Source

nvidia/skills

377 skills · 403.2K combined installs

Skills from this source

#

Skill

Source

8W Activity

Installs

holoscan-install-conda Official Install Holoscan SDK v4.3+ via Conda in a CUDA 13 environment. Use for Conda installs; redirect CUDA 12 hosts to cont…

holoscan-install-wheel Official Install Holoscan SDK Python wheel via pip into a venv. Use for Python installs; not for native C++/apt or Conda insta…

mcore-testing Official Test system for Megatron-LM. Covers test layout, recipe YAML structure, adding and running unit and functional tests,…

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

nv-generate-mr-brain Official Used for generating synthetic T1, T2, FLAIR, SWI, or MRA brain MRI volumes with NV-Generate-CTMR MR-Brain v1. Not for…

holoscan-install-debian Official Install Holoscan SDK natively on Ubuntu via apt. Use for C++ installs on Ubuntu; pair with /holoscan-install-wheel fo…

mcore-split-pr Official Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.

nemo-rl-brev-etiquette Official Brev instance operating guidance for NeMo-RL agents working in /home/ubuntu/RL with limited workspace disk, a larger …

nv-generate-mr-brain-finetune Official Used for finetuning NV-Generate-CTMR MR-Brain v1 for T1, T2, FLAIR, SWI, or MRA data from a NIfTI datalist. Not for c…

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

nv-generate-mr Official Used for generating synthetic body MRI volumes with NV-Generate-CTMR rflow-mr. Not for paired masks or production tra…

nv-reason-cxr Official Used for command-shape or live NV-Reason-CXR chest X-ray reasoning smoke tests. Not for diagnosis or clinical reporti…

nv-generate-ct-rflow Official Used for generating synthetic CT volumes and masks with NV-Generate-CTMR rflow-ct. Not for production training data w…

nv-segment-ctmr Official Used for running NV-Segment-CTMR on CT or MRI NIfTI volumes and recording label-map evidence. Not for clinical interp…

nv-segment-ct-finetune Official Runs standard or fixed-channel softmax finetuning of NV-Segment-CT VISTA3D on CT NIfTI image/label datasets, with opt…

nv-generate-vae-finetune Official Used for finetuning the NV-Generate-CTMR MAISI VAE from CT/MRI NIfTI datalists. Not for clinical or production data a…

cufolio Official Use when a user asks to build, optimize, backtest, rebalance, or analyze a stock portfolio with Mean-CVaR, efficient …

cuopt-numerical-optimization-api-python Official Solve LP, MILP, QP (beta) with cuOpt Python API — linear/quadratic objectives, integer variables, scheduling, portfol…

hsb-setup Official Clone the latest NVIDIA Holoscan Sensor Bridge repo, ask which supported devkit is being used, configure the host per…

hsb-test Official Execute QA test plans on Holoscan Sensor Bridge hardware. Reads a user-provided test document, filters tests by the u…

hsb-flash Official Flash the FPGA on an HSB board connected to an NVIDIA devkit.

hsb-app Official Discover and run Holoscan Sensor Bridge example applications on a connected devkit. Filters available apps by the use…

tao-finetune-huggingface-model Official Fine-tune any HuggingFace CV / VLM / LLM model on local NVIDIA GPUs inside an NGC PyTorch container when no dedicated…

tao-setup-nvidia-gpu-host Official >- Host setup for TAO GPU backends. Checks and, after user approval, installs minimum-compatible NVIDIA driver, CUDA …

tao-analyze-changenet-rca Official Performs deep Root Cause Analysis (RCA) on NVIDIA TAO Visual ChangeNet classification experiments with image-evidence…

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

tao-finetune-clip Official CLIP vision-language model for image-text retrieval, zero-shot classification, embedding extraction, ONNX export, and…

tao-finetune-cosmos-embed Official >- Cosmos-Embed1 video-text embedding for text-to-video retrieval, video-to-video search, semantic deduplication, and…

tao-finetune-cosmos-reason Official Cosmos3-Nano video QA supervised fine-tuning with FSDP parallelism across variable-width GPU configurations. Use when…

tao-generate-image-grounding Official Two-step image grounding pipeline: extracts referring expressions from (image, caption) pairs and grounds them to pix…

tao-generate-video-reasoning-annotations Official >- Multi-step video annotation pipeline that turns raw videos into Chain-of-Thought training data — multi-level capti…

tao-launch-workflow Official >- Shared launch intake for any TAO workflow or action. Use when the user wants to run TAO AutoML, train, evaluate, i…

tao-list-capabilities Official >- Answer what the TAO Skill Bank plugin can do by generating the response from packaged application, data, model, Au…

tao-port-huggingface-model Official Integrate a HuggingFace Computer Vision model into the NVIDIA TAO Toolkit ecosystem (tao-core config, tao-pytorch tra…

tao-run-automl Official Run container-backed AutoML / hyperparameter optimization (HPO) for NVIDIA TAO networks using AutoMLRunner. Handles a…

tao-run-inference-service Official Start, query, and stop a network-specific TAO inference microservice ({network_arch}-inference-microservice) by deleg…

tao-run-on-kubernetes Official Kubernetes execution platform — submits TAO container jobs as single-pod k8s Jobs with NVIDIA GPU scheduling. Use whe…

tao-run-on-local-docker Official Local or remote Docker execution for TAO SDK job containers using a Docker daemon with NVIDIA GPU runtime. Use when r…

tao-train-action-recognition Official Action recognition from video sequences. Supports RGB, optical flow, and joint (multi-stream) input types for classif…

tao-train-grounding-dino Official Grounding DINO for open-set object detection. Combines DINO-style detection with a BERT text encoder for language-gui…

tao-train-image-classification Official PyTorch-based TAO image classification. Supports a wide range of backbones (FAN, EfficientNet, ResNet, etc.) with dis…

tao-train-ocrnet Official OCRNet for scene text recognition. Recognizes text content from cropped text-region images and supports CTC and atten…

tao-train-optical-inspection Official Optical Inspection for defect detection using Siamese networks. Compares image pairs to detect manufacturing defects,…

tilegym-cutile-python Official Expert cuTile programming assistant. Write high-performance GPU kernels using cuTile's tile-based programming model w…

tao-train-nvpanoptix3d Official NVPanoptix3D for panoptic 3D scene reconstruction from posed RGB images. Produces 3D panoptic segmentation (semantic,…

tao-train-pose-classification Official Pose classification using ST-GCN (Spatial Temporal Graph Convolutional Network). Classifies skeleton sequences into a…

tao-analyze-gaps-visual-changenet Official Performs gap analysis on NVIDIA TAO VCN Classify (Visual Component Net) experiments by invoking the pinned TAO data-s…

tao-train-metric-learning-recognition Official Metric-learning recognition (ml-recog) for fine-grained visual recognition. Learns embeddings for retrieval-based mat…

tao-train-mask2former Official Mask2Former for universal image segmentation (panoptic, instance, and semantic). Transformer-based with masked attent…

tao-train-reid Official Person re-identification (ReID). Learns discriminative embeddings to match the same person across different camera vi…