOpt codebase, covering C++/CUDA, Python, server, and CI changes, build and test workflows, DCO signoff, and code conventions. Use it when modifying cuOpt internals rather than using cuOpt to solve problems.

CuOpt Numerical Optimization API models and solves linear programming (LP), mixed-integer linear programming (MILP), and quadratic programming (QP) problems using NVIDIA cuOpt's GPU-accelerated solver. Use it when the user needs to solve optimization problems with any cuOpt interface (Python, C, CLI).

CuPyNumeric Parallel Data Load loads sharded, on-disk datasets (.npy, Parquet/Arrow, raw binary, HDF5) into a distributed cuPyNumeric ndarray using manual partition and leaf task launch for CPU, OMP, and GPU variants. Use it when no single-call loader fits, including when per-shard row counts differ across files.

DALI Dynamic Mode guides AI agents in writing, reviewing, and migrating code that uses NVIDIA DALI's imperative dynamic-mode API (`nvidia.dali.experimental.dynamic`, ndd). Use it when working on ndd code or migrating pipeline-based DALI code to dynamic mode.

Data Designer builds synthetic datasets and data generation pipelines using the Data Designer library. Use it when you need to generate structured data, create datasets, or build a data generation pipeline.

DeepStream Development builds NVIDIA DeepStream SDK pipelines using the Python pyservicemaker API for video analytics, including object detection, tracking, and TensorRT inference. Use when creating GStreamer-based video processing, integrating inference models, or adding Kafka/message broker support.

DeepStream Import Vision Model automates the end-to-end import of object detection vision models from HuggingFace or NVIDIA NGC into an NVIDIA DeepStream pipeline, including ONNX download or SafeTensors export, TensorRT engine build, custom parser, multi-stream benchmark, and PDF report.

DeepStream Pipeline Builder generates ready-to-run gst-launch-1.0 pipelines for NVIDIA DeepStream SDK. Use when the user asks about pipelines for video/image inference, detection, tracking, or streaming.

DeepStream Profiling profiles NVIDIA DeepStream pipelines using Nsight Systems and derives performance configs such as batch size and precision from measurements. Use it when building efficient pipelines or benchmarking FPS on a target GPU.

Multi-Objective Exploration traces and interprets Pareto frontiers for multi-objective optimization problems by orchestrating repeated single-objective cuOpt solves (weighted-sum and ε-constraint). Use it when objectives conflict and the user needs the tradeoff curve, not a single weighted answer.

Numerical Optimization Formulation teaches how to parse problem statements and build LP, MILP, and QP models, covering decision variables, constraints, objectives, and convexity. It is used when an agent needs to formulate optimization problems from natural language without writing API code.

Video Calibration calibrates a new dataset from pre-recorded video files via the AutoMagicCalib REST API. Use when the user has local MP4s and says 'calibrate my videos' or 'run AMC on these videos'.

cuDF GPU DataFrames accelerates pandas data processing on NVIDIA GPUs for ETL, joins, groupby, and CSV/Parquet I/O. Use it to migrate pandas workloads to GPU or scale to multi-GPU with dask-cuDF.

cuOpt Install helps you install NVIDIA cuOpt for Python, C, or as a REST server via pip, conda, or Docker, and verify the installation. Use it when setting up cuOpt on systems with NVIDIA Compute Capability 7.0+ and CUDA 12.x/13.x.

cuOpt Routing Python API solves vehicle routing problems (TSP, VRP, PDP) with NVIDIA cuOpt from Python. Use it when building or solving routing models in Python.

cuOpt Server API Python provides REST server deployment and Python/curl client examples for NVIDIA cuOpt routing and LP/MILP problems. Use it when starting the server, understanding endpoints, or writing client code.

cuPyNumeric HDF5 I/O reads and writes large cuPyNumeric arrays to HDF5 files using Legate's parallel, distributed HDF5 I/O. Use it when a developer needs to save or load .h5/.hdf5 datasets, read large files in chunks, or accelerate HDF5 disk I/O with GPUDirect Storage.

cuPyNumeric Install helps set up and verify the cuPyNumeric Python library via conda or pip, including GPU usage checks. Use it when someone needs cuPyNumeric running in an isolated environment on Linux or WSL.

cuPyNumeric Migration Readiness assesses NumPy code before porting to cuPyNumeric, identifying which APIs will scale on GPU and which need refactoring. Use it before starting a migration to get a verdict and concrete refactor pointers.