Skill directory
Agent skills
Focused instruction packs that teach a coding agent one job well. Browse the catalog and use any of them inside a RiverX project.
18,175Skills
1,902Publishers
249Official
Tao Analyze Changenet Rcanvidia/skillsPerforms deep Root Cause Analysis (RCA) on NVIDIA TAO Visual ChangeNet classification experiments with016Tao Analyze Gaps Visual Changenetnvidia/skillsPerforms gap analysis on NVIDIA TAO VCN Classify (Visual Component Net) experiments by invoking the pinned TAO data-services container directly via `docker run … gap_analysis vcn_aoi …` — picks the optimal decision threshold, ranks per-sample weakness, and emits a top-K weakest parquet expanded per-lighting for downstream augmentation. Use when analyzing VCN classification failures, picking SDA augmentation targets, or auditing PASS/NO_PASS boundary cases.017Tao Analyze Gaps Vlm Bcqnvidia/skillsExtract false-positive and false-negative gaps from VLM binary-classification-question (BCQ, yes/no) predictions.09Tao Convert Dataset Formatnvidia/skillsRun `tao-daft convert` to convert NVIDIA TAO DAFT datasets between supported formats. Do not use for non-DAFT data.06Tao Finetune Clipnvidia/skillsCLIP vision-language model for image-text retrieval, zero-shot classification, embedding extraction, ONNX020Tao Finetune Cosmos Embednvidia/skills>-012Tao Finetune Cosmos Reasonnvidia/skills>-045Tao Finetune Huggingface Modelnvidia/skills>029Tao Generate Image Groundingnvidia/skillsTwo-step image grounding pipeline: extracts referring expressions from (image, caption) pairs and grounds them09Tao Generate Referring Expressionsnvidia/skillsFour-step image referring-expression pipeline: turns images plus KITTI bounding-box labels into region09Tao Generate Video Reasoning Annotationsnvidia/skills>-011Tao Launch Workflownvidia/skills>-010Tao List Capabilitiesnvidia/skills>-06Tao Mine Aoi Imagesnvidia/skillsRuns 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.017Tao Port Huggingface Modelnvidia/skills>022Tao Route Visual Changenet Samplesnvidia/skillsRoutes the weakest VCN samples (output of `tao-analyze-gaps-visual-changenet`) into per-augmentation-module012Tao Run Automlnvidia/skillsRun container-backed AutoML / hyperparameter optimization (HPO) for NVIDIA TAO networks using AutoMLRunner. Handles algorithm020Tao Run Automl Deft Pipelinenvidia/skills>010Tao Run Deft Aoinvidia/skills>049Tao Run Inference Servicenvidia/skills>012Tao Run On Brevnvidia/skillsRun a TAO training/evaluation/inference container on an NVIDIA Brev GPU instance. Instance provisioning (create/search/stop/delete/login) is delegated to the official brev-cli agent skill or the Brev MCP server; this skill covers only the TAO-specific part — running the container over `brev exec` via the four-verb docker contract. Trigger phrases include "run on Brev", "Brev GPU instance", "TAO on Brev", "submit job to Brev".07Tao Run On Kubernetesnvidia/skillsKubernetes execution platform — submits TAO container jobs as k8s Jobs with NVIDIA GPU scheduling; single-pod012Tao Run On Slurmnvidia/skillsRemote SLURM GPU cluster execution over SSH with sbatch/srun, Pyxis/Enroot containers, and Lustre-backed012Tao Setup Nvidia GPU Hostnvidia/skills>-08Tao Train Action Recognitionnvidia/skillsAction recognition from video sequences. Supports RGB, optical flow, and joint (multi-stream) input types for016Tao Train Bevfusionnvidia/skillsBEVFusion for multi-sensor 3D object detection. Fuses LiDAR point clouds and camera images in bird's-eye-view016Tao Train Centerposenvidia/skillsCenterPose for keypoint / pose estimation. Detects object centers and regresses keypoint locations for 6-DoF023Tao Train Deformable Detrnvidia/skillsDeformable DETR for 2D object detection. Uses deformable attention for efficient multi-scale feature processing,025Tao Train Depth Anything V2nvidia/skillsMonocular depth estimation using Metric Depth Anything v2 or Relative Depth Anything architectures. Predicts028Tao Train Dinonvidia/skillsDINO (DETR with Improved DeNoising Anchor Boxes) for 2D object detection. Transformer-based detector with031Tao Train Fast Foundation Stereonvidia/skillsReal-time stereo depth estimation using FastFoundationStereo (FFS), the distilled bp2 commercial variant of020Tao Train Foundation Stereonvidia/skillsStereo depth estimation using FoundationStereo. Predicts disparity maps from stereo image pairs for 3D027Tao Train Grounding Dinonvidia/skillsGrounding DINO for open-set object detection. Combines DINO-style detection with a BERT text encoder for025Tao Train Image Classificationnvidia/skillsPyTorch-based TAO image classification. Supports a wide range of backbones (FAN, EfficientNet, ResNet, etc.)027Tao Train Mask Auto Encodernvidia/skillsMasked Auto-Encoder (MAE) for self-supervised pretraining and fine-tuning. Masks random patches and reconstructs021Tao Train Mask Auto Labelnvidia/skillsMAL (Mask Auto-Label) for weakly-supervised segmentation. Produces segmentation masks from minimal annotations014Tao Train Mask Grounding Dinonvidia/skillsMask Grounding DINO for grounded instance segmentation. Extends Grounding DINO with a mask-prediction head for025Tao Train Mask2formernvidia/skillsMask2Former for universal image segmentation (panoptic, instance, and semantic). Transformer-based with025Tao Train Metric Learning Recognitionnvidia/skillsMetric-learning recognition (ml-recog) for fine-grained visual recognition. Learns embeddings for023Tao Train Nvdinov2nvidia/skillsNVDINOv2 for self-supervised visual representation learning. Trains vision transformers via self-distillation019Tao Train Nvpanoptix3dnvidia/skillsNVPanoptix3D for panoptic 3D scene reconstruction from posed RGB images. Produces 3D panoptic segmentation016Tao Train Ocdnetnvidia/skillsOCDNet for scene text detection. Detects arbitrary-oriented text regions in natural images using a029Tao Train Ocrnetnvidia/skillsOCRNet for scene text recognition. Recognizes text content from cropped text-region images and supports CTC029Tao Train Oneformernvidia/skillsOneFormer for universal image segmentation. Unifies panoptic, instance, and semantic segmentation with a025Tao Train Optical Inspectionnvidia/skillsOptical Inspection for defect detection using Siamese networks. Compares image pairs to detect manufacturing052Tao Train Pointpillarsnvidia/skillsPointPillars for 3D object detection from LiDAR point clouds. Encodes point clouds into a pseudo-image via a029Tao Train Pose Classificationnvidia/skillsPose classification using ST-GCN (Spatial Temporal Graph Convolutional Network). Classifies skeleton sequences017Tao Train Reidnvidia/skillsPerson re-identification (ReID). Learns discriminative embeddings to match the same person across different016
Skills, installed in one click
Start building freePut a skill to work
Open any project, search the Skills panel in the chat, and the agent picks it up from there.