Skip to content

Fresh entity pages

New and Recently Updated Skills

Verified Agent Skills sorted by source update date. This is where newly published SKILL.md files should surface first.

Snapshot 2026-09-023908 verified skills
#2929

Tao Finetune Cosmos Reason

Cosmos3-Nano video QA supervised fine-tuning with FSDP parallelism. Use when training or evaluating video

MediaClaude Code
#2930

Tao Finetune Huggingface Model

Fine-tune any HuggingFace CV / VLM / LLM model on local NVIDIA GPUs inside an NGC PyTorch container. Use when the user wants to fine-tune a HuggingFace model (full or LoRA), train a vision / VLM / LLM model end-to-end, generate a reproducible HF training pipeline, smoke-test a HuggingFace model locally before scale-up, push a fine-tuned model to the HF Hub with a model card, or emit a self-contained rerun skill for an existing HuggingFace finetune. Supports image classification, object detection, semantic / instance / panoptic segmentation, depth estimation, image-text-to-text VLM (SFT / LoRA), and LLM SFT / DPO / GRPO. Six-step workflow: inspect and qualify, hardware and NGC image, research, generate and smoke, train + eval + infer, push and emit rerun skill.

CommunicationClaude Code
#2931

Tao Generate Image Grounding

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

MediaClaude Code
#2932

Tao Generate Referring Expressions

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

MediaClaude Code
#2933

Tao Generate Video Reasoning Annotations

Multi-step video annotation pipeline that turns raw videos into Chain-of-Thought training data — multi-level captions, structured descriptions, and QA pairs (MCQ, binary, open-ended) with reasoning traces, via VLM/LLM distillation. Use when the user wants to "create video training data", "generate video QA datasets", "build CoT reasoning traces from videos", "auto-label videos", or run the video_reasoning_annotation pipeline. Triggers include "video annotation", "video CoT", "video QA", "chain-of-thought", "video captioning pipeline", "video distillation".

MediaClaude Code
#2934

Tao Launch Workflow

Shared launch intake for any TAO workflow or action. Use when the user wants to run TAO AutoML, train, evaluate, infer, export, generate TensorRT engines, or launch DEFT/workflow jobs on an execution platform.

CodingClaude Code
#2935

Tao List Capabilities

Answer what the TAO Skill Bank plugin can do by generating the response from packaged application, data, model, AutoML, and platform manifests. Use when the user asks "what can TAO Skill Bank do", "list TAO models", "which TAO workflows are available", or "what supports AutoML".

CodingClaude Code
#2936

Tao Mine Aoi Images

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 source images for downstream augmentation. Use as the immediate next step after `tao-route-visual-changenet-samples` when expanding a real-image augmentation queue from the mining subset.

MediaClaude Code
#2937

Tao Port Huggingface Model

Integrate a HuggingFace Computer Vision model into the NVIDIA TAO Toolkit ecosystem (tao-core config, tao-pytorch trainer, tao-deploy TensorRT pipeline). Use when the user asks to "integrate a HuggingFace model into TAO", "add an HF model to TAO Toolkit", "wire a HuggingFace ViT/DETR/ SegFormer into tao-pytorch", "build a TAO trainer + deploy pipeline for an HF CV model", or pastes a HuggingFace model URL/ID and wants it turned into a TAO model. Covers the full 7-phase loop: prerequisites check, HuggingFace inspection and validation, codebase exploration, tao-core configuration and native trainer implementation, ONNX export plus TensorRT deploy integration, packaging and L0 testing, container-based end-to-end validation, and (conditional) accuracy/latency tuning. Supports classification, object detection, semantic / instance / panoptic segmentation, zero-shot detection, and depth estimation.

DevOpsClaude Code
#2938

Tao Route Visual Changenet Samples

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

CodingClaude Code
#2939

Tao Run Automl

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

CodingClaude Code
#2940

Tao Run Automl Deft Pipeline

Run the canonical NVIDIA AOI three-phase training pipeline — Phase 1 AutoML baseline (HPO), Phase 2 DEFT loop (RCA → SDG → mining → plain-train retrain), Phase 3 AutoML refinement on the DEFT-augmented dataset. Use when the user asks to "run the AOI workflow", "fine-tune my PCB AOI model end-to-end", "improve my AOI ChangeNet model", or "AOI workflow with AutoML" request — route here instead of tao-run-deft-aoi directly unless the user explicitly asks for the DEFT loop ONLY (e.g. "run JUST the DEFT loop", "skip AutoML, only DEFT"). Also handles the same three-phase pattern for non-AOI DEFT applications — AutoML baseline then DEFT loop warm-started from AutoML's winning HPs then post-DEFT AutoML refinement on the iteration-augmented dataset. Trigger phrases include "run the AOI workflow", "AOI end-to-end", "AutoML + DEFT", "AutoML then DEFT", "tune hyperparameters then DEFT", "DEFT with AutoML at both ends", "warm-start DEFT", "improve my AOI model".

CodingClaude Code
#2941

Tao Run Deft Aoi

Run the full DEFT AOI improvement loop for NVIDIA TAO VisualChangeNet / ChangeNet PCB inspection models: baseline evaluate, RCA, Cosmos AnomalyGen / AMP synthetic defects, k-NN mining, retraining, and deployment gating until FAR / recall KPI targets are met. Use for prompts like "run the DEFT loop", "fine-tune until FAR below 0.1% at recall=100%", or "improve my AOI ChangeNet model with RCA and synthetic defects"; do not use for standalone TAO training, one-off inference, generic anomaly generation, or RCA-only analysis.

CommunicationClaude Code
#2942

Tao Run Inference Service

Start, query, and stop a network-specific TAO inference microservice ({network_arch}-inference-microservice) by delegating container execution to the appropriate platform skill. Handles container image resolution, job-payload JSON construction, and the service registry. Use when the user wants to run inference on a TAO model checkpoint using a microservice container, deploy a TAO inference endpoint, or stop a running inference container.

MediaClaude Code
#2943

Tao Run On Brev

Brev managed GPU instances with Docker support. Use when running TAO training, evaluation, or inference on

DevOpsClaude Code
#2944

Tao Run On Docker

Docker conventions for running NVIDIA GPU container workloads — NGC authentication, --gpus flag, mount patterns,

DevOpsClaude Code
#2945

Tao Run On Kubernetes

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

DevOpsClaude Code
#2946

Tao Run On Local Docker

Local or remote Docker execution for TAO SDK job containers using a Docker daemon with NVIDIA GPU runtime. Use

DevOpsClaude Code
#2947

Tao Run On Slurm

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

CodingClaude Code
#2948

Tao Run Platform

TAO Execution SDK for submitting and monitoring GPU training jobs on supported platforms (Brev, SLURM,

DevOpsClaude Code
#2949

Tao Setup Nvidia Gpu Host

Host setup for TAO GPU backends. Checks and, after user approval, installs NVIDIA driver branch 580, CUDA Toolkit 13.0, and NVIDIA Container Toolkit 1.19.0 for Docker/local-Docker and Kubernetes GPU worker hosts. The `--check-only` path works on any Linux distribution; `--install` automates debian-family (Ubuntu/Debian/Pop!_OS/Mint/Zorin/Raspbian), rhel-family (Fedora/RHEL/Rocky/AlmaLinux), and suse-family (openSUSE/SLES) hosts, and prints actionable manual-install steps for everything else. Use when the user asks to "set up an NVIDIA GPU host", "check TAO Docker GPU runtime", or prepare a Kubernetes GPU worker for TAO.

DevOpsClaude Code
#2950

Tao Train Action Recognition

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

MediaClaude Code
#2951

Tao Train Bevfusion

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

MediaClaude Code
#2952

Tao Train Centerpose

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

CodingClaude Code
#2953

Tao Train Deformable Detr

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

CodingClaude Code
#2954

Tao Train Depth Anything V2

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

CodingClaude Code
#2955

Tao Train Dino

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

CodingClaude Code
#2956

Tao Train Fast Foundation Stereo

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

CodingClaude Code
#2957

Tao Train Foundation Stereo

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

MediaClaude Code
#2958

Tao Train Grounding Dino

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

CodingClaude Code
#2959

Tao Train Image Classification

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

MediaClaude Code
#2960

Tao Train Mask Auto Encoder

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

CodingClaude Code
#2961

Tao Train Mask Auto Label

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

CodingClaude Code
#2962

Tao Train Mask Grounding Dino

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

CodingClaude Code
#2963

Tao Train Mask2former

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

MediaClaude Code
#2964

Tao Train Metric Learning Recognition

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

CodingClaude Code
#2965

Tao Train Nvdinov2

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

CodingClaude Code
#2966

Tao Train Nvpanoptix3d

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

MediaClaude Code
#2967

Tao Train Ocdnet

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

MediaClaude Code
#2968

Tao Train Ocrnet

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

MediaClaude Code
#2969

Tao Train Oneformer

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

MediaClaude Code
#2970

Tao Train Optical Inspection

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

MediaClaude Code
#2971

Tao Train Pointpillars

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

MediaClaude Code
#2972

Tao Train Pose Classification

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

CodingClaude Code
#2973

Tao Train Reid

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

CodingClaude Code
#2974

Tao Train Rtdetr

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

CodingClaude Code
#2975

Tao Train Segformer

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

CodingClaude Code
#2976

Tao Train Single Step

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

CodingClaude Code