NVIDIA
- 1.2k skills
- 0 followers
- 23k repo stars
- 561 verified
- yesterday last updated
- ▌ Tao Train Grounding Dino · nvidia bundleTrains, evaluates, exports, quantizes, and runs inference for a Grounding DINO model that detects objects described by text prompts without a fixed class vocabulary.
- ▌ Cuopt Routing Formulation · nvidia bundleDefines vehicle routing problem types (TSP, VRP, PDP) and the data requirements needed to formulate them, without covering any API or interface details.
- ▌ Dynamo Interconnect Check · nvidia bundleValidates that a Dynamo deployment's NIXL/UCX/NCCL interconnect is ready for disaggregated serving over RDMA/NVLink. Use after deploying a disagg or multi-node recipe to confirm KV transport is correct, or use troubleshoot for already-failed pods.
- ▌ Jetson Customize Nvpmodel · nvidia bundleAdd, remove, edit, list, or change the boot default of nvpmodel power modes on Jetson/Tegra platforms (Orin, Thor) by modifying the BSP-side configuration file.
- ▌ Jetson Inference Mem Tune · nvidia bundleRecommends an inference runtime and memory-related launch flags for LLM/VLM workloads on NVIDIA Jetson devices, based on a live memory audit snapshot.
- ▌ Nemo Data Designer Plugin · nvidia bundleBuild synthetic datasets and data generation pipelines using the Data Designer library.
- ▌ Nemotron Policy Generator · nvidia bundleGenerates custom safety policies for NVIDIA Nemotron content-safety guardrails, producing a Markdown policy, JSON taxonomy, and inference prompts from rough user input.
- ▌ Omniverse Cad To Simready · nvidia bundleCoordinate the end-to-end pipeline from CAD or source assets to SimReady USD assets, including conversion, material and physics assignment, validation, conformance, and optional packaging.
- ▌ Omniverse Realtime Viewer · nvidia bundleRoutes Omniverse Realtime Viewer requests to focused reference documents and enforces architectural rules for building USD viewer applications.
- ▌ Tao Analyze Changenet Rca · nvidia bundlePerforms deep root cause analysis on NVIDIA TAO Visual ChangeNet classification experiments, using image-evidence-driven investigation to diagnose model failures and produce actionable reports.
- ▌ Tao Finetune Cosmos Embed · nvidia bundleFine-tune, evaluate, run inference, and export Cosmos-Embed1 video-text embedding models for tasks like text-to-video retrieval and semantic deduplication.
- ▌ Tao Run Inference Service · nvidia bundleStart, query, and stop a TAO inference microservice for a specific network architecture by delegating container execution to the appropriate platform skill.
- ▌ Tao Setup Nvidia Gpu Host · nvidia bundleChecks and installs NVIDIA driver, CUDA Toolkit, and NVIDIA Container Toolkit for GPU-accelerated Docker and Kubernetes hosts. Supports multiple Linux distributions with automated install and read-only check modes.
- ▌ Tao Train Deformable Detr · nvidia bundleTrain, evaluate, export, quantize, and run inference for a Deformable DETR 2D object detection model using TAO, with deformable attention for efficient multi-scale feature processing.
- ▌ Tao Train Mask Auto Label · nvidia bundleTrains, evaluates, and runs inference for Mask Auto-Label (MAL) weakly-supervised segmentation models using ViT-MAE backbones with minimal point or box annotations.
- ▌ Tilegym Cutile Autotuning · nvidia bundleAdds autotuning to CuTile kernels using the exhaustive_search API with a tune-once/cache/direct-launch pattern, covering occupancy-only and complex tile-size search spaces.
- ▌ Accelerated Computing Cudf · nvidia bundleAccelerate pandas workflows with GPU DataFrames using cuDF and dask-cuDF for ETL, joins, groupby, and large-scale data processing.
- ▌ Holoscan Install Container · nvidia bundlePull and verify the official Holoscan SDK container from NGC, selecting the correct CUDA/arch tag for the host GPU and validating with bundled Python and C++ examples.
- ▌ Nemotron Retrieval Recipes · nvidia bundlePlan, debug, tune, evaluate, export, or deploy public Nemotron embedding and reranking retrieval recipes using the current checkout.
- ▌ Tao Run On Slurm · nvidia bundleSubmit and manage TAO training, evaluation, and inference jobs on SLURM GPU clusters over SSH with sbatch/srun, Pyxis/Enroot containers, and Lustre-backed storage.
- ▌ Tao Run Platform · nvidia bundleSubmit and monitor GPU training jobs on Brev, SLURM, Docker, or Kubernetes using the TAO Execution SDK, with job handles, S3 I/O wrapping, and multi-node distributed training.
- ▌ Dali Dynamic Mode · nvidia bundleWrite, review, and migrate code using NVIDIA DALI's imperative dynamic-mode API for efficient data loading and preprocessing.
- ▌ Jetson Diagnostic · nvidia bundleCaptures a read-only health snapshot from a Jetson device, reporting identity, memory, GPU, thermal, power, storage, services, and top processes.
- ▌ Jetson Init Image · nvidia bundleExtract Jetson Linux BSP and sample-rootfs tarballs, run apply_binaries.sh with the correct GPU stack flag, and record the image metadata in the active target profile.
- ▌ Jetson Set Target · nvidia bundleSwitch the active Jetson target-platform pointer to an existing profile YAML. Use before customize/build/flash to change target; not for authoring profiles — use jetson-init-target instead.
- ▌ Tao Finetune Clip · nvidia bundleFine-tune and deploy CLIP vision-language models for zero-shot classification, image-text retrieval, and embedding extraction with ONNX and TensorRT support.
- ▌ Tao Run On Lepton · nvidia bundleSubmit TAO jobs to Lepton managed GPU compute on DGX Cloud, with run/status/cancel interface and multi-node distributed training support.
- ▌ Vss Manage Alerts · nvidia bundleOperate the VSS alert pipeline for real-time monitoring, Alert-Bridge subscriptions, Slack notifications, incident queries, and camera onboarding.
- ▌ Jetson Flash Image · nvidia bundleFlash a promoted BSP image to a Jetson device in RCM mode using NVIDIA's flash.sh or l4t_initrd_flash.sh toolchain.
- ▌ Jetson Generate Kb · nvidia bundleGenerates a per-target knowledge-base markdown file by walking the BSP root and source tree, documenting image layout, source tree structure, and document references.
- ▌ Jetson Init Source · nvidia bundleBootstraps a BSP customization workspace for NVIDIA Jetson, including the Linux_for_Tegra overlay tracker, bsp_sources mono-tree, and Crosstool-NG toolchain.
- ▌ Jetson Init Target · nvidia bundleCreates a new Jetson target-platform profile YAML by selecting a reference devkit and optional custom carrier, then updates the active target pointer.
- ▌ Jetson Quick Start · nvidia bundleDispatches Jetson BSP customization by presenting a click-to-select setup questionnaire and passing prefilled answers to downstream setup skills.
- ▌ Mcore Create Issue · nvidia bundleInvestigate a failing GitHub Actions job, extract the root cause, and file a well-structured bug issue against NVIDIA/Megatron-LM.
- ▌ Mcore Run On Slurm · nvidia bundleLaunch distributed Megatron-LM training jobs on a SLURM cluster with a minimal sbatch skeleton, environment-variable setup for torch.distributed.run, CUDA_DEVICE_MAX_CONNECTIONS rules, container conventions, monitoring, and per-rank failure diagnosis.
- ▌ Nemotron Customize · nvidia bundlePlan, configure, and chain Nemotron model customization steps into single-step or multi-step pipelines for curation, translation, fine-tuning, RL alignment, benchmarking, checkpoint conversion, optimization, and evaluation.
- ▌ Tao Train Nvdinov2 · nvidia bundleTrains vision transformers via self-distillation without labels for self-supervised visual representation learning, and supports export and inference of NVDINOv2 backbones.
- ▌ Tao Train Sparse4d · nvidia bundleTrains, evaluates, exports, quantizes, and runs inference for Sparse4D multi-camera temporal 3D object detection and tracking models using TAO.
- ▌ Vss Deploy Profile · nvidia bundleSelects, configures, deploys, verifies, debugs, or tears down a VSS profile (base, search, lvs, warehouse, edge) for NVIDIA's video search and summarization stack.
- ▌ Vss Search Archive · nvidia bundleSearch archived video using natural language, ingest video files or RTSP streams, and manage ingested sources.
- ▌ Cuopt Server Common · nvidia bundleExplains the domain concepts of the cuOpt REST server, including supported problem types, request flow, and key endpoints, without deployment or client code.
- ▌ Cupynumeric Install · nvidia bundleInstall and verify cuPyNumeric for Python using conda or pip, including GPU usage checks.
- ▌ Dynamo Troubleshoot · nvidia bundleDiagnose failed or unhealthy Dynamo deployments by collecting a read-only debug bundle, classifying failures, and providing step-by-step remediation guidance.
- ▌ Jetson Build Source · nvidia bundleRebuild kernel-side artifacts (DTBs, OOT modules, kernel Image) from source changes under bsp_sources/ and produce a manifest for staging into a BSP image.
- ▌ Jetson Download Bsp · nvidia bundleDownloads NVIDIA Jetson Linux BSP artifacts (BSP tarball, sample rootfs, public_sources, x-tools, guides) for the active target. Used for Auto Setup; does not extract or edit profiles.
- ▌ Jetson Memory Audit · nvidia bundleMeasure Jetson DRAM and NvMap usage, capture before/after baselines, and verify memory reclamation with live audit data.
- ▌ Nemoclaw User Guide · nvidia bundleGuides AI coding assistants to the official NemoClaw documentation via MCP server or Markdown files for installation, configuration, operation, and troubleshooting.
- ▌ Tao Launch Workflow · nvidia bundleCollects launch inputs and runs preflight checks before executing TAO workflows such as AutoML, training, evaluation, inference, export, TensorRT engine generation, or DEFT jobs on supported platforms.
- ▌ Tao Mine Aoi Images · nvidia bundleEmbeds target and source image parquets, then mines nearest-neighbour source images for augmentation in VCN AOI workflows.
- ▌ Tao Train Bevfusion · nvidia bundleTrains, evaluates, and runs inference for BEVFusion multi-sensor 3D object detection models that fuse LiDAR and camera data in bird's-eye-view space for autonomous driving.
- ▌ Tao Train Oneformer · nvidia bundleTrain, evaluate, export, quantize, and run inference for a TAO OneFormer model that performs panoptic, instance, and semantic segmentation using task-conditioned queries.
- ▌ Tao Train Segformer · nvidia bundleTrains, evaluates, exports, quantizes, and runs inference for SegFormer semantic segmentation models using NVIDIA TAO.
- ▌ Vss Query Analytics · nvidia bundleQueries video analytics incidents, alerts, metrics, and sensor data from Elasticsearch via the VA-MCP server.
- ▌ Vss Summarize Video · nvidia bundleSummarize recorded video clips using the LVS microservice with a VLM fallback, producing a narrative summary with timestamped events.
- ▌ Dynamo Recipe Runner · nvidia bundleSelect, validate, patch, and deploy existing NVIDIA Dynamo Kubernetes recipes for model serving with GPU support.
- ▌ Earth2studio Install · nvidia bundleGuides installing Earth2Studio via uv or pip, selecting model extras, and configuring environment variables.
- ▌ Jetson Customize Fan · nvidia bundleAdd, remove, edit, list, or change the boot default of an nvfancontrol fan profile on a Jetson/Tegra target.
- ▌ Jetson Customize Usb · nvidia bundleEnable, disable, or change the role of USB2/USB3 SS ports on Jetson custom carriers by generating kernel-DT overlays that flip lane, port, and host xHCI phys in lockstep.
- ▌ Jetson Headless Mode · nvidia bundlePlan and apply safe, reversible headless-mode changes on Jetson devices to reclaim memory from the GUI and non-essential daemons.
- ▌ Jetson LLM Benchmark · nvidia bundleBenchmark Jetson LLM/VLM serving performance across vLLM, llama.cpp, and Ollama with structured JSON output.
- ▌ Jetson Promote Image · nvidia bundleCopies overlay files and built artifacts into a staged BSP image for NVIDIA Jetson platforms, preparing it for flashing without modifying the workspace.
- ▌ Nv Generate Ct Rflow · nvidia bundleGenerates synthetic CT volumes and masks using NVIDIA's rectified-flow pipeline for medical imaging research.
- ▌ Nv Generate Mr Brain · nvidia bundleGenerates synthetic brain MRI volumes using NVIDIA's NV-Generate-CTMR workflow, with configurable modality and random seed.
- ▌ Physicsnemo Discover · nvidia bundleNavigate the PhysicsNeMo repository by discovering model families, datapipes, and examples through live file search, without writing training code.
- ▌ Skill Card Generator · nvidia bundleGenerates or updates a governance skill card for an existing agent skill directory by analyzing source signals, building a grounded JSON context, and rendering a deterministic markdown card.
- ▌ Tao Train Centerpose · nvidia bundleTrain, evaluate, export, and run inference for CenterPose models used in 6-DoF object pose estimation with keypoint regression.
- ▌ Cuopt Skill Evolution · nvidia bundleDetects generalizable learnings from problem-solving interactions and proposes skill updates to improve future performance.
- ▌ Dynamo Router Starter · nvidia bundleStart or patch Dynamo router modes and run router endpoint smoke checks for round-robin, KV-aware, least-loaded, or device-aware routing.
- ▌ Earth2studio Discover · nvidia bundleFind Earth2Studio models, data sources, and examples for weather/climate use cases by consulting live documentation and verifying compatibility via the lexicon system.
- ▌ Jetson Customize Mgbe · nvidia bundleGenerates kernel-DT overlay fragments to enable 25G/10G/1G MGBE QSFP interfaces on Jetson Thor, verifying pinmux and integrating with the BSP customization workflow.
- ▌ Jetson Customize Pcie · nvidia bundleGenerates kernel device-tree overlay fragments to enable or disable individual PCIe controllers and configure lane count and link speed on Jetson Thor/Orin custom carriers.
- ▌ Jetson Derive Carrier · nvidia bundleBootstrap a custom carrier board by forking carrier files and scaffolding a DT overlay from the reference devkit.
- ▌ Cufolio · nvidia bundleBuild, optimize, backtest, rebalance, or analyze stock portfolios using NVIDIA-accelerated Mean-CVaR optimization with cuOpt GPU solver.
- ▌ Hsb App · nvidia bundleDiscover, select, and run Holoscan Sensor Bridge example applications on a connected devkit over SSH, filtering by platform, board type, and sensors.
- ▌ Hsb Test · nvidia bundleExecute QA test plans on Holoscan Sensor Bridge hardware by reading a test document, filtering tests by setup, running automatable tests with pass/fail evaluation, and producing a structured report.
- ▌ RAG Eval · nvidia bundleEvaluates RAG pipelines using a filesystem-based benchmark with corpus/ and train.json, running evaluate_rag.py to tune retrieval and generation flags and interpret RAGAS metrics.
- ▌ RAG Perf · nvidia bundleRun config-driven performance benchmarks against a deployed NVIDIA RAG Blueprint server, including profiling and load testing, with a unified report.
- ▌ Hsb Flash · nvidia bundleFlash FPGA firmware on HSB Lattice boards and Leopard Imaging VB1940 cameras connected to NVIDIA devkits, with safety checks and multi-step upgrade/downgrade procedures.
- ▌ Hsb Setup · nvidia bundleSet up the Holoscan Sensor Bridge demo environment end-to-end: clone the repo, configure the host per platform, build and run the demo container, and verify connectivity to the sensor board.
- ▌ Aiq Deploy · nvidia bundleInstalls, deploys, runs, validates, troubleshoots, and stops NVIDIA AI-Q Blueprint infrastructure for local or self-hosted servers.
- ▌ Cudaq Guide · nvidia bundleGuide users through installing CUDA-Q, writing quantum kernels, running GPU-accelerated simulations, connecting to QPU hardware, and exploring built-in applications.
- ▌ Aiq Research · nvidia bundleRuns deep research queries through a reachable NVIDIA AI-Q Blueprint backend, handling health checks, job submission, polling, and report retrieval.
- ▌ Nemo Rl Docs · nvidia bundleUpdate docs/index.md and write Google-style docstrings for NeMo-RL documentation changes.
- ▌ Cuopt Install · nvidia bundleInstall cuOpt for Python, C, or REST server via pip, conda, or Docker, and verify the installation.
- ▌ Data Designer · nvidia bundleBuild synthetic datasets and data generation pipelines using the Data Designer library.
- ▌ Mcore Testing · nvidia bundleGuides testing Megatron-LM: test layout, recipe YAML, adding and running unit/functional tests, golden values, marker filters, and CI parity.
- ▌ Nv Reason Cxr · nvidia bundleRuns chest X-ray reasoning smoke tests using the NV-Reason-CXR-3B model via local inference or a public Hugging Face Space API.
- ▌ Nv Segment Ct · nvidia bundleSegments abdominal organs from CT NIfTI volumes using the NV-Segment-CT VISTA3D model, producing label maps and structured evidence JSON.
- ▌ RAG Blueprint · nvidia bundleDeploy, configure, troubleshoot, and manage NVIDIA RAG Blueprint deployments across Docker, Helm, and library setups.
- ▌ Vss Ask Video · nvidia bundleAsk visual questions about video clips using a VSS agent's video_understanding tool, requiring a fresh look at frames rather than prior metadata or search results.
- ▌ Deepstream Dev · nvidia bundleBuild video analytics pipelines using NVIDIA DeepStream SDK 9.0 with Python pyservicemaker API, including GStreamer-based video processing, TensorRT inference integration, object detection/tracking, and Kafka/message broker integration.
- ▌ Holoscan Setup · nvidia bundleInspects the host system, assesses platform compatibility, and recommends the correct Holoscan SDK installation method, then delegates to a method-specific install skill.
- ▌ Jetson Package · nvidia bundleSelects Jetson-compatible containers, vLLM runtime images, and Jetson AI Lab PyPI indexes based on Orin SM 8.7 vs Thor SM 11.0 and JetPack version.
- ▌ Launch Nemo Rl · nvidia bundleLaunch, monitor, stop, and debug NeMo-RL recipes on a Kubernetes cluster using the nrl-k8s CLI, supporting ephemeral and long-lived RayCluster modes.
- ▌ Mcore Split Pr · nvidia bundleSplit a large pull request into multiple smaller PRs to reduce the number of required CODEOWNERS reviewer groups.
- ▌ Nemo Retriever · nvidia bundleIndex folders of PDFs and other documents into LanceDB for vector search, then query them with semantic search, page filters, verbatim quotes, and cross-document aggregation.
- ▌ Nv Generate Mr · nvidia bundleGenerates synthetic body MRI volumes using NVIDIA's NV-Generate-CTMR rflow-mr model. Wraps the upstream diffusion inference pipeline with config staging, output validation, and NIfTI volume summarization.
- ▌ Tao Run Automl · nvidia bundleRun automated hyperparameter optimization for NVIDIA TAO models using AutoMLRunner, supporting multiple search algorithms and experiment tracking.
- ▌ Tao Train Dino · nvidia bundleTrain, evaluate, export, distill, quantize, or run inference for a TAO DINO 2D object detector using transformer-based detection with denoising training and multi-scale features.
- ▌ Tao Train Reid · nvidia bundleTrains, evaluates, exports, and runs inference for person re-identification models using TAO, learning discriminative embeddings for cross-camera matching.