Skip to content

Agent skills for Codex

3,289 agent skills for Codex, out of 3,419 agent skills listed. Popular ones include Rea analysis optimization, Rea changelog update and Rea ci tests audit. Codex reads the SKILL.md folder format, so each skill here can be copied into ~/.agents/skills. Each one lists what it can run and the steps to install it.

Showing 1,021–1,050 of 3,289

  1. Guides an agent through training, evaluating and running FoundationStereo stereo depth

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

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

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

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

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

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

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

    • Open source
    • 4K GitHub stars
    • Computer vision
  9. Trains, evaluates, exports and runs NVPanoptix3D models for 3D panoptic scene segmentation

    • Open source
    • 4K GitHub stars
    • Design and media
  10. Trains, evaluates and deploys OCDNet text detection models through TAO in Docker

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

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

    • Open source
    • 4K GitHub stars
    • Computer vision
  13. Trains, evaluates and exports Siamese models that flag defects in AOI image pairs

    • Open source
    • 4K GitHub stars
    • Health and science
  14. Trains, evaluates and exports PointPillars 3D LiDAR object detection models with TAO

    • Open source
    • 4K GitHub stars
    • Design and media
  15. Trains, evaluates, exports and runs ST-GCN models that classify skeleton pose sequences

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

    • Open source
    • 4K GitHub stars
    • Computer vision
  17. Trains, distills, quantizes and runs RT-DETR real-time object detection models

    • Open source
    • 4K GitHub stars
    • AI models and LLM tooling
  18. Runs a standard TAO train, evaluate and export sequence without AutoML loops

    • Open source
    • 4K GitHub stars
    • AI models and LLM tooling
  19. Trains, evaluates and runs Visual ChangeNet models for PCB and AOI defect inspection

    • Open source
    • 4K GitHub stars
    • Computer vision
  20. Runs tao-daft validate to check NVIDIA TAO DAFT datasets for structure and schema errors

    • Open source
    • 4K GitHub stars
    • Developer tools
  21. Ports a paper's CV training recipe to your own dataset and checks for silent bugs

    • Open source
    • 4K GitHub stars
    • Computer vision
  22. Guides an agent through adding a new cuTile GPU kernel operator to TileGym

    • Open source
    • 4K GitHub stars
    • Developer tools
  23. Adds autotuning with cached config selection to CuTile GPU kernels

    • Open source
    • 4K GitHub stars
    • Developer tools
  24. Guides an agent to write, debug and validate cuTile GPU kernels in Python

    • Open source
    • 4K GitHub stars
    • Developer tools
  25. Composes and deploys an NVIDIA VSS vision stack with captioning, detection, search

    • Open source
    • 4K GitHub stars
    • Design and media