Skip to content

Agent skills for computer vision

27 agent skills for computer vision. Each one shows what it can run and how to install it in Claude Code, Codex, Cursor and other agents.
  1. Trains, evaluates, exports and runs TAO models that classify actions in video clips

    • Open source
    • 4K GitHub stars
    • Computer vision
  2. Trains, evaluates and runs TAO CenterPose models for 6-DoF object pose estimation

    • Open source
    • 4K GitHub stars
    • Computer vision
  3. Trains, evaluates and runs Co-DETR object detectors in NVIDIA TAO containers

    • Open source
    • 4K GitHub stars
    • Computer vision
  4. Trains, evaluates and exports TAO monocular depth models from single RGB images

    • Open source
    • 4K GitHub stars
    • Computer vision
  5. Guides an agent through training, evaluating and running FoundationStereo stereo depth

    • Open source
    • 4K GitHub stars
    • Design and media
  6. Trains, evaluates and exports Grounding DINO text-prompted object detectors via TAO

    • Open source
    • 4K GitHub stars
    • Computer vision
  7. Trains, evaluates, distills and quantizes PyTorch image classifiers inside TAO containers

    • Open source
    • 4K GitHub stars
    • Design and media
  8. Pretrains and fine-tunes masked autoencoder vision backbones with NVIDIA TAO

    • Open source
    • 4K GitHub stars
    • Computer vision
  9. Trains and runs ViT-MAE segmentation models from point or box annotations via Docker

    • Open source
    • 4K GitHub stars
    • Computer vision
  10. Trains and runs NVIDIA TAO Mask Grounding DINO for text-prompted instance segmentation

    • Open source
    • 4K GitHub stars
    • Computer vision
  11. Trains, evaluates and exports Mask2Former segmentation models through NVIDIA TAO

    • Open source
    • 4K GitHub stars
    • Computer vision
  12. Trains vision transformers with self-supervised NVDINOv2 learning on unlabeled images

    • Open source
    • 4K GitHub stars
    • Computer vision
  13. Trains, evaluates and deploys OCDNet text detection models through TAO in Docker

    • Open source
    • 4K GitHub stars
    • Computer vision
  14. Trains, evaluates and exports OCRNet scene text recognition models with TAO

    • Open source
    • 4K GitHub stars
    • Computer vision
  15. Trains, evaluates and exports OneFormer universal segmentation models on TAO with Docker

    • Open source
    • 4K GitHub stars
    • Computer vision
  16. Trains, evaluates, exports and runs ST-GCN models that classify skeleton pose sequences

    • Open source
    • 4K GitHub stars
    • Computer vision
  17. Trains, evaluates, exports and runs person re-identification models in Docker

    • Open source
    • 4K GitHub stars
    • Computer vision
  18. Guides an agent through training, evaluating and exporting TAO SegFormer segmentation

    • Open source
    • 4K GitHub stars
    • Computer vision
  19. Guides an agent through NVIDIA's CDF AnomalyGen pipeline for synthetic defect images

    • Open source
    • 4K GitHub stars
    • Design and media
  20. Guides an agent through setting up and running NVIDIA CDF auto-labeling pipelines

    • Open source
    • 4K GitHub stars
    • Computer vision
  21. Builds validated NVIDIA cdf simulation jobs for PCB AOI synthetic inspection images

    • Open source
    • 4K GitHub stars
    • AI models and LLM tooling
  22. Guides an agent through building NVIDIA DeepStream video analytics pipelines in Python

    • Open source
    • 4K GitHub stars
    • Computer vision
  23. Runs and re-scores FoundationPose 6D pose pipelines on BOP-format datasets

    • Open source
    • 4K GitHub stars
    • Computer vision
  24. Installs and repairs the FoundationPose perception pipeline and builds its depth engines

    • Open source
    • 4K GitHub stars
    • Computer vision
  25. Guides Java code that analyzes images with Azure AI Vision for captions, OCR and objects

    • Open source
    • 3.2K GitHub stars
    • Cloud and infrastructure
  26. Lets an agent caption, tag, detect objects and people, read text and crop images via Azure

    • Open source
    • 3.2K GitHub stars
    • Cloud and infrastructure

See every kind of AI for computer vision: tools, agents, MCP servers and skills.Ranked: the best AI for computer vision.