所有 Skills
找到 6179 個 Skills
Skills 列表
tao-validate-dataset-format
Run `tao-daft validate` to check NVIDIA TAO DAFT datasets for structure, schema, and cross-reference errors. Do
nvidiatao-train-bevfusion
BEVFusion for multi-sensor 3D object detection. Fuses LiDAR point clouds and camera images in bird's-eye-view
nvidiatao-train-mask-grounding-dino
Mask Grounding DINO for grounded instance segmentation. Extends Grounding DINO with a mask-prediction head for
nvidiatao-train-ocdnet
OCDNet for scene text detection. Detects arbitrary-oriented text regions in natural images using a
nvidiatao-train-oneformer
OneFormer for universal image segmentation. Unifies panoptic, instance, and semantic segmentation with a
nvidiatao-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.
nvidiatao-run-on-slurm
Remote SLURM GPU cluster execution over SSH with sbatch/srun, Pyxis/Enroot containers, and Lustre-backed
nvidiatao-train-segformer
SegFormer for semantic segmentation. Lightweight transformer-based architecture with hierarchical feature
nvidiatao-train-foundation-stereo
Stereo depth estimation using FoundationStereo. Predicts disparity maps from stereo image pairs for 3D
nvidiatao-train-deformable-detr
Deformable DETR for 2D object detection. Uses deformable attention for efficient multi-scale feature processing,
nvidiatilegym-monkey-patch-kernels-to-transformers
Integrate TileGym kernels into Hugging Face `transformers` models by replacing the library's submodule(s) and certain class(es)' implementations, and patching certain class(es)' init/forward/load weight methods prior to instantiating models. Used when the user requires integrating TileGym kernels into `transformers` models.
nvidiatao-train-fast-foundation-stereo
Real-time stereo depth estimation using FastFoundationStereo (FFS), the distilled bp2 commercial variant of
nvidiatao-train-sparse4d
Sparse4D for multi-camera temporal 3D object detection and tracking. Uses sparse queries with deformable
nvidiatao-route-visual-changenet-samples
Routes the weakest VCN samples (output of `tao-analyze-gaps-visual-changenet`) into per-augmentation-module
nvidia
archimate
Create ArchiMate enterprise architecture diagrams using PlantUML stdlib macros. Best for TOGAF viewpoints, layered EA modeling (Business/Application/Technology), motivation analysis, and migration planning.
markdown-viewervega
Create data-driven charts with Vega-Lite (declarative) and Vega (programmatic). Best for statistical visualization of numeric data — bar, line, scatter, heatmap, area, radar charts, and word clouds.
markdown-viewercloud
Create cloud provider architecture diagrams using PlantUML syntax with official AWS, Azure, GCP, and Alibaba Cloud service icons. Best for multi-service cloud topologies and migration blueprints.
markdown-viewerinfocard
Create editorial-style information cards using HTML/CSS in Markdown. Best for knowledge summaries, data highlights, event announcements, and single-topic content cards with magazine-quality typography.
markdown-viewermindmap
Create hierarchical mind maps using PlantUML @startmindmap syntax. Best for brainstorming, topic decomposition, study notes, and decision trees with automatic radial layout, left/right branches, and per-node styling.
markdown-vieweriot
Create IoT architecture diagrams using PlantUML syntax with device and sensor stencil icons. Best for smart home, industrial IoT (IIoT), fleet management, edge computing, and sensor network layouts.
markdown-viewersecurity
Create security architecture diagrams using PlantUML syntax with identity, encryption, firewall, and compliance stencil icons. Best for IAM flows, zero-trust models, encryption pipelines, and threat detection architectures.
markdown-viewer
difit-review
A skill for reviewing a specific diff and showing the findings as comments inside difit (the diff viewer). Use it to review branch diffs, commit diffs, or GitHub PRs, then preload findings or code explanations into difit with `--comment` before launching it for the user.
yoshiko-pgcanvas
Create spatial diagrams with free-positioned nodes using JSON format. Best for concept maps, knowledge graphs, and planning boards requiring precise x/y coordinate control.
markdown-viewerbpmn
Create business process diagrams using PlantUML syntax with BPMN, EIP, and Lean Mapping stencil icons. Best for workflow automation, approval chains, message-based integration patterns, and value stream mapping.
markdown-viewer