Agent Skills for NVIDIA products — install into Claude Code, Codex, and other coding agents to run Physical AI, robotics, simulation, CUDA, and RAG workflows end to end.
Install
npx skills add NVIDIA/skillsgh skill install NVIDIA/skillsgit clone --depth 1 https://github.com/NVIDIA/skillsSkills in this collection
- Accelerated Computing CudfNVIDIAOfficialOfficial 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.
- Ambient Healthcare Agent With Nemotron Voice AgentNVIDIAOfficialCustomize NVIDIA Nemotron Voice Agent's Generic Pipecat example for healthcare appointment, five-field patient intake, or custom tool-calling workflows without a separate backend.
- Amc Run Rtsp CalibrationNVIDIAOfficialCalibrate 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, AMC ingests them, then runs calibration.
- Amc Run Sample CalibrationNVIDIAOfficialRun 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'.
- Amc Run Video CalibrationNVIDIAOfficialCalibrates 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`.
- Amc Setup Calibration StackNVIDIAOfficialLaunch 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.
- Boltz2 NimNVIDIAOfficialUse Boltz2 NIM for biomolecular structure prediction and binding affinity. Invoke for Boltz2, protein structures, protein-ligand/DNA/RNA complexes, SMILES or CCD ligands, pIC50/IC50 affinity scoring, mmCIF output, hosted NVIDIA API calls, or local Docker deployment.
- Cdf AnomalygenNVIDIAOfficialUse when running the CDF AnomalyGen pipeline over a defect dataset — mask placement, fine-tuning, synthetic defect-image generation (SDG), evaluation, quality refinement, and pseudo-labeling — even when the user names only one stage.
- Cdf AugmentationNVIDIAOfficialUse when authoring or validating Cosmos Data Factory (CDF) augmentation YAML configs, or running remote Cosmos Transfer (including Cosmos3 WSM controls), Cosmos Predict, image-edit, or image-to-video inference.
- Cdf Auto LabelingNVIDIAOfficialUse when a user needs to get started with CDF Auto-Labeling, plan a scenario, run or debug a shipped cookbook, author prompts or cookbooks, migrate a pipeline, configure a stage, or pull the prebuilt stage containers from NGC (nvcr.io). Confirm critical inputs (data path, output path, endpoints) and ask when any are missing.
- Cdf Autonomous Vehicle Dataset GenerationNVIDIAOfficialPrepare payloads, run and monitor the Autonomous Vehicle Dataset Generation Airflow workflow, and inspect results for driving-clip retrieval and Cosmos3-Nano variants. Existing clips with no retrieval use cdf-video-data-augmentation; seed-image event or anomaly generation uses cdf-event-video-generation.
- Cdf Curation And RetrievalNVIDIAOfficialNVIDIA CDF curation and retrieval. Cosmos Curator video and image pipelines (split, dedup, shard, annotate) with filtering, captioning, and embedding. Cosmos Dataset Search ingest, search, and capability qualification. TAO data mining embeddings and neighbor matching. Ships domain event catalogs, including workplace employee conduct monitoring, which requires legal review before use.
- Cdf Defect Image GenerationNVIDIAOfficialGenerate synthetic PCB inspection images on Kubernetes with the SMT Defect Image Generation (DIG) DAG in CDF Orchestration. The DAG renders components in simulation, turns the renders into realistic golden images (sim2real), and uses AnomalyGen to add texture defects such as solder bridges, excess solder or missing components. Simulation can also render shift, tombstone and sideflip pose defects.
- Cdf Event Video GenerationNVIDIAOfficialRun the CDF Orchestration Event Video Generation DAG on Kubernetes or OSMO - image-to-video anomaly generation, auto-labeling, and anomaly dataset generation. Select for requests about event video generation, anomaly video generation, image-to-video synthesis, Cosmos3 image2video, anomaly dataset creation, safety/surveillance SDG, or generating person-falling, person-climbing, person-running…
- Cdf Image Attribute AugmentationNVIDIAOfficialRun the CDF Orchestration Image Attribute Augmentation DAG on Kubernetes - person-crop clothing augmentation, attribute search, and augmented dataset generation. Select for requests about image attribute augmentation, person attribute search, person re-identification data, clothing augmentation, attribute captions, augmentation payloads, run status, or result retrieval.
- Cdf Orchestration PreflightNVIDIAOfficialSet up missing Linux prerequisites and audit whether a Cosmos Data Factory (CDF) Orchestration checkout and its Kubernetes or OSMO environment are ready to install the controller and run every packaged DAG. Use for prerequisite, pre-setup, Kubernetes, GPU, RWX/NFS, credential, controller-readiness, and quick-start checks.
- Cdf Orchestration SetupNVIDIAOfficialUse when the user asks to deploy, install, reinstall, redeploy, upgrade, or connect to the CDF Orchestration Airflow controller. Owns the end-to-end deploy sequence and runs the cdf-orchestration-preflight audit first. Covers make setup, controller image builds, Helm installation, controller connection, port-forwarding, and post-install verification.
- Cdf Orchestration Write DagNVIDIAOfficialUse when a user describes a custom CDF Orchestration pipeline — a specific ordered combination of stages such as augmentation only, auto-labeling only, detection+captioning only, or image attribute augmentation without full auto-labeling — that no existing DAG in airflow/dags/workflows/ covers, and asks for a new Kubernetes DAG.
- Cdf SimulationNVIDIAOfficialComponent-owned guidance for CDF Simulation requests submitted directly or through Airflow-triggered DIG Flow Catalog prompts — golden THT board, THT pin-geometry variation, good/clean SMT images, structural pose defects, and solder texture defects, from a board USD.
- Cdf Video Data AugmentationNVIDIAOfficialRun the CDF Video Data Augmentation Airflow workflow on Kubernetes or OSMO to create Cosmos video-to-video variants and auto-label both source and generated videos. Use for VDA payload authoring, preflight, execution, monitoring, output verification, or result retrieval. OSMO requires external endpoints.
- Codonfm EmbedNVIDIAOfficialValidate coding-sequence CSVs, extract public CodonFM/Encodon embeddings, and choose checkpoints for downstream property modeling.
- Codonfm FinetuneNVIDIAOfficialFine-tune public CodonFM Encodon checkpoints on labeled coding-sequence or coding-variant data using LoRA, head-only, or full fine-tuning. Use when a user explicitly asks to fine-tune CodonFM or Encodon for regression or classification. Support generic public-v1 Encodon workflows only; reject Decodon, MissenseDataset, missense_synom_agg, and generation workflows.
- Codonfm ScoreNVIDIAOfficialValidate, prepare, or run public CodonFM Encodon masked-codon variant scoring and review compatibility of its scoring workflows. Use only when the user explicitly requests CodonFM or Encodon, or that context is already established in the conversation. Do not select this skill for a generic variant-scoring request without that context; ask for the variant and intended analysis first.
- Codonfm SetupNVIDIAOfficialSet up the public CodonFM v1 repository and download public Encodon checkpoints. Use for requests to build or launch the CodonFM development container, configure local data/checkpoint mounts, verify GPU access, or download public Encodon 80M, 600M, 1B, or Cdwt-1B weights.
- Complexa Evaluate PdbsNVIDIAOfficialAgent runbook for evaluating an existing PDB directory through the separately installed first-party Proteina-Complexa CLI. Use to refold or score designs, compute interface pAE, i_pLDDT, scRMSD, motif RMSD, or designability, run complexa analysis, or assess third-party BindCraft, AlphaProteo, or RFdiffusion outputs.
- Complexa SweepNVIDIAOfficialAgent runbook for Proteina-Complexa parameter sweeps through the separately installed first-party CLI and config generator. Use for cartesian-product hyperparameter scans, sweeper YAML authoring, configuration comparisons, ablations, tuning, success-rate ranking, or Pareto searches over quality and wall-clock cost. Do not use for a single existing-job launch or SLURM submission template.
- Complexa TargetNVIDIAOfficialAdd, edit, inspect, or validate Proteina-Complexa target definitions for protein binders, ligand binders, and AME motif scaffolding. Use for target registries, chain/residue selectors, hotspots, ligand fields, and incomplete motif inputs. Covers direct YAML edits and complexa target/validate target commands; running a campaign with an already registered target belongs to complexa-design.
- Compute Sanitizer Diagnose Cuda BugsNVIDIAOfficialDetect and diagnose CUDA correctness bugs with NVIDIA Compute Sanitizer. Routes GPU memory errors, shared-memory data races, uninitialized-memory reads, and synchronization/barrier bugs to the right sub-tool (memcheck, racecheck, initcheck, synccheck) and explains how to build, run, and read the report.
- CUDA-Q GuideNVIDIAOfficialUse for CUDA-Q setup, simulation targets, QPU access, and @cudaq.kernel authoring guidance.
- CUDA-Q ImportingNVIDIAOfficialUse when porting circuits from another framework (e.g. Qiskit) into CUDA-Q kernels while preserving the source algorithm and validation fidelity.
- CufolioNVIDIAOfficialUse when a user asks to build, optimize, backtest, rebalance, or analyze a stock portfolio with Mean-CVaR, efficient frontiers, scenario generation, or NVIDIA cuOpt.
- Cuopt DeveloperNVIDIAOfficialModify, build, test, debug, and contribute to NVIDIA cuOpt (C++/CUDA, Python, server, CI). Use for solver internals, PRs, DCO, and code conventions.
- Cuopt InstallNVIDIAOfficialInstall cuOpt for Python, C, or server via pip, conda, or Docker; verify the install. For building cuOpt from source, see cuopt-developer.
- Cuopt Multi Objective ExplorationNVIDIAOfficialTrace, complete, and interpret the Pareto frontier across competing objectives using repeated single-objective cuOpt solves (weighted-sum and ε-constraint).
- Cuopt Numerical Optimization APINVIDIAOfficialLP, MILP, and QP (beta) with cuOpt — Python, C, and CLI. Use when the user is solving LP, MILP, or QP with any cuOpt interface.
- Cuopt Numerical Optimization API CNVIDIAOfficialLP, MILP, and QP (beta) with cuOpt — C API only. Use when the user is embedding LP, MILP, or QP in C/C++.
- Cuopt Numerical Optimization API CliNVIDIAOfficialLP, MILP, and QP (beta) with cuOpt — CLI only (MPS/LP/QPS files, cuopt_cli). Use when the user is solving LP, MILP, or QP from an MPS or LP file via command line.
- Cuopt Numerical Optimization API PythonNVIDIAOfficialSolve LP, MILP, QP (beta) with cuOpt Python API — linear/quadratic objectives, integer variables, scheduling, portfolio, least squares.
- Cuopt Numerical Optimization FormulationNVIDIAOfficialLP, MILP, QP — concepts, problem-text parsing, and formulation patterns (parameters, constraints, decisions, objective). Concepts only; no API.
- Cuopt Routing API PythonNVIDIAOfficialVehicle routing (VRP, TSP, PDP) with cuOpt — Python API only. Use when the user is building or solving routing in Python.
- Cuopt Routing FormulationNVIDIAOfficialVehicle routing (VRP, TSP, PDP) — problem types and data requirements. Domain concepts; no API or interface.
- Cuopt Server API PythonNVIDIAOfficialcuOpt REST server — start server, endpoints, Python/curl client examples. Use when the user is deploying or calling the REST API.
- Cuopt Server CommonNVIDIAOfficialcuOpt REST server — what it does and how requests flow. Domain concepts; no deploy or client code.
- Cuopt Skill EvolutionNVIDIAOfficialAfter solving a non-trivial problem, detect generalizable learnings and propose skill updates. Always active — applies to every interaction.
- Cupynumeric Hdf5NVIDIAOfficialRead and write large cuPyNumeric arrays to HDF5 with Legate's parallel, distributed HDF5 I/O (legate.io.hdf5: to_file, from_file, from_file_batched). Use when a developer needs to save a cuPyNumeric array to an .h5/.hdf5 file, load an HDF5 dataset into a distributed cuPyNumeric array, read a large HDF5 dataset in chunks, hand arrays to an HPC pipeline as a single file, or accelerate HDF5 disk…
- Cupynumeric InstallNVIDIAOfficialInstall and verify cuPyNumeric for Python — requirements, commands, verification. Source builds are out of scope.
- Cupynumeric Migration ReadinessNVIDIAOfficialPre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment, scaling analysis, or refactor planning.
- Cupynumeric Parallel Data LoadNVIDIAOfficialLoad a sharded, on-disk dataset (sharded .npy, Parquet/Arrow, raw binary, sharded HDF5, custom layouts) into a distributed cuPyNumeric ndarray via a manual partition + leaf @task launch with CPU/OMP/GPU variants. Use when no single-call loader fits, including when per-shard row counts differ across files. Prefer cupynumeric.load or legate.io.hdf5.from_file when they apply.