nvidia/skills

nvidia/skills · plugins/nvidia-skills/skills/nvidia-skill-finder/SKILL.md · Use for NVIDIA-related requests where an NVIDIA skill might help, even if the user did not ask for a skill. Trigger on…

nvidia/skills · skills/accelerated-computing-cudf/SKILL.md · Official NVIDIA-authored guidance for NVIDIA cuDF GPU DataFrames, pandas acceleration, dask-cuDF, ETL, joins, groupby…

nvidia/skills · skills/aiq-deploy/SKILL.md · Use when asked to install, deploy, run, validate, troubleshoot, or stop NVIDIA AI-Q Blueprint infrastructure.

nvidia/skills · skills/aiq-research/SKILL.md · Use when asked to run deep research or AI-Q research through a reachable NVIDIA AI-Q Blueprint backend.

nvidia/skills · skills/amc-run-rtsp-calibration/SKILL.md · Calibrate a new dataset from live RTSP camera streams via the AutoMagicCalib REST API. Use when the user provides RTSP…

nvidia/skills · skills/amc-run-sample-calibration/SKILL.md · Run end-to-end calibration on the shipped sample dataset (sdg_08_2_sample_data_010926.zip) against a running AMC…

nvidia/skills · skills/amc-run-video-calibration/SKILL.md · Calibrates pre-recorded `cam_*.mp4` datasets through the AutoMagicCalib REST API. Use for user-supplied local MP4s…

nvidia/skills · skills/amc-setup-calibration-stack/SKILL.md · Launch AutoMagicCalib microservice and web UI from NGC release images via Docker Compose. Use when user says 'deploy…

nvidia/skills · skills/bionemo-kermt-add-cmim-pretrain/SKILL.md · Convert a grover_base checkpoint (encoder-only or encoder + vocab heads) into a hybrid checkpoint by adding a…

nvidia/skills · skills/bionemo-kermt-continue-pretrain/SKILL.md · Continue KERMT pretraining on a custom SMILES corpus with a grover_base, cmim, or hybrid checkpoint. Use a local…

nvidia/skills · skills/bionemo-kermt-embed/SKILL.md · Extract per-molecule embeddings from any encoder-bearing KERMT checkpoint. Use a local checkpoint or optionally…

nvidia/skills · skills/bionemo-kermt-finetune/SKILL.md · Finetune a pretrained KERMT encoder on a labeled CSV. Validate the checkpoint and data, prepare features, and run…

nvidia/skills · skills/bionemo-kermt-infer/SKILL.md · Run predictions with a finetuned KERMT checkpoint on a SMILES-only CSV. The skill validates that the input ckpt has…

nvidia/skills · skills/bionemo-kermt-monitor/SKILL.md · Check progress for a detached KERMT run (pretrain, finetune, or any kermt_run_detached invocation). Reads run.json…

nvidia/skills · skills/bionemo-kermt-pretrain-scratch/SKILL.md · Pretrain a fresh KERMT model from scratch on a user-provided corpus. Builds a new vocabulary from the corpus…

nvidia/skills · skills/bionemo-kermt-setup/SKILL.md · Bootstrap the KERMT agent environment — verify host docker + nvidia-container-toolkit, build the kermt:latest image…

nvidia/skills · skills/cudaq-guide/SKILL.md · Use for CUDA-Q setup, simulation targets, QPU access, and @cudaq.kernel authoring guidance.

nvidia/skills · skills/cudaq-importing/SKILL.md · Use when porting circuits from another framework (e.g. Qiskit) into CUDA-Q kernels while preserving the source…

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

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

nvidia/skills · skills/cuopt-multi-objective-exploration/SKILL.md · Trace, complete, and interpret the Pareto frontier across competing objectives using repeated single-objective cuOpt…

nvidia/skills · skills/cuopt-numerical-optimization-api/SKILL.md · LP, MILP, and QP (beta) with cuOpt — Python, C, and CLI. Use when the user is solving LP, MILP, or QP with any cuOpt…

nvidia/skills · skills/cuopt-numerical-optimization-formulation/SKILL.md · LP, MILP, QP — concepts, problem-text parsing, and formulation patterns (parameters, constraints, decisions…

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

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

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

nvidia/skills · skills/cupynumeric-install/SKILL.md · Install and verify cuPyNumeric for Python — requirements, commands, verification. Source builds are out of scope.

nvidia/skills · skills/cupynumeric-migration-readiness/SKILL.md · Pre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the…

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

nvidia/skills · skills/dali-dynamic-mode/SKILL.md · DALI imperative dynamic mode (`nvidia.dali.experimental.dynamic`, ndd): use when working on ndd code or migrating…

nvidia/skills · skills/data-designer/SKILL.md · Use when the user wants to create a dataset, generate synthetic data, or build a data generation pipeline.

nvidia/skills · skills/deepstream-dev/SKILL.md · NVIDIA DeepStream SDK development with Python pyservicemaker API. Use when building video analytics pipelines…

nvidia/skills · skills/deepstream-generate-pipeline/SKILL.md · Build DeepStream GStreamer pipelines interactively. Use when the user asks about pipelines for video/image inference…

nvidia/skills · skills/deepstream-import-vision-model/SKILL.md · Use this skill to bring a supported object-detection vision model from HuggingFace or NVIDIA NGC into an NVIDIA…

nvidia/skills · skills/deepstream-profile-pipeline/SKILL.md · Profile a DeepStream pipeline with Nsight Systems and derive its configs from the measurement. Use when the user asks…

nvidia/skills · skills/deepstream-run-mv3dt/SKILL.md · Run and operate the DeepStream Multi-View 3D Tracking reference app, also known as MV3DT. Use when the user asks to set…

nvidia/skills · skills/deepstream-sop/SKILL.md · Use this skill when building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP Inference…

nvidia/skills · skills/dicom-metadata-extract/AGENTS.md

nvidia/skills · skills/dicom-metadata-extract/SKILL.md · Used for extracting selected metadata from one DICOM file and flagging standard-tag PHI presence. Not for anonymization…

nvidia/skills · skills/dicom-series-preflight/SKILL.md · Used for header-only preflight of one DICOM series folder before conversion or inference. Not for de-identification or…

nvidia/skills · skills/dicom-series-to-volume/SKILL.md · Used for converting one CT DICOM series folder to a HU NIfTI volume with affine evidence. Not for multi-frame DICOM or…

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

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

nvidia/skills · skills/digital-health-clinical-asr-finetune/SKILL.md · 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…

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

nvidia/skills · skills/doca-aes-gcm/SKILL.md · Use this skill when the user is doing hands-on DOCA AES-GCM work on a BlueField DPU or ConnectX NIC — configuring…

nvidia/skills · skills/doca-argp/SKILL.md · Use this skill for hands-on DOCA Arg Parser CLI work on a shipped sample or new DOCA-using app — adding / removing /…

nvidia/skills · skills/doca-argus/SKILL.md · Use this skill when the user is deploying or operating the DOCA Argus Service — the packaged BlueField-side…

nvidia/skills · skills/doca-bare-metal-deployment/SKILL.md · Use this skill for launching, supervising, debugging, OR platform lifecycle on a BlueField — BFB install, RShim/TMFIFO…

nvidia/skills · skills/doca-bench-extension/SKILL.md · Use this skill when the operator is authoring, building, loading, or debugging a custom doca-bench plug-in — a…

nvidia/skills · skills/doca-bench/SKILL.md · Run `doca_bench` (DOCA 2.7.0 or newer) to measure throughput, bulk latency, precision latency, or maximum bandwidth for…

nvidia/skills · skills/doca-bf3-deployment/SKILL.md · Use this skill for BlueField-3 (BF3) day-1 platform bring-up via the classic RShim/BFB path: pushing a BlueField bundle…

nvidia/skills · skills/doca-bf4-deployment/SKILL.md · WARNING: guides potentially IRREVERSIBLE BlueField-4 hardware operations (PLDM firmware burns, ISO reflashes, power…

nvidia/skills · skills/doca-caps/SKILL.md · Use this skill when the user wants to invoke the read-only doca_caps CLI to ask what DOCA sees on this host — listing…

nvidia/skills · skills/doca-collectx-deployment/SKILL.md · Use this skill to deploy and operate a CollectX (clx) based DOCA telemetry collector on a host or BlueField — wiring…

nvidia/skills · skills/doca-comch/SKILL.md · Use this skill when the user is doing hands-on DOCA Comch work on a host + BlueField pair — bringing up host ↔ DPU PCIe…

nvidia/skills · skills/doca-comm-channel-admin/SKILL.md · Use this skill to enumerate host↔DPU DOCA comch (formerly Comm Channel) servers and connections via the shipped…

nvidia/skills · skills/doca-common/SKILL.md · Use this skill whenever the user is doing hands-on DOCA programming on a BlueField DPU or ConnectX NIC and needs the…

nvidia/skills · skills/doca-compress/SKILL.md · Use this skill for hands-on DOCA Compress programming on a BlueField DPU, ConnectX NIC, or host with DOCA — enabling…

nvidia/skills · skills/doca-container-deployment/SKILL.md · Use this skill when the user is hands-on deploying an in-bundle DOCA service container (Argus, DMS, Firefly, or UROM…

nvidia/skills · skills/doca-debug/SKILL.md · Use this skill when the user is debugging any DOCA symptom — a build that won't compile, a link step that can't resolve…

nvidia/skills · skills/doca-devemu/SKILL.md · Use this skill when the user is doing hands-on DOCA Device Emulation on a BlueField DPU — exposing a custom emulated…

nvidia/skills · skills/doca-dma/SKILL.md · Use this skill when the user is doing hands-on DOCA DMA programming — bringing up a doca_dma context, configuring the…

nvidia/skills · skills/doca-dms/SKILL.md · Operate NVIDIA DOCA Management Service (`dmsd` + `dmspe`) on a BlueField, Arm/x86 host, or Kubernetes pod: choose…

nvidia/skills · skills/doca-dpa-hl-tracer/SKILL.md · Use this skill when the user runs doca_dpa_hl_tracer to capture/decode DPA-side traces at the programming-events layer…

nvidia/skills · skills/doca-dpa/SKILL.md · Use this skill when the user is doing hands-on DOCA DPA host-side work on a BlueField — creating the `doca_dpa` Core…

nvidia/skills · skills/doca-dpdk-bridge/SKILL.md · Use this skill when the user has an existing DPDK application and is adding DOCA capabilities in-place — most commonly…

nvidia/skills · skills/doca-erasure-coding/SKILL.md · Use this skill when the user is doing hands-on DOCA Erasure Coding programming on a BlueField DPU, ConnectX NIC, or…

nvidia/skills · skills/doca-eth/SKILL.md · Use this skill for hands-on DOCA Ethernet packet-queue work on a BlueField DPU or ConnectX NIC — bringing up a…

nvidia/skills · skills/doca-firefly/SKILL.md · Use this skill when the user is operating the DOCA Firefly Service container on BlueField — picking the four PTP…

nvidia/skills · skills/doca-flow-dpa-perf/SKILL.md · Use this skill when the user is invoking doca_flow_dpa_perf on DPA-capable hardware (ConnectX-7 minimum supported…

nvidia/skills · skills/doca-flow-dpa-provider/SKILL.md · Use this skill when the user is doing hands-on DOCA Flow DPA Provider work — exporting a `doca-flow` pipe or external…

nvidia/skills · skills/doca-flow-grpc-server/SKILL.md · PLAINTEXT-ONLY: the shipped `doca_flow_grpc` server uses `grpc::InsecureServerCredentials()` with NO TLS / mTLS /…

nvidia/skills · skills/doca-flow-perf/SKILL.md · Use this skill when the user is measuring the host or DPU-CPU control-plane rate of a DOCA Flow pipeline with…

nvidia/skills · skills/doca-flow-tune/SKILL.md · Use this skill when the user is tuning a live or captured `doca-flow` pipeline with `doca_flow_tune` — snapshotting…

nvidia/skills · skills/doca-flow/SKILL.md · Build and debug DOCA Flow applications on supported NVIDIA NICs/DPUs: define match/action pipes, initialize ports and…

nvidia/skills · skills/doca-gpi/SKILL.md · Use this skill for hands-on DOCA GPI programming — wiring a GPU-Packet-Initiator context so a CUDA kernel drives RDMA…

nvidia/skills · skills/doca-gpunetio-ib-write-bw/SKILL.md · Use this skill when the user is building, running, or interpreting the doca/tools/gpunetio_ib_write_bw client+server…

nvidia/skills · skills/doca-gpunetio-ib-write-lat/SKILL.md · Use this skill when the user is measuring GPU-kernel-initiated RDMA WRITE latency through doca-gpunetio — building and…

nvidia/skills · skills/doca-gpunetio/SKILL.md · Use this skill when the user is doing hands-on DOCA GPUNetIO programming — wiring a CUDA kernel on an NVIDIA GPU to a…

nvidia/skills · skills/doca-hardware-safety/SKILL.md · Use this skill whenever the agent is about to recommend or apply a change that touches DPU / NIC hardware state on a…

nvidia/skills · skills/doca-mgmt/SKILL.md · Use this skill when the user is doing hands-on DOCA Management programming against BlueField / ConnectX devices —…

nvidia/skills · skills/doca-pcc-counters/SKILL.md · Use this skill when the user is invoking the DOCA PCC Counters tool — the `pcc_counters.sh` bash script under the DOCA…

nvidia/skills · skills/doca-pcc-ztr-rttcc-algo/SKILL.md · Use this skill when the user is doing hands-on deployment, tuning, or evaluation of the DOCA-shipped Zero-Touch RoCE…

nvidia/skills · skills/doca-pcc/SKILL.md · Use this skill when the user is doing hands-on host-side DOCA PCC work to load a CUSTOM Programmable Congestion Control…

nvidia/skills · skills/doca-programming-guide/SKILL.md · Use this skill when the user is writing their first DOCA app or asking a library-agnostic programming question —…

nvidia/skills · skills/doca-public-knowledge-map/SKILL.md · Use this skill when the user needs to locate authoritative information about NVIDIA DOCA without access to the source…

nvidia/skills · skills/doca-rdma/SKILL.md · Use this skill when the user is doing hands-on DOCA RDMA programming on a BlueField DPU, ConnectX NIC, or DOCA host —…

nvidia/skills · skills/doca-rdmi/SKILL.md · Use this skill when the user is doing hands-on DOCA RDMI (RDMA Initiator) programming — picking doca-rdmi vs doca-rdma…

nvidia/skills · skills/doca-rmax/SKILL.md · Use this skill when the user is doing hands-on DOCA Rivermax work on a BlueField DPU or ConnectX host — standing up…

nvidia/skills · skills/doca-setup/SKILL.md · Use this skill when the user is dealing with the DOCA environment around their workload — verifying an install is…

nvidia/skills · skills/doca-sha-offload-engine/SKILL.md · Use this skill when wiring the DOCA SHA Offload Engine (an OpenSSL ENGINE) into an existing OpenSSL pipeline to offload…

nvidia/skills · skills/doca-sha/SKILL.md · Use this skill when the user is doing hands-on DOCA SHA programming — offloading SHA-1, SHA-256, or SHA-512 hashing…

nvidia/skills · skills/doca-socket-relay/SKILL.md · Use this skill when the operator is driving the DOCA Socket Relay to bridge a socket-oriented host application onto a…

nvidia/skills · skills/doca-spcx-cc/SKILL.md · Use this skill when the user is invoking `doca_spcx_cc` (the host-side CLI under /opt/mellanox/doca/tools/) to load…

nvidia/skills · skills/doca-sta/SKILL.md · Use this skill when the user is doing hands-on NVMe-over-Fabrics storage-target work on a BlueField DPU or ConnectX NIC…

nvidia/skills · skills/doca-structured-tools-contract/SKILL.md · Use this skill whenever another DOCA skill says "prefer the structured tool per doca-structured-tools-contract", or…

nvidia/skills · skills/doca-telemetry-exporter/SKILL.md · Use this skill when the user is doing hands-on DOCA Telemetry Exporter programming on a host where DOCA is installed —…

nvidia/skills · skills/doca-telemetry-utils/SKILL.md · Use this skill when the user is invoking `doca_telemetry_utils` on a host with DOCA installed — discovering the…

nvidia/skills · skills/doca-telemetry/SKILL.md · Use this skill to read DOCA hardware-counter events from a `doca_dev` through the per-domain Telemetry reader…

nvidia/skills · skills/doca-upgrade/SKILL.md · Use this skill when the user is contemplating a DOCA upgrade or downgrade — moving a host to a newer DOCA release…

nvidia/skills · skills/doca-urom-svc/SKILL.md · Operate the DOCA UROM Service container on BlueField Arm for remote memory operations (puts, gets, atomics…

nvidia/skills · skills/doca-urom/SKILL.md · Use this skill when the user is doing hands-on DOCA UROM library work from the host side — wiring doca-urom under an…

nvidia/skills · skills/doca-verbs/SKILL.md · Use this skill when the user is dropping below the higher-level DOCA libraries (doca-rdma / doca-eth / doca-rmax) into…

nvidia/skills · skills/doca-version/SKILL.md · Use this skill when the user is doing DOCA version handling — detecting the installed release, validating the four-way…

nvidia/skills · skills/dynamo-interconnect-check/SKILL.md · Validate that a Dynamo deployment's NIXL/UCX/NCCL interconnect is ready for disaggregated serving over RDMA/NVLink. Use…

nvidia/skills · skills/dynamo-recipe-runner/SKILL.md · Select, validate, patch, and deploy existing NVIDIA Dynamo Kubernetes recipes. Use for…

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

nvidia/skills · skills/dynamo-troubleshoot/SKILL.md · Diagnose failed or unhealthy Dynamo deployments. Use when pods, model-cache jobs, PVCs, workers, frontend/router…

nvidia/skills · skills/earth2studio-create-datasource/SKILL.md · Create and validate Earth2Studio data source wrappers (DataSource, ForecastSource, DataFrameSource…

nvidia/skills · skills/earth2studio-create-diagnostic/SKILL.md · Create Earth2Studio diagnostic model wrappers for single-step data transformations, including simple derived…

nvidia/skills · skills/earth2studio-create-prognostic/SKILL.md · Create Earth2Studio prognostic (time-stepping forecast) model wrappers. Do NOT use for diagnostic models, data sources…

nvidia/skills · skills/earth2studio-data-fetch/SKILL.md · Fetch weather/climate data via Earth2Studio data sources for specific variables and times. Do NOT use for inference…

nvidia/skills · skills/earth2studio-deterministic-forecast/SKILL.md · Build deterministic forecast scripts with Earth2Studio (model, data source, IO, inference). Do NOT use for ensemble…

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

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

nvidia/skills · skills/foundationpose-pipeline/SKILL.md · Adapt BOP datasets, run the FoundationPose perception pipeline with TAO depth, and evaluate or re-score pose results…

nvidia/skills · skills/foundationpose-setup/SKILL.md · Install or repair the FoundationPose perception pipeline and build its FoundationStereo TensorRT engines. Use for…

nvidia/skills · skills/holohub-app-lifecycle/SKILL.md · Use for non-failing HoloHub app work with ./holohub: scaffold, build, run, test, visual evidence, lint, and flow…

nvidia/skills · skills/holohub-debug-build-run/SKILL.md · Use when a concrete ./holohub command fails, hangs, regresses, or returns wrong output and needs reproducible diagnosis…

nvidia/skills · skills/holohub-module-lifecycle/SKILL.md · Use for reusable Holoscan Module work with ./holohub: scaffold, tests, editable install, DEB/WHEEL packaging, and…

nvidia/skills · skills/holoscan-install-conda/SKILL.md · Install Holoscan SDK v4.3+ via Conda in a CUDA 13 environment. Use for Conda installs; redirect CUDA 12 hosts to…

nvidia/skills · skills/holoscan-install-container/SKILL.md · Install Holoscan SDK via the NGC Docker container. Use for container-based installs; not for native apt/pip/Conda…

nvidia/skills · skills/holoscan-install-debian/SKILL.md · Install Holoscan SDK natively on Ubuntu via apt. Use for C++ installs on Ubuntu; pair with /holoscan-install-wheel for…

nvidia/skills · skills/holoscan-install-source/SKILL.md · Build Holoscan SDK from source via the in-tree ./run script. Use only when published packages don't meet the user's…

nvidia/skills · skills/holoscan-install-wheel/SKILL.md · Install Holoscan SDK Python wheel via pip into a venv. Use for Python installs; not for native C++/apt or Conda…

nvidia/skills · skills/holoscan-setup/SKILL.md · Guides Holoscan SDK installation: inspects the host, assesses platform compatibility, recommends an install method, and…

nvidia/skills · skills/hsb-app/SKILL.md · Discover and run Holoscan Sensor Bridge example applications on a connected devkit. Filters available apps by the…

nvidia/skills · skills/hsb-flash/SKILL.md · Flash the FPGA on an HSB board connected to an NVIDIA devkit. Supports HSB Lattice boards (FPGA versions 2407, 2412…

nvidia/skills · skills/hsb-ip-create-top/SKILL.md · Create or explain fixed-format HSB FPGA_top.sv wrappers from validated HOLOLINK_def.svh files. Do not use for def…

nvidia/skills · skills/hsb-ip-def/SKILL.md · Generate, validate, compare, or explain HSB HOLOLINK_def.svh macros. Do not use for FPGA_top.sv wrappers or…

nvidia/skills · skills/hsb-ip-packetizer/SKILL.md · Choose or explain HSB Sensor RX packetizer fields for HOLOLINK_def.svh. Do not use for full defs, validation, or…

nvidia/skills · skills/hsb-setup/SKILL.md · Clone the latest NVIDIA Holoscan Sensor Bridge repo, ask which supported devkit is being used, configure the host per…

nvidia/skills · skills/hsb-test/SKILL.md · Execute QA test plans on Holoscan Sensor Bridge hardware. Reads a user-provided test document, filters tests by the…

nvidia/skills · skills/i4h-lerobot-viz/SKILL.md · Serve and visually inspect a converted LeRobot dataset in the browser. Use for videos and state/action timelines; do…

nvidia/skills · skills/i4h-workflow-create/SKILL.md · Create a minimal blank Workflow scaffold with a Scene containing ground and light plus an idle run mode. Use for fast…

nvidia/skills · skills/i4h-workflow-dataset-annotate/SKILL.md · Grade or filter workflow HDF5 episodes with an OpenAI-compatible vision model. Use for visual success labels; do not…

nvidia/skills · skills/i4h-workflow-dataset-convert/SKILL.md · Convert workflow HDF5 recordings to LeRobot datasets for training or browser inspection. Use for conversion; do not use…

nvidia/skills · skills/i4h-workflow-dataset-mimic/SKILL.md · Expand workflow HDF5 demonstrations with action jitter, optionally scoped to node segments. Use for synthetic variants…

nvidia/skills · skills/i4h-workflow-dataset-replay/SKILL.md · Replay a workflow HDF5 episode through its original Scene. Use for visual trajectory and recording verification; do not…

nvidia/skills · skills/i4h-workflow-dataset-teleop/SKILL.md · Record demonstrations through a workflow's teleop Task into workflow HDF5. Use for keyboard, leader, VR, or bus input…

nvidia/skills · skills/i4h-workflow-e2e/SKILL.md · Run the maintained workflow data-to-policy pipeline from recording through checkpoint validation. Use for full…

nvidia/skills · skills/i4h-workflow-finetune/SKILL.md · Fine-tune a manifest-backed GR00T or openpi remote Task on compatible LeRobot data. Use for training; do not use for…

nvidia/skills · skills/i4h-workflow-scene-edit/SKILL.md · Edit an existing workflow Scene or task contract. Use for assets, layout, cameras, randomization, task text, or success…

nvidia/skills · skills/i4h-workflow-setup/SKILL.md · Preflight and set up the root-level workflow runtime. Use for installation, missing component environments, or…

nvidia/skills · skills/i4h-workflow-train-rl/SKILL.md · Use when training, evaluating, or exporting Workflow policies with online RSL-RL or RLinf, including RL checkpoint and…

nvidia/skills · skills/i4h-workflow-validate/SKILL.md · Run the root-level workflow runtime policy or rule-based rollouts and verify simulator success. Use for evaluation…

nvidia/skills · skills/i4h-workflow/SKILL.md · Orient users to the i4h workflow runtime and route them to the correct stage skill. Use for architecture, support, or…

nvidia/skills · skills/isaac-mission-control-showcase/SKILL.md · Run and validate an end-to-end Mission Control showcase with a locally installed Isaac Sim launched in its GUI window…

nvidia/skills · skills/jetson-build-source/SKILL.md · Use when you need to rebuild the BSP overlay — DT, OOT modules, or kernel — from changes under bsp_sources/. Triggers…

nvidia/skills · skills/jetson-customize-camera/SKILL.md · Enable MIPI/GMSL camera sensors on a Jetson Thor or Orin custom carrier by rendering a kernel-DT overlay from the…

nvidia/skills · skills/jetson-customize-clocks/SKILL.md · Use to lock/cap Jetson CPU/GPU/EMC clocks, toggle EMC/CPU DVFS, or change cpufreq governors by editing BPMP DTB and…

nvidia/skills · skills/jetson-customize-fan/SKILL.md · Use when you need to add, remove, edit, list, or change the boot default of an nvfancontrol fan profile on a…

nvidia/skills · skills/jetson-customize-mgbe/SKILL.md · Enable Jetson Thor 25G/10G/1G MGBE QSFP via kernel-DT overlay. Do NOT use for UPHY lane allocation or ODMDATA edits.

nvidia/skills · skills/jetson-customize-nvpmodel/SKILL.md · Use when you need to add, remove, edit, list, or change the boot default of an nvpmodel power mode on a Jetson/Tegra…

nvidia/skills · skills/jetson-customize-pcie/SKILL.md · Per-controller PCIe enable / disable / lanes / link-speed for a Jetson Thor or Orin custom carrier via ODMDATA +…

nvidia/skills · skills/jetson-customize-pinmux/SKILL.md · Per-pin SFIO / direction / initial-state configurator for a Jetson Orin or Thor custom carrier from the pinmux XLSM. Do…

nvidia/skills · skills/jetson-customize-uphy/SKILL.md · Configure Jetson UPHY lane allocation (uphy0/uphy1-config) on Orin/Thor custom carriers. Do NOT use for pinmux or…

nvidia/skills · skills/jetson-customize-usb/SKILL.md · Enable/disable Jetson USB2/USB3 SS ports via kernel-DT overlay. Do NOT use for UPHY lane allocation or ODMDATA edits.

nvidia/skills · skills/jetson-derive-carrier/SKILL.md · Bootstrap a custom carrier board by forking carrier files and scaffolding a DT overlay from the reference devkit. Use…

nvidia/skills · skills/jetson-diagnostic/SKILL.md · Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.

nvidia/skills · skills/jetson-download-bsp/SKILL.md · Download NVIDIA Jetson Linux BSP artifacts (BSP tarball, sample rootfs, public_sources, x-tools, guides) for the active…

nvidia/skills · skills/jetson-flash-image/SKILL.md · 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…

nvidia/skills · skills/jetson-generate-kb/SKILL.md · Build a per-target knowledge-base markdown next to the active profile by walking the BSP root and source tree. Use…

nvidia/skills · skills/jetson-headless-mode/SKILL.md · Plan and apply safe Jetson headless-mode changes to reclaim GUI and daemon memory.

nvidia/skills · skills/jetson-inference-mem-tune/SKILL.md · Pick the serving stack and per-runtime memory flags (vLLM, SGLang, llama.cpp, TensorRT Edge-LLM) for an LLM/VLM…

nvidia/skills · skills/jetson-init-image/SKILL.md · Extract Jetson Linux + sample-rootfs tarballs and run apply_binaries.sh for the active target, then record bsp_image in…

nvidia/skills · skills/jetson-init-source/SKILL.md · Set up the BSP source workspace: Linux_for_Tegra overlay tracker, bsp_sources, Crosstool-NG toolchain. Use after…

nvidia/skills · skills/jetson-init-target/SKILL.md · Author a new Jetson target-platform profile (reference_devkit + optional custom_carrier) and update the active pointer…

nvidia/skills · skills/jetson-link-docs/SKILL.md · Bind pre-downloaded Jetson reference docs (developer guide, design guide, pinmux, schematics) into the active profile…

nvidia/skills · skills/jetson-llm-benchmark/SKILL.md · Benchmark Jetson LLM/VLM serving performance across vLLM, llama.cpp, and Ollama with structured JSON output.

nvidia/skills · skills/jetson-llm-serve/SKILL.md · Stand up vLLM or SGLang serving on Jetson, using upstream vLLM on Thor and Orin JetPack 7.2+, and NVIDIA-AI-IOT vLLM on…

nvidia/skills · skills/jetson-memory-audit/SKILL.md · Measure Jetson DRAM/NvMap usage and verify before/after memory reclamation with live audit data.

nvidia/skills · skills/jetson-memory-audit/references/DESIGN.md

nvidia/skills · skills/jetson-optimize-memory/SKILL.md · Reclaim DRAM by disabling unused subsystems across MB1 BCT, MB2 BCT, kernel reserved-memory, and SWIOTLB. Use for…

nvidia/skills · skills/jetson-package/SKILL.md · Pick Jetson-compatible containers, vLLM runtime images, and Jetson AI Lab PyPI indexes; maps Orin SM 8.7 vs Thor SM…

nvidia/skills · skills/jetson-print-bsp-info/SKILL.md · Use when you need to print Jetson BSP info (L4T version, board configs, rootfs state) from a Linux_for_Tegra root on…

nvidia/skills · skills/jetson-print-device-info/SKILL.md · Use when you need to print Jetson device info (module model, L4T version, kernel, OS version, current power mode) from…

nvidia/skills · skills/jetson-promote-image/SKILL.md · Use to promote overlay files and built artifacts into the staged BSP image. Do NOT use to flash or build. Triggers…

nvidia/skills · skills/jetson-quick-start/SKILL.md · Entry skill for Jetson / IGX BSP customization. Asks one core click-to-select setup questionnaire and passes prefilled…

nvidia/skills · skills/jetson-set-target/SKILL.md · Switch the active Jetson target-platform pointer to an existing profile YAML. Use before customize/build/flash to…

nvidia/skills · skills/jetson-speculative-decoding/SKILL.md · Add EAGLE-3 or draft-model speculative decoding to a Jetson vLLM server when TPOT is the bottleneck.

nvidia/skills · skills/jetson-validate-image/SKILL.md · Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not…

nvidia/skills · skills/jetson-video-benchmark/SKILL.md · Use when measuring Jetson Video Codec SDK or PyNvVideoCodec encode/decode throughput, comparing presets or surfaces…

nvidia/skills · skills/jetson-video-capability/SKILL.md · Use when Jetson codec, profile, chroma, bit-depth, dimension, engine-count, or operational support must be reconciled…

nvidia/skills · skills/jetson-video-pipeline/SKILL.md · Use when executing and verifying Jetson Video Codec SDK or PyNvVideoCodec encode/decode, transcode, segmentation…

nvidia/skills · skills/jetson-video-recipe/SKILL.md · Use when turning a Jetson encoder use case into one validated surface-neutral recipe with native and PyNvVideoCodec…

nvidia/skills · skills/jetson-video-setup/SKILL.md · Use when installing, repairing, probing, or verifying native NVIDIA Video Codec SDK or PyNvVideoCodec on Jetson with…

nvidia/skills · skills/launch-nemo-rl/SKILL.md · Playbook for launching, monitoring, stopping, and debugging NeMo-RL recipes on a Kubernetes cluster via the nrl-k8s…

nvidia/skills · skills/mcore-create-issue/SKILL.md · Investigate a failing GitHub Actions run or job and create a GitHub issue for the failure.

nvidia/skills · skills/mcore-linting-and-formatting/SKILL.md · Linting and formatting for Megatron-LM. Covers running autoformat.sh, tools (ruff, black, isort, pylint, mypy), and…

nvidia/skills · skills/mcore-run-on-slurm/SKILL.md · How to launch distributed Megatron-LM training jobs on a SLURM cluster. Covers a minimal sbatch skeleton…

nvidia/skills · skills/mcore-split-pr/SKILL.md · Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.

nvidia/skills · skills/mcore-testing/SKILL.md · Test system for Megatron-LM. Covers test layout, recipe YAML structure, adding and running unit and functional tests…

nvidia/skills · skills/medtech-model-evidence-export/SKILL.md · Exports sanitized metadata, parameters, reproducibility details, quality metrics, and optional review artifacts from…

nvidia/skills · skills/nemo-automodel-distributed-training/SKILL.md · Guide for selecting and configuring distributed training strategies in NeMo AutoModel, including FSDP2, Megatron FSDP…

nvidia/skills · skills/nemo-automodel-launcher-config/SKILL.md · Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.

nvidia/skills · skills/nemo-automodel-model-onboarding/SKILL.md · Guide for onboarding new model architectures into NeMo AutoModel, including architecture discovery, implementation…

nvidia/skills · skills/nemo-automodel-recipe-development/SKILL.md · Create and modify NeMo AutoModel training and evaluation recipes, including YAML structure, builders, and execution…

nvidia/skills · skills/nemo-fabric-build-adapter/SKILL.md · Build, migrate, review, and maintain third-party NVIDIA NeMo Fabric adapters against the public adapter contract. Use…

nvidia/skills · skills/nemo-fabric-integrate/SKILL.md · Use this skill when integrating NVIDIA NeMo Fabric into a consumer application, service, evaluation harness, or…

nvidia/skills · skills/nemo-mbridge-mlm-bridge-training/SKILL.md · Run Megatron-LM (MLM) and Megatron Bridge training with mock or real data. Covers correlation testing, available…

nvidia/skills · skills/nemo-mbridge-multi-node-slurm/SKILL.md · Convert single-node scripts to multi-node Slurm sbatch jobs and debug common multi-node failures. Covers srun-native vs…

nvidia/skills · skills/nemo-mbridge-perf-activation-recompute/SKILL.md · Validate and use selective and full activation recompute in Megatron Bridge to reduce GPU memory usage at the cost of…