Skill directory
Agent skills
Focused instruction packs that teach a coding agent one job well. Browse the catalog and use any of them inside a RiverX project.
18,175Skills
1,902Publishers
249Official
Accelerated Computing Cudfnvidia/skillsOfficial NVIDIA-authored guidance for NVIDIA cuDF GPU DataFrames, pandas acceleration, dask-cuDF, ETL, joins, groupby, CSV/Parquet I/O, nullable semantics, and multi-GPU DataFrame workloads.034Aiq Deploynvidia/skills|018Aiq Researchnvidia/skills|07Amc Run Sample Calibrationnvidia/skillsRun end-to-end calibration on the shipped sample dataset (sdg_08_2_sample_data_010926.zip) against a running AMC microservice. Use when user says 'test sample dataset', 'run sample calibration', 'verify AMC install', or 'launch and test'.06Amc Run Video Calibrationnvidia/skillsCalibrates pre-recorded `cam_*.mp4` datasets through the AutoMagicCalib REST API. Use for user-supplied local MP4s; route live RTSP streams to `amc-run-rtsp-calibration`.06Amc Setup Calibration Stacknvidia/skillsLaunch AutoMagicCalib microservice and web UI from NGC release images via Docker Compose. Use when user says 'deploy auto calibration', 'launch auto calibration', 'launch AMC', 'start MS+UI', or 'set up auto-magic-calib'. Requires NGC API key.05Cudaq Guidenvidia/skillsUse for CUDA-Q setup, simulation targets, QPU access, and @cudaq.kernel authoring guidance.09Cuopt Developernvidia/skillsModify, build, test, debug, and contribute to NVIDIA cuOpt (C++/CUDA, Python, server, CI). Use for solver internals, PRs, DCO, and code conventions.014Cuopt Installnvidia/skillsInstall cuOpt for Python, C, or server via pip, conda, or Docker; verify the install. For building cuOpt from source, see cuopt-developer.07Cuopt Multi Objective Explorationnvidia/skillsTrace, complete, and interpret the Pareto frontier across competing objectives using repeated single-objective cuOpt solves (weighted-sum and ε-constraint).05Cuopt Numerical Optimization APInvidia/skillsLP, MILP, and QP (beta) with cuOpt — Python, C, and CLI. Use when the user is solving LP, MILP, or QP with any cuOpt interface.052Cuopt Numerical Optimization Formulationnvidia/skillsLP, MILP, QP — concepts, problem-text parsing, and formulation patterns (parameters, constraints, decisions, objective). Concepts only; no API.05Cuopt Routing API Pythonnvidia/skillsVehicle routing (VRP, TSP, PDP) with cuOpt — Python API only. Use when the user is building or solving routing in Python.012Cuopt Server API Pythonnvidia/skillscuOpt REST server — start server, endpoints, Python/curl client examples. Use when the user is deploying or calling the REST API.016Dali Dynamic Modenvidia/skillsDALI imperative dynamic mode (`nvidia.dali.experimental.dynamic`, ndd): use when working on ndd code or migrating pipelines; skip pipeline-only tasks.08Data Designernvidia/skillsUse when the user wants to create a dataset, generate synthetic data, or build a data generation pipeline.011Deepstream Devnvidia/skillsNVIDIA DeepStream SDK development with Python pyservicemaker API. Use when building video analytics pipelines, GStreamer-based video processing, TensorRT inference integration, object detection/tracking, or Kafka/message broker integration.021Deepstream Generate Pipelinenvidia/skillsBuild DeepStream GStreamer pipelines interactively. Use when the user asks about pipelines for video/image inference, detection, tracking, or streaming — including natural phrases like 'pipeline to infer on image', 'run inference on video', 'detect objects in stream', 'save inference output', 'deepstream pipeline', 'gst-launch pipeline', 'process video with detection', 'build a pipeline', or any request involving GStreamer/DeepStream elements (nvinfer, nvstreammux, nvtracker, etc.).020Deepstream Import Vision Modelnvidia/skills>056Deepstream Profile Pipelinenvidia/skillsProfile a DeepStream pipeline with Nsight Systems and derive its configs from the measurement. Use when the user asks for an efficient, performant, or profiled pipeline — or to benchmark, tune, or measure FPS.016Deepstream Sopnvidia/skills>058Dicom Metadata Extractnvidia/skillsUsed for extracting selected metadata from one DICOM file and flagging standard-tag PHI presence. Not for anonymization or clinical use.012Dicom Series Preflightnvidia/skillsUsed for header-only preflight of one DICOM series folder before conversion or inference. Not for de-identification or clinical clearance.010Dicom Series To Volumenvidia/skillsUsed for converting one CT DICOM series folder to a HU NIfTI volume with affine evidence. Not for multi-frame DICOM or clinical use.010Digital Health Clinical Asr Buildnvidia/skillsStage 2 of the Clinical ASR Flywheel. Use when curating clinical terms, tagging IPA, and synthesizing a NeMo manifest. NOT for scoring (use /digital-health-clinical-asr-eval).07Digital Health Clinical Asr Evalnvidia/skillsStage 3 of Clinical ASR Flywheel. Score a NeMo manifest, produce the five-section KER leaderboard (by-ipa_source diagnostic). Not for ASR auth (/riva-asr).07Digital Health Clinical Asr Finetunenvidia/skillsStage 4 of the Clinical ASR Flywheel. Use when priority KER is above 0.3 to run stock NeMo SFT on Parakeet TDT v2 and offline cycle N+1 re-eval. NOT for generic word boosting (use /finetune-asr).07Digital Health Clinical Asr Setupnvidia/skillsStage 1 of Clinical ASR Flywheel. Use when bootstrapping a cycle: NVCF+MW disclosure, NVIDIA_API_KEY check, deps install, TTS+ASR smoke test.06Dynamo Interconnect Checknvidia/skillsValidate that a Dynamo deployment's NIXL/UCX/NCCL interconnect is ready for disaggregated serving over RDMA/NVLink. Use after recipe-runner brings a deployment up (especially disagg/multi-node) to confirm the KV transport is correct; use troubleshoot for diagnosing already-failed pods.07Dynamo Recipe Runnernvidia/skillsSelect, validate, patch, and deploy existing NVIDIA Dynamo Kubernetes recipes. Use for model/backend/GPU/deployment-mode recipe bring-up; use router-starter for router-only mode work and troubleshoot for broken deployments.07Dynamo Router Starternvidia/skillsStart or patch Dynamo router modes and run router endpoint smoke checks. Use for round-robin, KV-aware, least-loaded, or device-aware routing setup; use recipe-runner for recipe deployment and troubleshoot for failure diagnosis.07Dynamo Troubleshootnvidia/skillsDiagnose failed or unhealthy Dynamo deployments. Use when pods, model-cache jobs, PVCs, workers, frontend/router health, endpoints, or benchmark jobs fail; use recipe-runner/router-starter before this for normal bring-up.07Earth2studio Create Datasourcenvidia/skills>019Earth2studio Create Diagnosticnvidia/skills>020Earth2studio Create Prognosticnvidia/skills>018Earth2studio Data Fetchnvidia/skills>08Earth2studio Deterministic Forecastnvidia/skills>012Earth2studio Discovernvidia/skills>05Earth2studio Installnvidia/skills>05Holoscan Install Condanvidia/skillsInstall Holoscan SDK v4.3+ via Conda in a CUDA 13 environment. Use for Conda installs; redirect CUDA 12 hosts to container/wheel.05Holoscan Install Containernvidia/skillsInstall Holoscan SDK via the NGC Docker container. Use for container-based installs; not for native apt/pip/Conda installs.05Holoscan Install Debiannvidia/skillsInstall Holoscan SDK natively on Ubuntu via apt. Use for C++ installs on Ubuntu; pair with /holoscan-install-wheel for Python.05Holoscan Install Sourcenvidia/skillsBuild Holoscan SDK from source via the in-tree ./run script. Use only when published packages don't meet the user's needs.05Holoscan Install Wheelnvidia/skillsInstall Holoscan SDK Python wheel via pip into a venv. Use for Python installs; not for native C++/apt or Conda installs.05Holoscan Setupnvidia/skillsGuides Holoscan SDK installation: inspects the host, assesses platform compatibility, recommends an install method, and delegates to the matching install skill.07Hsb Appnvidia/skillsDiscover and run Holoscan Sensor Bridge example applications on a connected devkit. Filters available apps by the user's platform, HSB software version, board type, and sensors. Supports timed execution, failure analysis, code-edit suggestions, and iterative re-runs.06Hsb Flashnvidia/skillsFlash the FPGA on an HSB board connected to an NVIDIA devkit. Supports HSB Lattice boards (FPGA versions 2407, 2412, 2507, 2510) and Leopard Imaging VB1940 "all-in-one" cameras (FPGA versions 2507, 2510). Uses release-specific YAML manifests and board-type-specific program commands. Lattice and VB1940 commands must never be mixed.017Hsb Setupnvidia/skillsClone the latest NVIDIA Holoscan Sensor Bridge repo, ask which supported devkit is being used, configure the host per platform, build the correct demo container, run it, and verify HSB connectivity by pinging 192.168.0.2. Use for Holoscan Sensor Bridge setup, build, container launch, and first-connectivity bring-up.015
Skills, installed in one click
Start building freePut a skill to work
Open any project, search the Skills panel in the chat, and the agent picks it up from there.