@skills · Owner

Agent skills by nvidia

443 skills indexed from github.com/nvidia. Reference any of them in AdaL, Claude Code, Cursor or any coding agent — nothing to install.

• accelerated-computing-cudf · Skill · 2,816 stars

  Official NVIDIA-authored guidance for NVIDIA cuDF GPU DataFrames, pandas acceleration, dask-cuDF, ETL, joins, groupby, CSV/Parquet I/O, nullable semantics,

• amc-run-sample-calibration · Skill · 2,816 stars

  Run 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 sam

• amc-run-video-calibration · Skill · 2,816 stars

  Calibrates pre-recorded `cam_*.mp4` datasets through the AutoMagicCalib REST API. Use for user-supplied local MP4s; route live RTSP streams to `amc-run-rts

• amc-setup-calibration-stack · Skill · 2,816 stars

  Launch AutoMagicCalib microservice and web UI from NGC release images via Docker Compose. Use when user says 'deploy auto calibration', 'launch auto calibr

• cudaq-guide · Skill · 2,816 stars

  Use for CUDA-Q setup, simulation targets, QPU access, and @cudaq.kernel authoring guidance.

• cuopt-developer · Skill · 2,816 stars

  Modify, build, test, debug, and contribute to NVIDIA cuOpt (C++/CUDA, Python, server, CI). Use for solver internals, PRs, DCO, and code conventions.

• cuopt-install · Skill · 2,816 stars

  Install 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-exploration · Skill · 2,816 stars

  Trace, complete, and interpret the Pareto frontier across competing objectives using repeated single-objective cuOpt solves (weighted-sum and ε-constraint)

• cuopt-numerical-optimization-api · Skill · 2,816 stars

  LP, 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-formulation · Skill · 2,816 stars

  LP, MILP, QP — concepts, problem-text parsing, and formulation patterns (parameters, constraints, decisions, objective). Concepts only; no API.

• cuopt-routing-api-python · Skill · 2,816 stars

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

• cuopt-server-api-python · Skill · 2,816 stars

  cuOpt REST server — start server, endpoints, Python/curl client examples. Use when the user is deploying or calling the REST API.

• dali-dynamic-mode · Skill · 2,816 stars

  DALI imperative dynamic mode (`nvidia.dali.experimental.dynamic`, ndd): use when working on ndd code or migrating pipelines; skip pipeline-only tasks.

• data-designer · Skill · 2,816 stars

  Use when the user wants to create a dataset, generate synthetic data, or build a data generation pipeline. The argument is the description of the dataset t

• deepstream-dev · Skill · 2,816 stars

  NVIDIA DeepStream SDK development with Python pyservicemaker API. Use when building video analytics pipelines, GStreamer-based video processing, TensorRT i

• deepstream-generate-pipeline · Skill · 2,816 stars

  Build DeepStream GStreamer pipelines interactively. Use when the user asks about pipelines for video/image inference, detection, tracking, or streaming — i

• deepstream-import-vision-model · Skill · 2,816 stars

  Use this skill to bring a supported object-detection vision model from HuggingFace or NVIDIA NGC into an NVIDIA DeepStream pipeline with end-to-end automat

• deepstream-profile-pipeline · Skill · 2,816 stars

  Profile a DeepStream pipeline with Nsight Systems and derive its configs from the measurement. Use when the user asks for an efficient, performant, or prof

• deepstream-sop · Skill · 2,816 stars

  Use this skill when building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP Inference Microservice — a GPU-accelerated Fast

• dicom-metadata-extract · Skill · 2,816 stars

  Used for extracting selected metadata from one DICOM file and flagging standard-tag PHI presence. Not for anonymization or clinical use.

• dicom-series-preflight · Skill · 2,816 stars

  Used for header-only preflight of one DICOM series folder before conversion or inference. Not for de-identification or clinical clearance.

• dicom-series-to-volume · Skill · 2,816 stars

  Used for converting one CT DICOM series folder to a HU NIfTI volume with affine evidence. Not for multi-frame DICOM or clinical use.

• digital-health-clinical-asr-build · Skill · 2,816 stars

  Stage 2 of the Clinical ASR Flywheel. Use when curating clinical terms, tagging IPA, and synthesizing a NeMo manifest. NOT for scoring (use /digital-health

• digital-health-clinical-asr-eval · Skill · 2,816 stars

  Stage 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).

• digital-health-clinical-asr-finetune · Skill · 2,816 stars

  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 offline cycle N+1 re-eval. NOT for ge

• digital-health-clinical-asr-setup · Skill · 2,816 stars

  Stage 1 of Clinical ASR Flywheel. Use when bootstrapping a cycle: NVCF+MW disclosure, NVIDIA_API_KEY check, deps install, TTS+ASR smoke test.

• doca-aes-gcm · Skill · 2,816 stars

  Use this skill when the user is doing hands-on DOCA AES-GCM work on a BlueField DPU or ConnectX NIC — configuring `doca_aes_gcm_task_encrypt` / `_task_decr

• doca-argp · Skill · 2,816 stars

  Use this skill for hands-on DOCA Arg Parser CLI work on a shipped sample or new DOCA-using app — adding / removing / renaming flags; wiring `doca_argp_init

• doca-argus · Skill · 2,816 stars

  Use this skill when the user is deploying or operating the DOCA Argus Service — the packaged BlueField-side runtime-security container that watches the Blu

• doca-bare-metal-deployment · Skill · 2,816 stars

  Running a DOCA-linked binary directly on the hardware, with no container or kubelet: on host x86 with a BlueField NIC over PCIe, or bare-metal on BlueField

• doca-bench · Skill · 2,816 stars

  Run `doca_bench` (DOCA 2.7.0 or newer) to measure throughput, bulk latency, precision latency, or maximum bandwidth for RDMA, Compress, AES-GCM, SHA, DMA,

• doca-bf3-deployment · Skill · 2,816 stars

  Use this skill for BlueField-3 (BF3) day-1 platform bring-up via the classic RShim/BFB path: pushing a BlueField bundle (BFB) to the DPU over RShim with bf

• doca-bf4-deployment · Skill · 2,816 stars

  WARNING: guides IRREVERSIBLE BlueField-4 hardware operations (PLDM firmware burns, ISO reflashes, power cycles, BMC factory resets); every mutating step is

• doca-caps · Skill · 2,816 stars

  Use this skill when the user wants to invoke the read-only doca_caps CLI to ask what DOCA sees on this host — listing DOCA devices and PCIe addresses, list

• doca-comch · Skill · 2,816 stars

  Use this skill when the user is doing hands-on DOCA Comch work on a host + BlueField pair — bringing up host ↔ DPU PCIe control-plane messaging, picking se

• doca-comm-channel-admin · Skill · 2,816 stars

  Use this skill to enumerate host↔DPU DOCA comch (formerly Comm Channel) servers and connections via the shipped doca_comm_channel_admin binary — listing co

• doca-common · Skill · 2,816 stars

  Use this skill whenever the user is doing hands-on DOCA programming on a BlueField DPU or ConnectX NIC and needs the foundation primitives every per-librar

• doca-compress · Skill · 2,816 stars

  Hardware compression offload with DOCA Compress on a BlueField DPU, ConnectX NIC, or host: DEFLATE compress and decompress, plus LZ4 decompress (stream and

• doca-container-deployment · Skill · 2,816 stars

  Running an in-bundle DOCA service as a container on a BlueField (Argus, DMS, Firefly, or UROM service): kubelet standalone watching a static-pod manifests

• doca-debug · Skill · 2,816 stars

  Use this skill when the user is debugging any DOCA symptom — a build that won't compile, a link step that can't resolve a doca_* symbol, a runtime call ret

• doca-devemu · Skill · 2,816 stars

  Use this skill when the user is doing hands-on DOCA Device Emulation on a BlueField DPU — exposing a custom emulated PCIe device the host sees as a real pe

• doca-dma · Skill · 2,816 stars

  Use this skill when the user is doing hands-on DOCA DMA programming — bringing up a doca_dma context, configuring the single doca_dma_task_memcpy task type

• doca-dms · Skill · 2,816 stars

  Operate NVIDIA DOCA Management Service on a BlueField, Arm/x86 host, or Kubernetes pod: from DOCA 3.5 the local `dms-cli` (one command per YANG path, no se

• doca-dpa · Skill · 2,816 stars

  Use this skill when the user is doing hands-on DOCA DPA host-side work on a BlueField — creating the `doca_dpa` Core context, loading a DPACC-compiled DPA

• doca-dpdk-bridge · Skill · 2,816 stars

  Use this skill when the user has an existing DPDK application and is adding DOCA capabilities in-place — most commonly DOCA Flow hardware steering — withou

• doca-erasure-coding · Skill · 2,816 stars

  Hardware-offloaded erasure coding with DOCA Erasure Coding (Reed-Solomon, doca_ec) on a BlueField DPU, ConnectX NIC, or host: generating parity for data bl

• doca-eth · Skill · 2,816 stars

  Use this skill for hands-on DOCA Ethernet packet-queue work on a BlueField DPU or ConnectX NIC — bringing up a `doca_eth_rxq` or `doca_eth_txq` on a port /

• doca-firefly · Skill · 2,816 stars

  Use this skill when the user is operating the DOCA Firefly Service container on BlueField — picking the four PTP configuration axes (role / profile / domai

• doca-flow · Skill · 2,816 stars

  DOCA Flow packet steering on NVIDIA NICs/DPUs, linked into a C application: match/action pipes, ports, representors, forwarding, hairpin, counters. Trigger

• doca-flow-tune · Skill · 2,816 stars

  Use this skill when the user is tuning a live or captured `doca-flow` pipeline with `doca_flow_tune` — snapshotting pipe / counter / KPI state, picking a t

• doca-gpunetio · Skill · 2,816 stars

  Use this skill when the user is doing hands-on DOCA GPUNetIO programming — wiring a CUDA kernel on an NVIDIA GPU to a doca-eth queue via doca_gpu_eth_rxq /

• doca-hardware-safety · Skill · 2,816 stars

  Use this skill whenever the agent is about to recommend or apply a change that touches DPU / NIC hardware state on a live system — mlxconfig firmware-param

• doca-mgmt · Skill · 2,816 stars

  Use this skill when the user is doing hands-on DOCA Management programming against BlueField / ConnectX devices — standing up a management or representor c

• doca-pcc · Skill · 2,816 stars

  Use this skill when the user is doing hands-on host-side DOCA PCC work to load a CUSTOM Programmable Congestion Control algorithm onto a BlueField DPU — cr

• doca-pcc-counters · Skill · 2,816 stars

  Use this skill when the user is invoking the DOCA PCC Counters tool — the `pcc_counters.sh` bash script under the DOCA tools directory — to arm and read th

• doca-programming-guide · Skill · 2,816 stars

  Use this skill when the user is writing their first DOCA app or asking a library-agnostic programming question — picking a shipped sample to copy and modif

• doca-public-knowledge-map · Skill · 2,816 stars

  Use this skill to locate authoritative NVIDIA DOCA information without the source tree: the docs.nvidia.com page for a library/service/tool, which DOCA lib

• doca-rdma · Skill · 2,816 stars

  RDMA data movement on NVIDIA BlueField/ConnectX NICs (RoCE/InfiniBand) with DOCA RDMA, instead of hand-written libibverbs/rdma_cm. Use when the user moves

• doca-rmax · Skill · 2,816 stars

  DOCA Rivermax (doca_rmax) receive streams for timing-precise media over IP (SMPTE ST 2110 video / audio, market data, scientific feeds) on a target BlueFie

• doca-setup · Skill · 2,816 stars

  Use this skill when the user is dealing with the DOCA environment around their workload — verifying an install is healthy, preparing the build env (pkg-con

• doca-sha · Skill · 2,816 stars

  Use this skill when the user needs SHA-1, SHA-256, or SHA-512 digest acceleration on BlueField-2 silicon via doca_sha (absent on BF-3) — selecting one-shot

• doca-sha-offload-engine · Skill · 2,816 stars

  Use this skill when wiring the DOCA SHA Offload Engine (an OpenSSL ENGINE) into an existing OpenSSL pipeline to offload one-shot SHA-1, SHA-256, or SHA-512

• doca-socket-relay · Skill · 2,816 stars

  Use this skill when the operator is driving the DOCA Socket Relay to bridge a socket-oriented host application onto a BlueField DPU peer without rewriting

• doca-spcx-cc · Skill · 2,816 stars

  Use this skill when the user is invoking `doca_spcx_cc` (the host-side CLI under /opt/mellanox/doca/tools/) to load, parameterize, start, observe, or stop

• doca-sta · Skill · 2,816 stars

  Use this skill when the user builds an NVMe-over-Fabrics storage target on BlueField with DOCA STA — instantiating doca_sta, declaring doca_sta_subsystem N

• doca-structured-tools-contract · Skill · 2,816 stars

  Not for writing library code (name that library skill). Use this skill whenever another DOCA skill says "prefer the structured tool per doca-structured-too

• doca-telemetry · Skill · 2,816 stars

  Use this skill to read DOCA hardware-counter events from a `doca_dev` through the per-domain Telemetry reader libraries: `doca_telemetry_pcc`, `_dpa`, `_di

• doca-telemetry-exporter · Skill · 2,816 stars

  Use this skill when the user is doing hands-on DOCA Telemetry Exporter programming on a host where DOCA is installed — defining a doca_telemetry_exporter_s

• doca-telemetry-utils · Skill · 2,816 stars

  doca_telemetry_utils command line on a host with DOCA: discover the diagnostic-counter schema, translate counter names to binary Data IDs and back, and che

• doca-upgrade · Skill · 2,816 stars

  Changing DOCA versions safely: upgrading or downgrading the host DOCA packages, refreshing the BlueField BFB, bumping the NGC DOCA container tag, or rollin

• doca-urom · Skill · 2,816 stars

  Host-side DOCA UROM library (doca_urom_*): offload an HPC / UCX / MPI application's remote memory operations (puts, gets, atomics, collectives) from the ho

• doca-urom-svc · Skill · 2,816 stars

  Operate the DOCA UROM Service container on BlueField Arm for remote memory operations (puts, gets, atomics, collectives) enqueued by a paired host using `d

• doca-verbs · Skill · 2,816 stars

  Raw verbs inside DOCA Core (doca-verbs): direct control of QP, CQ, PD, SRQ and address-handle objects through doca_verbs_context and doca_verbs_qp_create /

• doca-version · Skill · 2,816 stars

  DOCA version handling: detect the installed release and validate the four-way match across pkg-config doca-common, applications/VERSION, doca_caps --versio

• dynamo-interconnect-check · Skill · 2,816 stars

  Validate that a Dynamo deployment's NIXL/UCX/NCCL interconnect is ready for disaggregated serving over RDMA/NVLink. Use after recipe-runner brings a deploy

• dynamo-recipe-runner · Skill · 2,816 stars

  Select, validate, patch, and deploy existing NVIDIA Dynamo Kubernetes recipes. Use for model/backend/GPU/deployment-mode recipe bring-up; use router-starte

• dynamo-router-starter · Skill · 2,816 stars

  Start 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 re

• dynamo-troubleshoot · Skill · 2,816 stars

  Diagnose failed or unhealthy Dynamo deployments. Use when pods, model-cache jobs, PVCs, workers, frontend/router health, endpoints, or benchmark jobs fail;

• earth2studio-create-datasource · Skill · 2,816 stars

  Create and validate Earth2Studio data source wrappers (DataSource, ForecastSource, DataFrameSource, ForecastFrameSource) from remote stores. Do NOT use for

• earth2studio-create-diagnostic · Skill · 2,816 stars

  Create Earth2Studio diagnostic model wrappers for single-step data transformations, including simple derived diagnostics, packaged AutoModel diagnostics, a

• earth2studio-create-prognostic · Skill · 2,816 stars

  Create Earth2Studio prognostic (time-stepping forecast) model wrappers. Do NOT use for diagnostic models, data sources, or installation.

• earth2studio-data-fetch · Skill · 2,816 stars

  Fetch weather/climate data via Earth2Studio data sources for specific variables and times. Do NOT use for inference pipelines, model discovery, or installa

• earth2studio-deterministic-forecast · Skill · 2,816 stars

  Build deterministic forecast scripts with Earth2Studio (model, data source, IO, inference). Do NOT use for ensemble, diagnostics, data-only fetch, or insta

• earth2studio-discover · Skill · 2,816 stars

  Find Earth2Studio models, data sources, and examples for a weather/climate use case. Do NOT use for writing inference code, downloading data, or installati

• earth2studio-install · Skill · 2,816 stars

  Guide installing Earth2Studio via uv or pip, selecting model extras, and configuring the environment. Do NOT use for writing inference code, choosing model

• holoscan-install-conda · Skill · 2,816 stars

  Handle Holoscan SDK 5.x Conda installation requests: explain 5.0 package unavailability, check later releases, and select a supported installation method.

• holoscan-install-container · Skill · 2,816 stars

  Install and verify the Holoscan SDK 5.x CUDA 13 development container after checking release availability and host compatibility.

• holoscan-install-debian · Skill · 2,816 stars

  Install Holoscan SDK 5.x native C++ Debian packages on Ubuntu 24.04, choosing the full SDK or matching modular packages.

• holoscan-install-source · Skill · 2,816 stars

  Build and verify Holoscan SDK 5.x from an explicit source ref with the repository run wrapper; use for Early Access or SDK development.

• holoscan-install-wheel · Skill · 2,816 stars

  Install Holoscan SDK 5.x CUDA 13 Python wheels in an isolated environment, choosing the full stack or version-matched components.

• holoscan-setup · Skill · 2,816 stars

  Assess a host and choose a Holoscan SDK 5.x installation method using release availability, CUDA 13 compatibility, and component needs.

• hsb-app · Skill · 2,816 stars

  Discover and run Holoscan Sensor Bridge example applications on a connected devkit. Filters available apps by the user's platform, HSB software version, bo

• hsb-flash · Skill · 2,816 stars

  Flash 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

• hsb-ip-create-top · Skill · 2,816 stars

  Create or explain fixed-format HSB FPGA_top.sv wrappers from validated HOLOLINK_def.svh files. Do not use for def generation or validation.

• hsb-ip-def · Skill · 2,816 stars

  Generate, validate, compare, or explain HSB HOLOLINK_def.svh macros. Do not use for FPGA_top.sv wrappers or packetizer-only derivation. Generation runs bun

• hsb-ip-packetizer · Skill · 2,816 stars

  Choose or explain HSB Sensor RX packetizer fields for HOLOLINK_def.svh. Do not use for full defs, validation, or runtime APB programming.

• hsb-setup · Skill · 2,816 stars

  Clone the latest NVIDIA Holoscan Sensor Bridge repo, ask which supported devkit is being used, configure the host per platform, build the correct demo cont

• hsb-test · Skill · 2,816 stars

  Execute QA test plans on Holoscan Sensor Bridge hardware. Reads a user-provided test document, filters tests by the user's setup, determines which tests ca

• i4h-lerobot-viz · Skill · 2,816 stars

  Serve and visually inspect a converted LeRobot dataset in the browser. Use for videos and state/action timelines; do not use for raw workflow HDF5 or incom

• i4h-workflow · Skill · 2,816 stars

  Orient users to the i4h workflow runtime and route them to the correct stage skill. Use for architecture, support, or where-to-start questions; do not exec

• i4h-workflow-create · Skill · 2,816 stars

  Create a minimal blank Workflow scaffold with a Scene containing ground and light plus an idle run mode. Use for fast new Workflow scaffolding.

• i4h-workflow-dataset-annotate · Skill · 2,816 stars

  Grade or filter workflow HDF5 episodes with an OpenAI-compatible vision model. Use for visual success labels; do not use for replay, policy evaluation, or

• i4h-workflow-dataset-convert · Skill · 2,816 stars

  Convert workflow HDF5 recordings to LeRobot datasets for training or browser inspection. Use for conversion; do not use for replay, augmentation, or raw-da

• i4h-workflow-dataset-mimic · Skill · 2,816 stars

  Expand workflow HDF5 demonstrations with action jitter, optionally scoped to node segments. Use for synthetic variants; do not use to collect data, alter s

• i4h-workflow-dataset-replay · Skill · 2,816 stars

  Replay a workflow HDF5 episode through its original Scene. Use for visual trajectory and recording verification; do not use for policy evaluation or LeRobo

• i4h-workflow-dataset-teleop · Skill · 2,816 stars

  Record demonstrations through a workflow's teleop Task into workflow HDF5. Use for keyboard, leader, VR, or bus input; do not use for policy evaluation or

• i4h-workflow-e2e · Skill · 2,816 stars

  Run the maintained workflow data-to-policy pipeline from recording through checkpoint validation. Use for full end-to-end requests; do not use for one indi

• i4h-workflow-finetune · Skill · 2,816 stars

  Fine-tune a manifest-backed GR00T or openpi remote Task on compatible LeRobot data. Use for training; do not use for inference-only Tasks or checkpoint rol

• i4h-workflow-scene-edit · Skill · 2,816 stars

  Edit an existing workflow Scene or task contract. Use for assets, layout, cameras, randomization, task text, or success rules; do not use to create a new w

• i4h-workflow-setup · Skill · 2,816 stars

  Preflight and set up the root-level workflow runtime. Use for installation, missing component environments, or third-party failures; do not use for rollout

• i4h-workflow-validate · Skill · 2,816 stars

  Run the root-level workflow runtime policy or rule-based rollouts and verify simulator success. Use for evaluation, checkpoints, or local controllers; do n

• jetson-build-source · Skill · 2,816 stars

  Use when you need to rebuild the BSP overlay — DT, OOT modules, or kernel — from changes under bsp_sources/. Triggers: build bsp, rebuild dtb, rebuild kern

• jetson-customize-camera · Skill · 2,816 stars

  Enable MIPI/GMSL camera sensors on a Jetson Thor or Orin custom carrier by rendering a kernel-DT overlay from the in-tree sensor DTSI. Do NOT use for UPHY

• jetson-customize-clocks · Skill · 2,816 stars

  Use to lock/cap Jetson CPU/GPU/EMC clocks, toggle EMC/CPU DVFS, or change cpufreq governors by editing BPMP DTB and nvpower.sh pre-flash. Do NOT use for li

• jetson-customize-fan · Skill · 2,816 stars

  Use when you need to add, remove, edit, list, or change the boot default of an nvfancontrol fan profile on a Jetson/Tegra (Orin, Thor) target. Triggers: ed

• jetson-customize-mgbe · Skill · 2,816 stars

  Enable Jetson Thor 25G/10G/1G MGBE QSFP via kernel-DT overlay. Do NOT use for UPHY lane allocation or ODMDATA edits.

• jetson-customize-nvpmodel · Skill · 2,816 stars

  Use when you need to add, remove, edit, list, or change the boot default of an nvpmodel power mode on a Jetson/Tegra (Orin, Thor) target. Triggers: edit po

• jetson-customize-pcie · Skill · 2,816 stars

  Per-controller PCIe enable / disable / lanes / link-speed for a Jetson Thor or Orin custom carrier via ODMDATA + kernel-DT overlay. Do NOT use for UPHY lan

• jetson-customize-pinmux · Skill · 2,816 stars

  Per-pin SFIO / direction / initial-state configurator for a Jetson Orin or Thor custom carrier from the pinmux XLSM. Do NOT use for kernel-DT overlay or OD

• jetson-customize-uphy · Skill · 2,816 stars

  Configure Jetson UPHY lane allocation (uphy0/uphy1-config) on Orin/Thor custom carriers. Do NOT use for pinmux or PCIe-only edits.

• jetson-customize-usb · Skill · 2,816 stars

  Enable/disable Jetson USB2/USB3 SS ports via kernel-DT overlay. Do NOT use for UPHY lane allocation or ODMDATA edits.

• jetson-derive-carrier · Skill · 2,816 stars

  Bootstrap a custom carrier board by forking carrier files and scaffolding a DT overlay from the reference devkit. Use after jetson-init-source; not for mod

• jetson-diagnostic · Skill · 2,816 stars

  Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.

• jetson-download-bsp · Skill · 2,816 stars

  Download NVIDIA Jetson Linux BSP artifacts (BSP tarball, sample rootfs, public_sources, x-tools, guides) for the active target. Use for Auto Setup; not for

• jetson-flash-image · Skill · 2,816 stars

  Use to flash a promoted BSP image to a Jetson DUT in RCM mode via flash.sh or l4t_initrd_flash.sh. Do NOT use for BSP customization, image promotion, or ca

• jetson-generate-kb · Skill · 2,816 stars

  Build a per-target knowledge-base markdown next to the active profile by walking the BSP root and source tree. Use after init-image / init-source; not for

• jetson-headless-mode · Skill · 2,816 stars

  Plan and apply safe Jetson headless-mode changes to reclaim GUI and daemon memory.

• jetson-inference-mem-tune · Skill · 2,816 stars

  Pick the serving stack and per-runtime memory flags (vLLM, SGLang, llama.cpp, TensorRT Edge-LLM) for an LLM/VLM workload on any NVIDIA Jetson.

• jetson-init-image · Skill · 2,816 stars

  Extract Jetson Linux + sample-rootfs tarballs and run apply_binaries.sh for the active target, then record bsp_image in the profile. Use after jetson-init-

• jetson-init-source · Skill · 2,816 stars

  Set up the BSP source workspace: Linux_for_Tegra overlay tracker, bsp_sources, Crosstool-NG toolchain. Use after jetson-init-image; not for fetching inputs

• jetson-init-target · Skill · 2,816 stars

  Author a new Jetson target-platform profile (reference_devkit + optional custom_carrier) and update the active pointer. Use to create a target; not for swi

• jetson-link-docs · Skill · 2,816 stars

  Bind pre-downloaded Jetson reference docs (developer guide, design guide, pinmux, schematics) into the active profile documents block. Use after staging do

• jetson-llm-benchmark · Skill · 2,816 stars

  Benchmark Jetson LLM/VLM serving performance across vLLM, llama.cpp, and Ollama with structured JSON output.

• jetson-llm-serve · Skill · 2,816 stars

  Stand up vLLM or SGLang serving on Jetson, using upstream vLLM on Thor and Orin JetPack 7.2+, and NVIDIA-AI-IOT vLLM on older Orin.

• jetson-memory-audit · Skill · 2,816 stars

  Measure Jetson DRAM/NvMap usage and verify before/after memory reclamation with live audit data.

• jetson-optimize-memory · Skill · 2,816 stars

  Reclaim DRAM by disabling unused subsystems across MB1 BCT, MB2 BCT, kernel reserved-memory, and SWIOTLB. Use for headless or no-camera Jetson deployments;

• jetson-package · Skill · 2,816 stars

  Pick Jetson-compatible containers, vLLM runtime images, and Jetson AI Lab PyPI indexes; maps Orin SM 8.7 vs Thor SM 11.0 and JetPack-specific package choic

• jetson-print-bsp-info · Skill · 2,816 stars

  Use when you need to print Jetson BSP info (L4T version, board configs, rootfs state) from a Linux_for_Tegra root on the host PC. This is an example skill.

• jetson-print-device-info · Skill · 2,816 stars

  Use when you need to print Jetson device info (module model, L4T version, kernel, OS version, current power mode) from a running Jetson target. This is an

• jetson-promote-image · Skill · 2,816 stars

  Use to promote overlay files and built artifacts into the staged BSP image. Do NOT use to flash or build. Triggers: promote bsp image.

• jetson-quick-start · Skill · 2,816 stars

  Entry skill for Jetson / IGX BSP customization. Asks one core click-to-select setup questionnaire and passes prefilled answers to downstream setup skills.

• jetson-set-target · Skill · 2,816 stars

  Switch the active Jetson target-platform pointer to an existing profile YAML. Use before customize/build/flash to change target; not for authoring profiles

• jetson-speculative-decoding · Skill · 2,816 stars

  Add EAGLE-3 or draft-model speculative decoding to a Jetson vLLM server when TPOT is the bottleneck.

• jetson-validate-image · Skill · 2,816 stars

  Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers:

• launch-nemo-rl · Skill · 2,816 stars

  Playbook for launching, monitoring, stopping, and debugging NeMo-RL recipes on a Kubernetes cluster via the nrl-k8s CLI. Covers ephemeral vs long-lived Ray

• mcore-create-issue · Skill · 2,816 stars

  Investigate a failing GitHub Actions run or job and create a GitHub issue for the failure.

• mcore-linting-and-formatting · Skill · 2,816 stars

  Linting and formatting for Megatron-LM. Covers running autoformat.sh, tools (ruff, black, isort, pylint, mypy), and code style rules.

• mcore-run-on-slurm · Skill · 2,816 stars

  How to launch distributed Megatron-LM training jobs on a SLURM cluster. Covers a minimal sbatch skeleton, environment-variable setup for torch.distributed.

• mcore-split-pr · Skill · 2,816 stars

  Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.

• mcore-testing · Skill · 2,816 stars

  Test system for Megatron-LM. Covers test layout, recipe YAML structure, adding and running unit and functional tests, golden values, marker filters, and CI

• nemo-automodel-distributed-training · Skill · 2,816 stars

  Guide for selecting and configuring distributed training strategies in NeMo AutoModel, including FSDP2, Megatron FSDP, DDP, and parallelism settings.

• nemo-automodel-launcher-config · Skill · 2,816 stars

  Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.

• nemo-automodel-model-onboarding · Skill · 2,816 stars

  Guide for onboarding new model architectures into NeMo AutoModel, including architecture discovery, implementation patterns, registration, and validation.

• nemo-automodel-recipe-development · Skill · 2,816 stars

  Create and modify NeMo AutoModel training and evaluation recipes, including YAML structure, builders, and execution flow.

• nemo-mbridge-mlm-bridge-training · Skill · 2,816 stars

  Run Megatron-LM (MLM) and Megatron Bridge training with mock or real data. Covers correlation testing, available recipes, and multi-GPU examples.

• nemo-mbridge-multi-node-slurm · Skill · 2,816 stars

  Convert single-node scripts to multi-node Slurm sbatch jobs and debug common multi-node failures. Covers srun-native vs uv run torch.distributed approaches

• nemo-mbridge-perf-activation-recompute · Skill · 2,816 stars

  Validate and use selective and full activation recompute in Megatron Bridge to reduce GPU memory usage at the cost of extra compute. Use for activation mem

• nemo-mbridge-perf-cpu-offloading · Skill · 2,816 stars

  Validate and use CPU offloading in Megatron Bridge, including layer-level activation offloading and fractional optimizer state offloading with HybridDevice

• nemo-mbridge-perf-cuda-graphs · Skill · 2,816 stars

  Validate and use CUDA graph capture in Megatron Bridge, including local full-iteration graphs and Transformer Engine scoped graphs for attention, MLP, and

• nemo-mbridge-perf-expert-parallel-overlap · Skill · 2,816 stars

  Validate and use MoE expert-parallel communication overlap in Megatron-Bridge, including overlap_moe_expert_parallel_comm, delay_wgrad_compute, and flex di

• nemo-mbridge-perf-hierarchical-context-parallel · Skill · 2,816 stars

  Operational guide for enabling hierarchical context parallelism in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification.

• nemo-mbridge-perf-megatron-fsdp · Skill · 2,816 stars

  Operational guide for enabling Megatron FSDP in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification.

• nemo-mbridge-perf-memory-tuning · Skill · 2,816 stars

  Techniques for reducing peak GPU memory in Megatron Bridge — expandable segments, PEFT + SP input re-gather, parallelism resizing, activation recompute, CP

• nemo-mbridge-perf-moe-comm-overlap · Skill · 2,816 stars

  MoE expert-parallel communication overlap in Megatron Bridge. Covers dispatch/combine overlap, flex dispatcher backends, and expert wgrad scheduling.

• nemo-mbridge-perf-moe-dispatcher-selection · Skill · 2,816 stars

  Choose the right MoE token dispatcher (`alltoall`, DeepEP, or HybridEP) for the hardware, EP degree, and optimization stage. Summarizes patterns from DSV3,

• nemo-mbridge-perf-moe-hardware-configs · Skill · 2,816 stars

  Representative, point-in-time MoE training playbooks by hardware and model family. Use them as candidate seeds, then revalidate the exact runtime, semantic

• nemo-mbridge-perf-moe-long-context · Skill · 2,816 stars

  Long-context MoE training guidance for Megatron Bridge. Covers CP sizing, selective recompute, dispatcher choices, and practical patterns from DSV3, Qwen3,

• nemo-mbridge-perf-moe-optimization-workflow · Skill · 2,816 stars

  Evidence-gated workflow for MoE performance optimization in Megatron Bridge. Covers measurement contracts, the Three Walls framework, parallel folding, pro

• nemo-mbridge-perf-moe-vlm-training · Skill · 2,816 stars

  Practical guidance for training MoE VLMs in Megatron Bridge. Compares FSDP and 3D-parallel approaches, using rounded lessons from Qwen3-VL, Qwen3-Next, and

• nemo-mbridge-perf-parallelism-strategies · Skill · 2,816 stars

  Operational guide for choosing and combining parallelism strategies in Megatron Bridge, including sizing rules, hardware topology mapping, and combined par

• nemo-mbridge-perf-sequence-packing · Skill · 2,816 stars

  Validate and use packed sequences and long-context training in Megatron-Bridge, including offline LLM packing, collate-time VLM packing, Energon online pac

• nemo-mbridge-perf-tp-dp-comm-overlap · Skill · 2,816 stars

  Operational guide for enabling TP, DP, and PP communication overlap in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification.

• nemo-mbridge-recipe-recommender · Skill · 2,816 stars

  Recommend and customize Megatron Bridge library and benchmark recipes for a user's model, GPU count, hardware, sequence length, and pretrain/SFT/PEFT goal.

• nemo-mbridge-resiliency · Skill · 2,816 stars

  Resiliency features in Megatron Bridge including fault tolerance, straggler detection, in-process restart, preemption, and re-run state machine.

• nemo-relay-debug-runtime-integration · Skill · 2,816 stars

  Use this skill when NeMo Relay is installed or imported but application-side runtime behavior is missing or incorrect, including load failures, inactive sc

• nemo-relay-get-started · Skill · 2,816 stars

  Use this skill when first-time NeMo Relay users want help selecting and following an appropriate quick-start guide or verifying their first working integra

• nemo-relay-install · Skill · 2,816 stars

  Use this skill when choosing or running NeMo Relay installation for an agent runtime, application language, framework integration, or plugin bundle, or che

• nemo-relay-instrument-calls · Skill · 2,816 stars

  Use this skill when an application owns tool or LLM/provider call sites and needs to wrap them with NeMo Relay scopes and managed execution APIs for lifecy

• nemo-relay-instrument-context-isolation · Skill · 2,816 stars

  Use this skill when concurrent requests, async tasks, threads, workers, goroutines, or agents need independent NeMo Relay scope stacks and correct ancestry

• nemo-relay-instrument-typed-wrappers · Skill · 2,816 stars

  Use this skill when adding NeMo Relay typed wrappers, domain types, or provider codecs while preserving JSON middleware semantics and caller-visible behavi

• nemo-relay-migrate-from-flow · Skill · 2,816 stars

  Use this skill when migrating applications, examples, integrations, documentation, manifests, or repository code from NeMo Flow to NeMo Relay across Python

• nemo-relay-plugin-adaptive-tuning · Skill · 2,816 stars

  Use this skill when baseline NeMo Relay instrumentation exists and the user wants to configure or evaluate adaptive plugin behavior, including telemetry, s

• nemo-relay-plugin-build · Skill · 2,816 stars

  Use this skill when building or packaging reusable NeMo Relay runtime behavior as an embedded configuration component or a manifest-backed `rust_dynamic` n

• nemo-relay-plugin-observability · Skill · 2,816 stars

  Use this skill when choosing or configuring NeMo Relay 0.6 or 0.7 observability through the built-in plugin, subscribers, or exporters, including raw ATOF

• nemo-retriever · Skill · 2,816 stars

  Use when searching, extracting, ingesting, or querying a document collection with the NeMo Retriever 26.8.1 CLI, including local LanceDB indexes and deploy

• nemo-rl-auto-research · Skill · 2,816 stars

  Autonomous NeMo-RL research agent workflow for directed hypothesis testing and open-ended discovery. Guides agents through the full experiment lifecycle: u

• nemo-rl-brev-etiquette · Skill · 2,816 stars

  Brev instance operating guidance for NeMo-RL agents working in /home/ubuntu/RL with limited workspace disk, a larger /ephemeral volume, and optional /home/

• nemo-rl-docs · Skill · 2,816 stars

  Documentation conventions for NeMo-RL. Covers docs/index.md updates and docstring format. Do NOT use for: bug fixes, test fixes, dependency bumps, refactor

• nemo-rl-session-memory · Skill · 2,816 stars

  Manage durable working-session memory for coding agents. Use when a user asks to preserve or recover agent context across disconnects, VS Code restarts, lo

• nemoclaw-user-guide · Skill · 2,816 stars

  Guides human users' AI agents to the NemoClaw docs MCP server and canonical Fern documentation in Markdown form. Use when users ask how to install, configu

• nemotron-asr-finetune · Skill · 2,816 stars

  Orchestration skill for NVIDIA Nemotron Speech (Riva) / NeMo ASR domain and language adaptation. Given a goal like "improve/fine-tune ASR for my domain or

• nemotron-customize · Skill · 2,816 stars

  Plan, configure, and chain repo-native Nemotron customization steps into single-step or multi-step pipelines: curation, translation, SFT/PEFT (AutoModel or

• nemotron-policy-generator · Skill · 2,816 stars

  Generates BYO custom safety policies for NVIDIA Nemotron content-safety guardrails — Nemotron-Content-Safety-Reasoning-4B (text) and multimodal Nemotron-3-

• nemotron-retrieval-recipes · Skill · 2,816 stars

  Use when planning, debugging, tuning, evaluating, exporting, or deploying public Nemotron `embed`/`rerank` retrieval recipes.

• nemotron-speech · Skill · 2,816 stars

  Routes NVIDIA Nemotron Speech (Formerly Riva) NIM tasks — deploys, runs, and tests ASR, TTS, and NMT NIMs on build.nvidia.com or self-hosted.

• nv-generate-ct-rflow · Skill · 2,816 stars

  Used for generating synthetic CT volumes and masks with NV-Generate-CTMR rflow-ct. Not for production training data without review.

• nv-generate-mr · Skill · 2,816 stars

  Used for generating synthetic body MRI volumes with NV-Generate-CTMR rflow-mr. Not for paired masks or production training data.

• nv-generate-mr-brain · Skill · 2,816 stars

  Used for generating synthetic T1, T2, FLAIR, SWI, or MRA brain MRI volumes with NV-Generate-CTMR MR-Brain v1. Not for production training data.

• nv-generate-mr-brain-finetune · Skill · 2,816 stars

  Used for finetuning NV-Generate-CTMR MR-Brain v1 for T1, T2, FLAIR, SWI, or MRA data from a NIfTI datalist. Not for clinical or production data approval.

• nv-generate-vae-finetune · Skill · 2,816 stars

  Used for finetuning the NV-Generate-CTMR MAISI VAE from CT/MRI NIfTI datalists. Not for clinical or production data approval.

• nv-reason-cxr · Skill · 2,816 stars

  Used for command-shape or live NV-Reason-CXR chest X-ray reasoning smoke tests. Not for diagnosis or clinical reporting.

• nv-segment-ct · Skill · 2,816 stars

  Used for running NV-Segment-CT VISTA3D on CT NIfTI volumes and recording label-map evidence.

• nv-segment-ct-finetune · Skill · 2,816 stars

  Runs standard or fixed-channel softmax finetuning of NV-Segment-CT VISTA3D on CT NIfTI image/label datasets, with optional MONAI-native MLflow tracking and

• nv-segment-ctmr · Skill · 2,816 stars

  Used for running NV-Segment-CTMR on CT or MRI NIfTI volumes and recording label-map evidence. Not for clinical interpretation.

• nvidia-skill-finder · Skill · 2,816 stars

  Use for NVIDIA-related requests where an NVIDIA skill might help, even if the user did not ask for a skill. Trigger on NVIDIA products, hardware, software,

• nvidia-skill-finder · Skill · 2,816 stars

  Use for NVIDIA-related requests where an NVIDIA skill might help, even if the user did not ask for a skill. Trigger on NVIDIA products, hardware, software,

• nvidia-skills · Collection · 2,816 stars
• omniverse-cad-to-simready · Skill · 2,816 stars

  Coordinate the end-to-end CAD/source-asset to SimReady workflow. Use for broad requests such as CAD to SimReady, source asset to simulation-ready USD, or p

• omniverse-realtime-viewer · Skill · 2,816 stars

  Use as the top-level router for Omniverse Realtime Viewer USD apps, XR delivery, SPG GPU processing, stylized rendering, and focused viewer reference docum

• omniverse-usd-performance-tuning · Skill · 2,816 stars

  Diagnose and optimize USD stages for slow loading, high memory, low FPS or validation; preserve asset boundaries and reuse shared definitions.

• physical-ai-defect-image-generation · Skill · 2,816 stars

  Use when the user wants to orchestrate defect image generation with NVIDIA Cosmos AnomalyGen (Cosmos-Predict2-derived) on OSMO for PCBA, metal surface, and

• physical-ai-infrastructure-setup-and-resilient-scaling · Skill · 2,816 stars

  Use when the user wants to set up, scale, validate, or harden NVIDIA physical AI infrastructure for synthetic data generation workflows across local MicroK

• physical-ai-neural-reconstruction · Skill · 2,816 stars

  Router for NVIDIA NuRec/NRE: USDZ rendering, NCore conversion, 3DGS, gRPC sensor sim, carline adaptation, PhysicalAI HF datasets. Do NOT use for SimReady o

• physical-ai-video-data-augmentation · Skill · 2,816 stars

  Use when running video data augmentation and auto-labeling workflows on OSMO: flow selection, preflight, submit-time interpolation, monitoring, and output

• physicsnemo-discover · Skill · 2,816 stars

  Official NVIDIA-authored guidance for navigating PhysicsNeMo — pick the model, datapipe, or example for a SciML/AI4Science task (surrogates, forecasting, d

• physicsnemo-shard-tensor · Skill · 2,816 stars

  Official NVIDIA-authored guidance for PhysicsNeMo ShardTensor domain parallelism — integrate domain parallelism into training/inference scripts (new or exi

• plugins · Collection · 2,816 stars
• portfolio-optimization · Skill · 2,816 stars

  Use when a user asks to build, optimize, backtest, rebalance, or analyze a stock portfolio with Mean-CVaR, Mean-Variance/SOCP variance caps, efficient fron

• rag-blueprint · Skill · 2,816 stars

  NVIDIA RAG Blueprint — deploy, configure, troubleshoot, and manage. Handles any RAG action: deploy, install, start, enable, disable, toggle, change, config

• rag-eval · Skill · 2,816 stars

  Filesystem RAG benchmarks: corpus/, train.json, evaluate_rag.py (RAGAS quality). Not for prod monitoring, latency/throughput benchmarking (use rag-perf), o

• rag-perf · Skill · 2,816 stars

  Performance benchmarking for a deployed NVIDIA RAG Blueprint server: profiling pass + aiperf load test driven by a single YAML config. Not for accuracy / R

• skill-card-generator · Skill · 2,816 stars

  Use only to generate or update a governance skill card for a specified existing agent skill directory. Do not use for explaining, listing, comparing, or di

• skills · Collection · 2,816 stars
• skills · Collection · 2,816 stars
• skills · Collection · 2,816 stars
• tao-analyze-changenet-rca · Skill · 2,816 stars

  Performs deep Root Cause Analysis (RCA) on NVIDIA TAO Visual ChangeNet classification experiments with

• tao-analyze-gaps-visual-changenet · Skill · 2,816 stars

  Performs gap analysis on NVIDIA TAO VCN Classify (Visual Component Net) experiments by invoking the pinned TAO data-services container directly via `docker

• tao-analyze-gaps-vlm-bcq · Skill · 2,816 stars

  Extract false-positive and false-negative gaps from VLM binary-classification-question (BCQ, yes/no) predictions.

• tao-convert-dataset-format · Skill · 2,816 stars

  Run `tao-daft convert` to convert NVIDIA TAO DAFT datasets between supported formats. Do not use for non-DAFT data.

• tao-finetune-clip · Skill · 2,816 stars

  CLIP vision-language model for image-text retrieval, zero-shot classification, embedding extraction, ONNX

• tao-finetune-cosmos-embed · Skill · 2,816 stars

  Cosmos-Embed1 video-text embedding for text-to-video retrieval, video-to-video search, semantic deduplication, and fine-tuning. Use when the user asks to "

• tao-finetune-cosmos-reason · Skill · 2,816 stars

  Shared Cosmos3 frontend that explicitly routes Cosmos Framework and Cosmos-RL, validates runtime model/video-dataset/SLURM inputs, consumes an SQSH or pack

• tao-finetune-huggingface-model · Skill · 2,816 stars

  Fine-tune any HuggingFace CV / VLM / LLM model on local NVIDIA GPUs inside an NGC PyTorch container when no dedicated TAO model skill matches. Use when the

• tao-generate-image-grounding · Skill · 2,816 stars

  Two-step image grounding pipeline: extracts referring expressions from (image, caption) pairs and grounds them

• tao-generate-referring-expressions · Skill · 2,816 stars

  Four-step image referring-expression pipeline: turns images plus KITTI bounding-box labels into region

• tao-generate-video-reasoning-annotations · Skill · 2,816 stars

  Multi-step video annotation pipeline that turns raw videos into Chain-of-Thought training data — multi-level captions, structured descriptions, and QA pair

• tao-launch-workflow · Skill · 2,816 stars

  The mandatory pre-launch gate and four-verb execution contract for every TAO workflow or action. Invoke BEFORE launching anything side-effecting — AutoML,

• tao-list-capabilities · Skill · 2,816 stars

  Answer what the TAO Skill Bank plugin can do by generating the response from packaged application, data, model, AutoML, and platform manifests. Use when th

• tao-mine-aoi-images · Skill · 2,816 stars

  Runs the DEFT embed-then-mine workflow for VCN AOI iterations — embeds the gap-analysis target parquet, embeds a source pool, and mines nearest-neighbour s

• tao-port-huggingface-model · Skill · 2,816 stars

  Integrate a HuggingFace Computer Vision model into the NVIDIA TAO Toolkit ecosystem (tao-core config, tao-pytorch trainer, tao-deploy TensorRT pipeline). U

• tao-route-visual-changenet-samples · Skill · 2,816 stars

  Routes the weakest VCN samples (output of `tao-analyze-gaps-visual-changenet`) into per-augmentation-module

• tao-run-automl · Skill · 2,816 stars

  Run container-backed AutoML / hyperparameter optimization (HPO) for NVIDIA TAO networks using AutoMLRunner. Handles algorithm

• tao-run-automl-deft-pipeline · Skill · 2,816 stars

  Run the canonical NVIDIA AOI three-phase training pipeline — Phase 1 AutoML baseline (HPO), Phase 2 DEFT loop (RCA → SDG → mining → plain-train retrain), P

• tao-run-deft-aoi · Skill · 2,816 stars

  Run the full DEFT AOI improvement loop for NVIDIA TAO VisualChangeNet / ChangeNet PCB inspection models: baseline evaluate, RCA, Cosmos AnomalyGen / AMP sy

• tao-run-inference-service · Skill · 2,816 stars

  Start, query, and stop a network-specific TAO inference microservice ({network_arch}-inference-microservice) by delegating container execution to the appro

• tao-run-on-brev · Skill · 2,816 stars

  Run a TAO training/evaluation/inference container on an NVIDIA Brev GPU instance. Instance provisioning (create/search/stop/delete/login) is delegated to t

• tao-run-on-docker · Skill · 2,816 stars

  The Docker execution platform for TAO jobs — a local daemon or a remote GPU box via DOCKER_HOST=ssh://user@host. Implements the four-verb consumer contract

• tao-run-on-kubernetes · Skill · 2,816 stars

  Kubernetes execution platform — submits TAO container jobs as k8s Jobs with NVIDIA GPU scheduling; single-pod

• tao-run-on-slurm · Skill · 2,816 stars

  Remote SLURM GPU cluster execution over SSH with sbatch/srun, Pyxis/Enroot containers, and Lustre-backed

• tao-setup-nvidia-gpu-host · Skill · 2,816 stars

  Host setup for TAO GPU backends. Checks and, after user approval, installs minimum-compatible NVIDIA driver, CUDA Toolkit, and NVIDIA Container Toolkit ver

• tao-train-action-recognition · Skill · 2,816 stars

  Action recognition from video sequences. Supports RGB, optical flow, and joint (multi-stream) input types for

• tao-train-bevfusion · Skill · 2,816 stars

  BEVFusion for multi-sensor 3D object detection. Fuses LiDAR point clouds and camera images in bird's-eye-view

• tao-train-centerpose · Skill · 2,816 stars

  CenterPose for keypoint / pose estimation. Detects object centers and regresses keypoint locations for 6-DoF

• tao-train-deformable-detr · Skill · 2,816 stars

  Deformable DETR for 2D object detection. Uses deformable attention for efficient multi-scale feature processing,

• tao-train-depth-anything-v2 · Skill · 2,816 stars

  Monocular depth estimation using Metric Depth Anything v2 or Relative Depth Anything architectures. Predicts

• tao-train-dino · Skill · 2,816 stars

  DINO (DETR with Improved DeNoising Anchor Boxes) for 2D object detection. Transformer-based detector with

• tao-train-fast-foundation-stereo · Skill · 2,816 stars

  Real-time stereo depth estimation using FastFoundationStereo (FFS), the distilled bp2 commercial variant of

• tao-train-foundation-stereo · Skill · 2,816 stars

  Stereo depth estimation using FoundationStereo. Predicts disparity maps from stereo image pairs for 3D

• tao-train-grounding-dino · Skill · 2,816 stars

  Grounding DINO for open-set object detection. Combines DINO-style detection with a BERT text encoder for

• tao-train-image-classification · Skill · 2,816 stars

  PyTorch-based TAO image classification. Supports a wide range of backbones (FAN, EfficientNet, ResNet, etc.)

• tao-train-mask-auto-encoder · Skill · 2,816 stars

  Masked Auto-Encoder (MAE) for self-supervised pretraining and fine-tuning. Masks random patches and reconstructs

• tao-train-mask-auto-label · Skill · 2,816 stars

  MAL (Mask Auto-Label) for weakly-supervised segmentation. Produces segmentation masks from minimal annotations

• tao-train-mask-grounding-dino · Skill · 2,816 stars

  Mask Grounding DINO for grounded instance segmentation. Extends Grounding DINO with a mask-prediction head for

• tao-train-mask2former · Skill · 2,816 stars

  Mask2Former for universal image segmentation (panoptic, instance, and semantic). Transformer-based with

• tao-train-metric-learning-recognition · Skill · 2,816 stars

  Metric-learning recognition (ml-recog) for fine-grained visual recognition. Learns embeddings for

• tao-train-nvdinov2 · Skill · 2,816 stars

  NVDINOv2 for self-supervised visual representation learning. Trains vision transformers via self-distillation

• tao-train-nvpanoptix3d · Skill · 2,816 stars

  NVPanoptix3D for panoptic 3D scene reconstruction from posed RGB images. Produces 3D panoptic segmentation

• tao-train-ocdnet · Skill · 2,816 stars

  OCDNet for scene text detection. Detects arbitrary-oriented text regions in natural images using a

• tao-train-ocrnet · Skill · 2,816 stars

  OCRNet for scene text recognition. Recognizes text content from cropped text-region images and supports CTC

• tao-train-oneformer · Skill · 2,816 stars

  OneFormer for universal image segmentation. Unifies panoptic, instance, and semantic segmentation with a

• tao-train-optical-inspection · Skill · 2,816 stars

  Optical Inspection for defect detection using Siamese networks. Compares image pairs to detect manufacturing

• tao-train-pointpillars · Skill · 2,816 stars

  PointPillars for 3D object detection from LiDAR point clouds. Encodes point clouds into a pseudo-image via a

• tao-train-pose-classification · Skill · 2,816 stars

  Pose classification using ST-GCN (Spatial Temporal Graph Convolutional Network). Classifies skeleton sequences

• tao-train-reid · Skill · 2,816 stars

  Person re-identification (ReID). Learns discriminative embeddings to match the same person across different

• tao-train-rtdetr · Skill · 2,816 stars

  RT-DETR (Real-Time DEtection TRansformer) for 2D object detection. Designed for real-time inference with

• tao-train-segformer · Skill · 2,816 stars

  SegFormer for semantic segmentation. Lightweight transformer-based architecture with hierarchical feature

• tao-train-single-step · Skill · 2,816 stars

  Standard single-step train/eval/export workflow for any TAO model. Use when training a TAO model on a dataset

• tao-train-sparse4d · Skill · 2,816 stars

  Prepare calibrated multi-camera data and train, evaluate, run inference, export, or quantize TAO Sparse4D 3D detection and tracking models. Includes 2D-to-

• tao-train-visual-changenet · Skill · 2,816 stars

  Visual ChangeNet for binary image classification and segmentation in AOI defect detection. Use when training,

• tao-validate-dataset-format · Skill · 2,816 stars

  Run `tao-daft validate` to check NVIDIA TAO DAFT datasets for structure, schema, and cross-reference errors. Do

• tilegym-adding-cutile-kernel · Skill · 2,816 stars

  Add a new cuTile GPU kernel operator to TileGym. Covers dispatch registration in ops.py, cuTile backend implementation, __init__.py exports, test creation,

• tilegym-converting-cutile-to-julia · Skill · 2,816 stars

  Converts cuTile Python GPU kernels (@ct.kernel) to cuTile.jl Julia equivalents. Handles kernel syntax translation, 0-indexed to 1-indexed conversion, broad

• tilegym-converting-cutile-to-triton · Skill · 2,816 stars

  Converts cuTile GPU kernels (@ct.kernel) to Triton (@triton.jit). Handles standard in-repo conversion, debugging (cudaErrorIllegalAddress, shape mismatch,

• tilegym-cutile-autotuning · Skill · 2,816 stars

  Use when adding, modifying, optimizing, or debugging CuTile autotuning code. Trigger signals: `exhaustive_search` / `replace_hints` / `hints_fn` / `cuda.ti

• tilegym-cutile-python · Skill · 2,816 stars

  Expert cuTile programming assistant. Write high-performance GPU kernels using cuTile's tile-based programming model with proper validation and optimization

• tilegym-improve-cutile-kernel-perf · Skill · 2,816 stars

  Iteratively optimize cuTile kernel performance through systematic profiling, bottleneck analysis, IR comparison, and targeted tuning. Covers tile sizes, oc

• tilegym-monkey-patch-kernels-to-transformers · Skill · 2,816 stars

  Integrate TileGym kernels into Hugging Face `transformers` models by replacing the library's submodule(s) and certain class(es)' implementations, and patch

• ambient-healthcare-agent-with-nemotron-voice-agent · Skill

  Customize NVIDIA Nemotron Voice Agent's Generic Pipecat example for healthcare appointment, five-field patient intake, or custom tool-calling workflows wit

• amc-run-rtsp-calibration · Skill

  Calibrate 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 camer

• boltz2-nim · Skill

  Use Boltz2 NIM for biomolecular structure prediction and binding affinity. Invoke for Boltz2, protein structures, protein-ligand/DNA/RNA complexes, SMILES

• cdf-anomalygen · Skill

  Use when running the CDF AnomalyGen pipeline over a defect dataset — mask placement, fine-tuning, synthetic defect-image generation (SDG), evaluation, qual

• cdf-augmentation · Skill

  Use when authoring or validating Cosmos Data Factory (CDF) augmentation YAML configs, or running remote Cosmos Transfer (including Cosmos3 WSM controls), C

• cdf-auto-labeling · Skill

  Use 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 pipel

• cdf-autonomous-vehicle-dataset-generation · Skill

  Prepare payloads, run and monitor the Autonomous Vehicle Dataset Generation Airflow workflow, and inspect results for driving-clip retrieval and Cosmos3-Na

• cdf-curation-and-retrieval · Skill

  NVIDIA CDF curation and retrieval. Cosmos Curator video and image pipelines (split, dedup, shard, annotate) with filtering, captioning, and embedding. Cosm

• cdf-defect-image-generation · Skill

  Generate synthetic PCB inspection images on Kubernetes with the SMT Defect Image Generation (DIG) DAG in CDF Orchestration. The DAG renders components in s

• cdf-event-video-generation · Skill

  Run the CDF Orchestration Event Video Generation DAG on Kubernetes or OSMO - image-to-video anomaly generation, auto-labeling, and anomaly dataset generati

• cdf-image-attribute-augmentation · Skill

  Run the CDF Orchestration Image Attribute Augmentation DAG on Kubernetes - person-crop clothing augmentation, attribute search, and augmented dataset gener

• cdf-orchestration-preflight · Skill

  Set up missing Linux prerequisites and audit whether a Cosmos Data Factory (CDF) Orchestration checkout and its Kubernetes or OSMO environment are ready to

• cdf-orchestration-setup · Skill

  Use when the user asks to deploy, install, reinstall, redeploy, upgrade, or connect to the CDF Orchestration Airflow controller. Owns the end-to-end deploy

• cdf-orchestration-write-dag · Skill

  Use when a user describes a custom CDF Orchestration pipeline — a specific ordered combination of stages such as augmentation only, auto-labeling only, det

• cdf-simulation · Skill

  Component-owned guidance for CDF Simulation requests submitted directly or through Airflow-triggered DIG Flow Catalog prompts — golden THT board, THT pin-g

• cdf-video-data-augmentation · Skill

  Run the CDF Video Data Augmentation Airflow workflow on Kubernetes or OSMO to create Cosmos video-to-video variants and auto-label both source and generate

• codonfm-embed · Skill

  Validate coding-sequence CSVs, extract public CodonFM/Encodon embeddings, and choose checkpoints for downstream property modeling.

• codonfm-finetune · Skill

  Fine-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

• codonfm-score · Skill

  Validate, prepare, or run public CodonFM Encodon masked-codon variant scoring and review compatibility of its scoring workflows. Use only when the user exp

• codonfm-setup · Skill

  Set up the public CodonFM v1 repository and download public Encodon checkpoints. Use for requests to build or launch the CodonFM development container, con

• complexa-evaluate-pdbs · Skill

  Agent runbook for evaluating an existing PDB directory through the separately installed first-party Proteina-Complexa CLI. Use to refold or score designs,

• complexa-sweep · Skill

  Agent runbook for Proteina-Complexa parameter sweeps through the separately installed first-party CLI and config generator. Use for cartesian-product hyper

• complexa-target · Skill

  Add, edit, inspect, or validate Proteina-Complexa target definitions for protein binders, ligand binders, and AME motif scaffolding. Use for target registr

• compute-sanitizer-diagnose-cuda-bugs · Skill

  Detect and diagnose CUDA correctness bugs with NVIDIA Compute Sanitizer. Routes GPU memory errors, shared-memory data races, uninitialized-memory reads, an

• cudaq-importing · Skill

  Use when porting circuits from another framework (e.g. Qiskit) into CUDA-Q kernels while preserving the source algorithm and validation fidelity.

• cudf-query-engine-builder · Skill

  Build the first native, single-GPU cuDF path in a query engine, or complete its initial adapter. Use for libcudf C++ or cuDF Java implementation, buffer ow

• cuequivariance · Skill

  Use when defining cuEquivariance groups and irreps, building equivariant tensor products, or validating segmented polynomials with NumPy.

• cuequivariance-jax · Skill

  Use when writing or debugging cuEquivariance JAX polynomials, irrep dictionaries, Flax NNX layers, or CPU/CUDA execution and layouts.

• cuequivariance-torch · Skill

  Use when building or debugging cuEquivariance PyTorch tensor products or equivariant GNNs, especially CPU references, layouts, indexing, and gradients.

• cuml · Skill

  Use when writing, running, debugging or upgrading Python code that uses NVIDIA cuML (GPU machine learning), cuml.accel (zero-code-change GPU acceleration o

• deepstream-run-mv3dt · Skill

  Run and operate the DeepStream Multi-View 3D Tracking reference app, also known as MV3DT. Use when the user asks to set up prerequisites, run shipped MV3DT

• dgx-spark-skills · Skill

  Use for NVIDIA DGX Spark and related GB10 system identification, capacity, troubleshooting, known issues, updates, recovery, playbooks, examples, NVIDIA Sy

• diffdock-nim · Skill

  Run DiffDock molecular docking via NVIDIA NIM to predict small-molecule binding poses against protein targets. Use for DiffDock, molecular docking, ligand

• doca-dts · Skill

  Deploy and configure the NVIDIA DOCA Telemetry Service (DTS) as it is actually run: (A) BlueField (built-in static pod), (B) Host (docker) on x86_64 / aarc

• doca-ngauge · Skill

  Use this skill when the operator is driving the DOCA ngauge tool to analyze, visualize, and debug network performance on a single node by probing NIC hardw

• doca-perftest · Skill

  Use this skill when the user is running DOCA Perftest (doca_perftest), the RDMA benchmark that measures bandwidth, message rate and latency for RDMA verbs,

• doca-pipeline-language-developer-tools · Skill

  Use this skill when the operator is driving the DOCA Pipeline Language (DPL) Developer Tools to inspect or debug DPL programs on a BlueField DPU — DPL Nspe

• doca-telemetry-traceback-application · Skill

  Use this skill when the operator is driving the DOCA Telemetry Traceback application to monitor telemetry data locally on a BlueField DPU or ConnectX NIC,

• drug-discovery-pipeline · Skill

  NOTE: molecule and target inputs and your NGC_API_KEY are transmitted to external NVIDIA-hosted API endpoints on every call. Use local NIM containers for c

• ethos-explore · Skill

  Captures what an AI agent is supposed to do — its purpose, boundaries, and success criteria — as a durable snapshot for anyone building, evaluating, review

• ethos-orchestrate · Skill

  Entry point for an AI agent's ETHOS.md: a durable snapshot of what the agent is for, what it must not do, and what success looks like. Routes a request to

• ethos-write · Skill

  Writes an AI agent's ethos.md — a durable snapshot of its purpose, intended behavior, boundaries, and success criteria — from the answers gathered by ethos

• evo2-nim · Skill

  Generate and analyze DNA sequences using NVIDIA's Evo 2 BioNeMo NIM microservice. Use for Evo2/Evo 2, DNA generation, genomic sequence generation, hosted g

• foundationpose-pipeline · Skill

  Adapt BOP datasets, run the FoundationPose perception pipeline with TAO depth, and evaluate or re-score pose results. Use for dataset runs and result compa

• foundationpose-setup · Skill

  Install or repair the FoundationPose perception pipeline and build its FoundationStereo TensorRT engines. Use for SAM3/TAO dependency conflicts, CUDA libra

• g-assist-mcp-skill · Skill

  Use this skill to check or change this machine's NVIDIA display and GPU settings, such as resolution, refresh rate, V-Sync, G-SYNC, brightness, color, and

• genmol-nim · Skill

  Generate novel drug-like molecules using the GenMol NIM microservice. Use for de novo generation, scaffold decoration, motif extension, lead optimization,

• genomics-workflow-acceleration · Skill

  Use when accelerating existing genomics workflows with NVIDIA Parabricks, improving runtime or price/performance, converting pipeline steps to GPUs, or com

• holoscan-app-debug-build-run · Skill

  Use when a concrete holoscan command in holoscan-applications or a standalone Module fails, hangs, regresses, or returns wrong output.

• holoscan-module-lifecycle · Skill

  Develop external Holoscan Modules with the Holoscan CLI and use them in Holoscan applications: scaffold, test, Python bindings, DEB/WHEEL packaging, and cl

• i4h-workflow-train-rl · Skill

  Use when training, evaluating, or exporting Workflow policies with online RSL-RL or RLinf, including RL checkpoint and Workflow handoff.

• isaac-cable-insertion-policy-deployment · Skill

  Export a trained Isaac Lab DisplayPort task-space checkpoint with LEAPP, run it through Isaac ROS Deploy and Isaac Sim 6.0 in separate Docker containers, v

• isaac-cable-insertion-policy-training · Skill

  Set up the standalone IsaacLabTraining package from NVIDIA-ISAAC-ROS/isaac_ros_manipulation, then launch, monitor, resume, evaluate, and tune DisplayPort i

• isaac-humanoid-cloud-control · Skill

  Run streamed Unitree G1 cloud-navigation demos in Isaac Sim with guarded gantry release. Use for demo, destination, Mission Control, or cleanup requests.

• isaac-mission-control-showcase · Skill

  Run and validate an end-to-end Mission Control showcase with a locally installed Isaac Sim launched in its GUI window, driven through the isaac-sim-remote

• jetson-video-benchmark · Skill

  Use when measuring Jetson Video Codec SDK or PyNvVideoCodec encode/decode throughput, comparing presets or surfaces, testing codec-worker capacity with aut

• jetson-video-capability · Skill

  Use when Jetson codec, profile, chroma, bit-depth, dimension, engine-count, or operational support must be reconciled from live APIs, authenticated NVIDIA

• jetson-video-pipeline · Skill

  Use when planning, executing, and independently validating Jetson Video Codec SDK or PyNvVideoCodec encode/decode, transcode, segmentation, container decod

• jetson-video-recipe · Skill

  Use when turning a Jetson encoder use case into one surface-neutral recipe with native Video Codec SDK and PyNvVideoCodec projections.

• jetson-video-setup · Skill

  Use when installing, repairing, reusing, inspecting, or verifying readiness of the native NVIDIA Video Codec SDK or PyNvVideoCodec on Jetson, including the

• kermt-add-cmim-pretrain · Skill

  Convert a grover_base checkpoint (encoder-only or encoder + vocab heads) into a hybrid checkpoint by adding a randomly-initialized cMIM decoder + latent_di

• kermt-continue-pretrain · Skill

  Continue KERMT pretraining on a custom SMILES corpus with a grover_base, cmim, or hybrid checkpoint. Use a local checkpoint or optionally download a pinned

• kermt-embed · Skill

  Extract per-molecule embeddings from any encoder-bearing KERMT checkpoint. Use a local checkpoint or optionally download a pinned Hugging Face model bundle

• kermt-finetune · Skill

  Finetune a pretrained KERMT encoder on a labeled CSV. Validate the checkpoint and data, prepare features, and run containerized training. Use a local check

• kermt-infer · Skill

  Run predictions with a finetuned KERMT checkpoint on a SMILES-only CSV. The skill validates that the input ckpt has task FFN heads (refuses pretrain ckpts

• kermt-monitor · Skill

  Check progress for a detached KERMT run (pretrain, finetune, or any kermt_run_detached invocation). Reads run.json, queries docker for container state, tai

• kermt-pretrain-scratch · Skill

  Pretrain a fresh KERMT model from scratch on a user-provided corpus. Builds a new vocabulary from the corpus, instantiates the model architecture from defa

• kermt-setup · Skill

  Bootstrap the KERMT agent environment — verify host docker + nvidia-container-toolkit, build the kermt:latest image from the repo's Dockerfile if it doesn'

• medtech-model-evidence-export · Skill

  Exports sanitized metadata, parameters, reproducibility details, quality metrics, and optional review artifacts from Medical AI inference runs or evidence

• molmim-nim · Skill

  Use this skill for MolMIM, NVIDIA's BioNeMo NIM microservice for small-molecule latent-space generation and optimization. Invoke for MolMIM, molecular embe

• msa-search-nim · Skill

  Generate multiple sequence alignments (MSAs) for protein sequences using the ColabFold MSA-Search NIM. Use for homolog search, UniRef30/ColabFold env searc

• msa-structure-prediction-pipeline · Skill

  NOTE: your protein sequence and the retrieved MSA alignment are transmitted to external NVIDIA-hosted APIs (health.api.nvidia.com) on every call. Use local

• nemo-fabric-build-adapter · Skill

  Build, migrate, review, and maintain third-party NVIDIA NeMo Fabric adapters against the public adapter contract. Use when creating adapter or target descr

• nemo-fabric-integrate · Skill

  Use this skill when integrating NVIDIA NeMo Fabric into a consumer application, service, evaluation harness, or platform through the typed Python SDK — tra

• nemo-retriever-mcp · Skill

  Use when a task needs to search or add documents through NeMo Retriever MCP.

• nemotron-voice-agent-builder · Skill

  Create, refine, or fix NVIDIA voice agents (Cascaded or Omni) with Pipecat or LiveKit. Use when building, scaffolding, or iterating on a real-time voice-ag

• nv-reason-ct · Skill

  Run NV-Reason-CT inference on user-provided 3D NIfTI chest or abdominal CT volumes for engineering and research workflows. Not for diagnosis, treatment, or

• nvflare-autofl · Skill

  Use for agent-assisted Auto-FL optimization of an existing NVFLARE job in simulation, POC, or production. Do not use for code conversion, diagnosis-only wo

• nvflare-autofl-report · Skill

  Generate a reproducible final report, literature-outcome synthesis, JSON summary, and refreshed progress plot for a stopped or interrupted NVFLARE Auto-FL

• nvflare-convert-huggingface · Skill

  Convert existing Hugging Face Transformers Trainer or TRL SFTTrainer training code into an NVFLARE federated job using flare.patch(trainer), local validati

• nvflare-convert-lightning · Skill

  Convert existing PyTorch Lightning training code into an NVFLARE federated job using the Lightning Client API patch, local validation, and job export; use

• nvflare-convert-pytorch · Skill

  Convert existing plain or manual PyTorch training code into an NVFLARE federated job using Client API model exchange, local validation, and job export; use

• nvflare-diagnose-job · Skill

  Use when the user asks why a reported NVFLARE job failure signal occurred: the job failed, stalled, timed out, lost clients, ended with EXECUTION_EXCEPTION

• nvflare-fed-stats · Skill

  Compute federated statistics over tabular data (count, sum, mean, stddev, var, histogram, quantile, noise-protected min/max) and image data (count, failure

• nvflare-orient · Skill

  Route open-ended NVFLARE advice and only conversion requests whose preliminary source inspection reports unresolved or conflicting ownership; never load th

• nvflare-shared · Skill

  Internal NVFLARE conversion references and templates. Use only when another NVFLARE skill directs you to a shared workflow, policy, or asset.

• nvidia-app · Skill

  NVIDIA App MCP: drivers, games, laptops, overlay. Check drivers, manage and optimize games, configure laptop features.

• nvidia-broadcast · Skill

  Use when controlling NVIDIA Broadcast through MCP to apply effects, process local media, select devices, or change camera resolution, or when Broadcast is

• nvidia-ontology-management · Skill

  Model and publish semantic definitions in Auto Ontology. Use for terms, relationships, measures, imports, and governed results—not deployment or querying.

• nvidia-ontology-query · Skill

  Query Auto Ontology and validate generated SQL, rows, and answers. Use for MCP or REST access, readiness, authentication, conversations, and grounded quest

• nvidia-ontology-setup · Skill

  Set up or troubleshoot the Auto Ontology runtime. Use for Helm (the official install), Docker Compose, developer setup, and MCP connection to an existing d

• nvmolkit-usage · Skill

  Use when writing or debugging nvMolKit Python code for GPU-accelerated RDKit fingerprints, similarity, conformers, clustering, and molecular searches.

• nvshmem-collect-performance-data · Skill

  Collect and package NVSHMEM put/get bandwidth, latency, and other perftest results with system and topology evidence for performance sanity checks.

• nvshmem-configure-nic-pe-mapping · Skill

  Recommend NVSHMEM NIC-to-PE mappings and environment exports. Use for HCA selection, multi-NIC configuration, or topology-based mapping diagnostics.

• nvshmem-docs · Skill

  Find version-aware official NVSHMEM and NVSHMEM4Py documentation for releases, installation, APIs, runtime settings, transports, containers, and troublesho

• nvshmem-enable-tma · Skill

  Prepare or review NVSHMEM CUDA kernels for TMA SMEM registration and direct-SMEM transfers. Do not use for unrelated CUDA tuning.

• nvshmem-get-started · Skill

  Use when NVSHMEM beginners want a tutorial-style overview on assessment, mental models, first C/C++ or Python NVSHMEM programs, compilation, launching, and

• nvshmem-install · Skill

  Plan and validate NVSHMEM and NVSHMEM4Py installations. Use for package, container, or source deployments.

• nvshmem-select-remote-transport · Skill

  Select an NVSHMEM remote transport from target system and kernel evidence. Use for inter-node selection, compatibility checks, or configuration.

• nvshmem-troubleshoot-and-report-bugs · Skill

  Diagnose NVSHMEM runtime failures and prepare bug reports for launch, crashes, hangs, correctness, transport, or topology issues.

• nvshmem-tune-performance · Skill

  Route NVSHMEM tuning to data collection, remote transport, NIC-to-PE mapping, or TMA. Do not use for unrelated CUDA, NCCL, or application tuning.

• omniverse-content-services · Skill

  Omniverse Content Services, also discoverable as Omniverse Content Workspace or USD Content Workspace. Use for USD content collaboration as well as content

• openfold2-nim · Skill

  Use this skill for OpenFold2, NVIDIA's BioNeMo NIM microservice for monomer protein structure prediction. Invoke whenever the user mentions OpenFold2, Alph

• openfold3-nim · Skill

  Use this skill for OpenFold3, NVIDIA's BioNeMo NIM microservice for biomolecular structure prediction. Invoke whenever the user mentions OpenFold3 or needs

• paidf-cosmos-predict · Skill

  Prepare and run PAIDF Cosmos Predict video generation for DEFT media samples.

• parabricks · Skill

  Plan NVIDIA Parabricks pbrun commands, translate CPU options and check runtime readiness. Use for individual tools, including planning-only questions.

• physical-ai-physics-selection · Skill

  Choose a physics engine and integration for robot learning, manipulation, assembly, differentiable optimization, or other Physical AI simulation. Compare N

• proteinmpnn-nim · Skill

  Run ProteinMPNN inverse folding via NVIDIA NIM to design protein sequences for a target backbone. Sends user-provided PDB files and design parameters to NV

• pva-build-test · Skill

  Build and verify an NVIDIA PVA operator with the public PVA SDK. Use alone or from OpGen. Run optional EMU correctness, a fresh L4T build with the NVVPU or

• pva-debug · Skill

  Diagnose and narrowly repair one reproduced NVIDIA PVA operator failure. Use from OpGen or manually for compile, link, cuPVA lifecycle, dataflow, DMA, nume

• pva-doctor · Skill

  Check whether a host is ready for requested NVIDIA PVA work. Use before Spec, OpGen, Build-Test, or Debug. Verify references to the installed SDK documenta

• pva-opgen · Skill

  Generate, change, or repair a complete vectorized NVIDIA PVA operator from a validated pva-spec handoff. Deliver the contract's API, host and VPU code, ind

• pva-setup · Skill

  Install and configure the NVIDIA PVA SDK, NVVPU compiler, and L4T target runtime from the selected installation guide. Use when the user requests PVA envir

• pva-spec · Skill

  Create and validate an NVIDIA PVA operator specification, test matrix, evidence manifest, and deterministic OpGen handoff. Use after Doctor for new operato

• rfd4-proteina-nim · Skill

  Run RFD4-Proteina NIM for joint protein structure and sequence design, conditioned generation, and reward-guided search using the NVIDIA hosted API or a se

• rfdiffusion-nim · Skill

  Run RFDiffusion protein backbone design via NVIDIA NIM. Use for de novo protein backbones, motif scaffolding, binder design, hotspot residues, contigs synt

• rtvi-cv-customize-model · Skill

  How to swap the DeepStream CV detection model in the VSS Alerts Blueprint verification (2d_cv) mode - covers ONNX export, custom bbox parsers, compose moun

• rtvi-cv-scaffold-vss-service · Skill

  Scaffold a standalone RTVI CV microservice that plugs into VSS Search and Alerts profiles via Kafka mdx-raw. The shipped scaffold script is a YOLO26 refere

• rtvi-vlm-customize-model · Skill

  How to swap the VLM in the VSS Alerts Blueprint — covers RTVI-VLM microservice deployment methods, all three VLM consumers (rtvi-vlm, vlm-as-verifier, vss-

• rtx-remix-modding · Skill

  Mod or remaster a game with RTX Remix - open and edit projects, swap textures and models. Connect to the Remix Toolkit App via MCP. Not for non-Remix game

• runai-audit-assigned-quota · Skill

  Audit GPU quota fairness across a Run:ai cluster — find which projects are starved and which are borrowing over their deserved quota in each node pool, and

• runai-diagnose-failed-workload · Skill

  Use to diagnose failed, crashed, stopped, OOMKilled, CrashLoopBackOff, ImagePullBackOff, init, mount, node, or policy-terminated Run:ai workloads. Investig

• runai-get-cluster-health-summary · Skill

  Point-in-time Run:ai cluster and node-health check: a HEALTHY, DEGRADED, or STUCK verdict per node pool with the dominant blocker — NotReady nodes, offline

• runai-get-utilization-overview · Skill

  GPU efficiency check for a Run:ai cluster: are the GPUs that projects, departments, and node pools hold actually computing? Classifies holders as WELL_UTIL

• runai-get-workload-health-summary · Skill

  Summarizes scoped Run:ai workload health or one workload. Not for root cause, quota, cluster health, fleet utilization, history, or mutations.

• tao-analyze-detection-kpi · Skill

  Run TAO Data Services KPI analysis for object detection, comparing inference annotations against ground truth to compute per-class TP/FP/FN/TN, precision,

• tao-analyze-gaps-od-map · Skill

  Run TAO Data Services object-detection gap analysis from ground-truth and inference annotations. Use when an object detection workflow needs to identify we

• tao-artifacts · Skill

  The contract home for TAO's SDK-free execution pipeline — authoritative JSON Schemas for the four typed artifacts (spec-bundle, job-record, results_dir lay

• tao-data-io · Skill

  The data-mover for TAO jobs — decides the storage tier (A pre-positioned mount with zero fetch / B volume-from-S3 / C ephemeral in-compute fetch), stages i

• tao-finetune-anomalygennext · Skill

  Validate a user AnomalyGenNext dataset and recipe, freeze its validation set, and prepare a canonical texture fine-tuning recipe. Use when AnomalyGenNext t

• tao-finetune-kumo-anomaly · Skill

  Kumo-Anomaly — diffusion-based anomaly detection and fine-tuning for multivariate time series. Use when the user asks to "fine-tune Kumo-Anomaly", "run Kum

• tao-finetune-kumo-forecast · Skill

  Kumo-Forecast — transformer-based multivariate time series forecasting with DARR (context-enhanced kNN retrieval), interpretability, and fine-tuning. Use w

• tao-finetune-video-clip · Skill

  InternVideo2-CLIP L14 (TAO video_clip) for video-text retrieval, zero-shot classification, embedding extraction, LoRA fine-tuning, ONNX export, and TensorR

• tao-generate-anomalies · Skill

  Full PAIDF AnomalyGen pipeline — fine-tune on a new anomaly dataset, generate synthetic anomaly images (SDG), evaluate quality (nn_score), and search per-s

• tao-generate-image-embeddings · Skill

  Run TAO Data Services image embedding to turn a parquet of image filepaths into an embedding parquet using CLIP, SigLIP, or a TAO checkpoint. Use when a wo

• tao-generate-od-defects · Skill

  Run AnomalyGenNext 1.1 inference from a native testcase or a prepared generation plan, then publish validated fine-grained and binary COCO labels. Use for

• tao-mine-nearest-neighbors · Skill

  Run TAO Data Services TMM nearest-neighbor mining from embedding parquet files. Use when a workflow needs to mine source samples closest to target samples.

• tao-mine-od-images · Skill

  Run TAO Data Services TMM unique-neighbor matching mining from embedding parquet files for object detection workflows. Use when an object detection workflo

• tao-prepare-anomalygennext-inputs · Skill

  Prepare normalized object-detection false negatives, source masks, and clean-image embedding inputs for AnomalyGenNext. Use when turning box-level FN gaps

• tao-run-deft-aoi-cosmos3 · Skill

  Run the disk-backed DEFT AOI improvement loop for NVIDIA Cosmos Reason 3 / Cosmos3 models, using Nano by default and Edge or Super when explicitly requeste

• tao-run-deft-cr-its-mining · Skill

  Run the mining-based DEFT improvement workflow for ITS Cosmos-Reason binary video questions, focused on the non-reasoning classification/evaluation path. U

• tao-run-deft-object-detection · Skill

  Run the full DEFT smart-data-augmentation loop for NVIDIA TAO Grounding DINO object detection: zero-shot baseline inference, KPI analysis, per-class gap an

• tao-run-deft-od-aoi · Skill

  Run a binary industrial-inspection DEFT loop with TAO RT-DETR: measure on frozen KPI/test roles, mine gap-similar real and clean images with SigLIP, accumu

• tao-run-deft-pas · Skill

  Run iterative improvement for NVIDIA TAO CLIP / SigLIP image-text retrieval on attribute-labelled data. Use when a request combines retrieval evaluation, w

• tao-run-dinov3-ssl-deft · Skill

  Run iterative DINOv3 SSL DEFT data selection and retraining from an unlabeled pool, using GRIT or multi-task weakness and fixed-encoder retrieval. Use for

• tao-run-on-virtualenv · Skill

  Run a Python training/eval script directly in an existing local virtualenv — no docker, no container. Implements the four-verb consumer contract (submit/st

• tao-setup · Skill

  One-time session setup and orchestration map for the TAO skill bank. Run this first when the TAO skills were installed individually (e.g. from a public ski

• tao-token-efficient-execution · Skill

  Token-efficient execution kit for repeated TAO agentic workflows. Compiles a skill into stage cards once (with a strong model), then executes them forever

• tao-train-codetr · Skill

  Co-DETR (CoDINO) for object detection. A DETR-family detector with collaborative hybrid

• tao-train-dinov3 · Skill

  DINOv3 continual self-supervised pre-training. Domain-adapts public DINOv3 ViT backbones

• tao-validate-recipe-transfer · Skill

  Port a published computer vision paper's official code and training recipe onto a customer's own dataset, or diagnose why such a transfer produced bad numb

• using-ovnewton · Skill

  Connect the Newton physics engine to an Omniverse simulation or ovstage with ovnewton. Use when importing a populated ovstage into Newton, stepping its phy

• vss-build-vision-ai · Skill

  Add agent-ready vision capabilities — dense captioning, detection, search, alerting, summarization — to an agent or application through a customizable, sel

• warp-compile-time-optimizer · Skill

  Use when compile time or startup time is the problem in code that uses Warp: a request to improve, optimize, or cut compile times; an app that is slow to s

• warp-debug-gradients · Skill

  Use to diagnose and fix incorrect gradients in differentiable Warp programs. Anything trained, optimized, calibrated, or fit through Warp kernels depends o

• warp-eval · Skill

  Evaluate whether an existing hot path is a credible NVIDIA Warp candidate. Use for irregular or spatial queries, particle or geometry simulation, branch-he

Browse the @skills marketplace