Every Hermes skill, in one place

185 official skills from the Hermes Agent repository plus 101,376 community entries. Community index checked 2026-11-20 (UTC). Read community skills at their original sources.

Open baoyu-article-illustrator in the official library

Community index generated 2026-11-20 (UTC), checked 2026-11-20 (UTC).

Skill results

34 official + 4,295 community matches. Page 166 of 180.

Official skills first, then community.

Best match / quality.

Run container-backed AutoML / hyperparameter optimization (HPO) for NVIDIA TAO networks using AutoMLRunner. Handles algorithm selection (bayesian, hyperband, asha, bohb, llm, hybrid, autoresearch), WandB experiment tracking, job execution o

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install NVIDIA/skills/skills/tao-run-automl
AI models & providers · Automation & multi-agentSource (opens in a new tab)

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 "ru

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install NVIDIA/skills/skills/tao-run-automl-deft-pipeline
AI models & providers · Automation & multi-agentSource (opens in a new tab)

Run a Python training/eval script directly in an existing local virtualenv ; no docker, no container. Implements the four-verb consumer contract (submit/status/logs/cancel) over a vendored process-lifecycle runner with durable on-disk state

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install NVIDIA/skills/skills/tao-run-on-virtualenv
Coding & developer tools · AI models & providersSource (opens in a new tab)

Host setup for TAO GPU backends. Checks and, after user approval, installs minimum-compatible NVIDIA driver, CUDA Toolkit, and NVIDIA Container Toolkit versions for Docker/local-Docker and Kubernetes GPU worker hosts. TAO-wide defaults can

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install NVIDIA/skills/skills/tao-setup-nvidia-gpu-host
Coding & developer tools · AI models & providersSource (opens in a new tab)

Token-efficient execution kit for repeated TAO agentic workflows. Compiles a skill into stage cards once (with a strong model), then executes them forever in fresh, small headless sessions coordinated by a bash driver ; measured 67-91% toke

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install NVIDIA/skills/skills/tao-token-efficient-execution
AI models & providers · Cost, speed & monitoringSource (opens in a new tab)

Action recognition from video sequences. Supports RGB, optical flow, and joint (multi-stream) input types for classifying temporal actions in video clips. Use when training, evaluating, exporting, or running inference on a TAO action-recogn

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install NVIDIA/skills/skills/tao-train-action-recognition
AI models & providers · Images, video, music & 3DSource (opens in a new tab)

BEVFusion for multi-sensor 3D object detection. Fuses LiDAR point clouds and camera images in bird's-eye-view (BEV) space, used in autonomous driving for robust 3D perception. Use when training, evaluating, or running inference for a TAO BE

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install NVIDIA/skills/skills/tao-train-bevfusion
AI models & providers · Images, video, music & 3DSource (opens in a new tab)

CenterPose for keypoint / pose estimation. Detects object centers and regresses keypoint locations for 6-DoF object pose estimation. Use when training, evaluating, exporting, or running inference for a TAO CenterPose model. Trigger phrases

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install NVIDIA/skills/skills/tao-train-centerpose
AI models & providersSource (opens in a new tab)

Co-DETR (CoDINO) for object detection. A DETR-family detector with collaborative hybrid assignment ; auxiliary one-to-many heads supervise the encoder during training, giving strong closed-set accuracy at high inference cost. Use when train

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install NVIDIA/skills/skills/tao-train-codetr
AI models & providers · Cost, speed & monitoringSource (opens in a new tab)

Deformable DETR for 2D object detection. Uses deformable attention for efficient multi-scale feature processing, lighter than DINO with competitive accuracy. Use when training, evaluating, exporting, quantizing, or running inference for a T

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install NVIDIA/skills/skills/tao-train-deformable-detr
AI models & providersSource (opens in a new tab)

Monocular depth estimation using Metric Depth Anything v2 or Relative Depth Anything architectures. Predicts per-pixel depth from single RGB images. Use when training, evaluating, exporting, or running inference for a TAO monocular depth mo

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install NVIDIA/skills/skills/tao-train-depth-anything-v2
AI models & providers · Images, video, music & 3DSource (opens in a new tab)

Real-time stereo depth estimation using FastFoundationStereo (FFS), the distilled bp2 commercial variant of FoundationStereo. Predicts disparity maps from stereo image pairs with ~10× lower latency than full FoundationStereo. Use when train

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install NVIDIA/skills/skills/tao-train-fast-foundation-stereo
AI models & providers · Images, video, music & 3DSource (opens in a new tab)

Stereo depth estimation using FoundationStereo. Predicts disparity maps from stereo image pairs for 3D reconstruction. Use when training, evaluating, exporting, or running inference for a TAO FoundationStereo model. Trigger phrases include

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install NVIDIA/skills/skills/tao-train-foundation-stereo
AI models & providers · Images, video, music & 3DSource (opens in a new tab)

Grounding DINO for open-set object detection. Combines DINO-style detection with a BERT text encoder for language-guided detection ; detects objects described by text prompts without a fixed class vocabulary. Use when training, evaluating,

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install NVIDIA/skills/skills/tao-train-grounding-dino
Coding & developer tools · AI models & providersSource (opens in a new tab)

PyTorch-based TAO image classification. Supports a wide range of backbones (FAN, EfficientNet, ResNet, etc.) with distillation and quantization for deployment. Use when training, evaluating, distilling, quantizing, exporting, or running inf

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install NVIDIA/skills/skills/tao-train-image-classification
AI models & providers · Images, video, music & 3DSource (opens in a new tab)

MAL (Mask Auto-Label) for weakly-supervised segmentation. Produces segmentation masks from minimal annotations (point or box annotations) using a ViT-MAE backbone. Use when training, evaluating, or running inference for a TAO MAL model. Tri

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install NVIDIA/skills/skills/tao-train-mask-auto-label
AI models & providersSource (opens in a new tab)

Mask Grounding DINO for grounded instance segmentation. Extends Grounding DINO with a mask-prediction head for open-set segmentation guided by text prompts. Use when training, evaluating, exporting, quantizing, or running inference for a TA

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install NVIDIA/skills/skills/tao-train-mask-grounding-dino
AI models & providersSource (opens in a new tab)

Mask2Former for universal image segmentation (panoptic, instance, and semantic). Transformer-based with masked attention for high-quality segmentation results. Use when training, evaluating, exporting, quantizing, or running inference for a

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install NVIDIA/skills/skills/tao-train-mask2former
AI models & providers · Images, video, music & 3DSource (opens in a new tab)

Metric-learning recognition (ml-recog) for fine-grained visual recognition. Learns embeddings for retrieval-based matching (e.g., retail product recognition) using triplet / contrastive losses. Use when training, evaluating, exporting, or r

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install NVIDIA/skills/skills/tao-train-metric-learning-recognition
AI models & providersSource (opens in a new tab)

NVPanoptix3D for panoptic 3D scene reconstruction from posed RGB images. Produces 3D panoptic segmentation (semantic, instance, and panoptic masks) with occupancy completion. Built on a VGGT backbone with a Mask2Former-style head and 3D fru

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install NVIDIA/skills/skills/tao-train-nvpanoptix3d
AI models & providers · Images, video, music & 3DSource (opens in a new tab)

OCDNet for scene text detection. Detects arbitrary-oriented text regions in natural images using a differentiable binarization approach. Use when training, evaluating, exporting, pruning, quantizing, retraining, or running inference for a T

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install NVIDIA/skills/skills/tao-train-ocdnet
AI models & providers · Images, video, music & 3DSource (opens in a new tab)

OCRNet for scene text recognition. Recognizes text content from cropped text-region images and supports CTC and attention-based decoders. Use when training, evaluating, exporting, pruning, quantizing, retraining, or running inference for a

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install NVIDIA/skills/skills/tao-train-ocrnet
AI models & providers · Images, video, music & 3DSource (opens in a new tab)

OneFormer for universal image segmentation. Unifies panoptic, instance, and semantic segmentation with a single architecture using task-conditioned queries. Use when training, evaluating, exporting, quantizing, or running inference for a TA

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install NVIDIA/skills/skills/tao-train-oneformer
AI models & providers · Images, video, music & 3DSource (opens in a new tab)

Optical Inspection for defect detection using Siamese networks. Compares image pairs to detect manufacturing defects, anomalies, or quality issues. Use when training, evaluating, exporting, or running inference for a TAO Optical Inspection

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install NVIDIA/skills/skills/tao-train-optical-inspection
AI models & providers · Images, video, music & 3DSource (opens in a new tab)

Entries with unclear source links are withheld. Some restricted-license records have source links only. Full skill instructions stay at the original source.