Skip to content

Instruction-only agent skills

2,929 instruction-only agent skills, out of 3,419 agent skills listed. Popular ones include Rea analysis optimization, Rea changelog update and Rea ci tests audit. These skills contain instructions and reference files but no scripts, so they run no code of their own. Each one lists the tools it asks for and how to install it in Claude Code, Codex, Cursor and other agents.
  1. Guides swapping the VLM behind NVIDIA's VSS Alerts Blueprint and verifying the change

    • Open source
    • 4K GitHub stars
    • Developer tools
  2. Lets your agent open, edit and save RTX Remix mod projects through the Toolkit's MCP

    • Open source
    • 4K GitHub stars
    • Developer tools
  3. Converts NVIDIA TAO DAFT datasets between supported formats via the tao-daft CLI

    • Open source
    • 4K GitHub stars
    • Developer tools
  4. Fine-tunes and runs NVIDIA CLIP models for image-text retrieval and zero-shot

    • Open source
    • 4K GitHub stars
    • AI models and LLM tooling
  5. Runs Cosmos-Embed1 video-text embedding for search, dedup and fine-tuning in Docker

    • Open source
    • 4K GitHub stars
    • AI models and LLM tooling
  6. Fine-tunes HuggingFace vision, VLM and LLM models in an NVIDIA GPU container

    • Open source
    • 4K GitHub stars
    • AI models and LLM tooling
  7. Detects anomalies in multivariate time series and fine-tunes a diffusion model on your

    • Open source
    • 4K GitHub stars
    • Analytics and data
  8. Runs Kumo-Forecast time series forecasting, DARR retrieval blending and fine-tuning

    • Open source
    • 4K GitHub stars
    • AI models and LLM tooling
  9. Runs InternVideo2-CLIP video-text retrieval, fine-tuning, ONNX export and TensorRT deploy

    • Open source
    • 4K GitHub stars
    • Design and media
  10. Fine-tunes and runs the PAIDF AnomalyGen pipeline to generate synthetic anomaly images

    • Open source
    • 4K GitHub stars
    • AI models and LLM tooling
  11. Auto-labels image-caption pairs with referring expressions and pixel bounding boxes

    • Open source
    • 4K GitHub stars
    • Design and media
  12. Gates TAO model launches behind preflight checks, image confirmation and a review step

    • Open source
    • 4K GitHub stars
    • Developer tools
  13. Lists what the TAO Skill Bank plugin can do, including models, workflows and AutoML

    • Open source
    • 4K GitHub stars
    • AI models and LLM tooling
  14. Guides an agent to port a HuggingFace vision model into the NVIDIA TAO Toolkit

    • Open source
    • 4K GitHub stars
    • AI models and LLM tooling
  15. Chains AutoML tuning, a DEFT data-improvement loop and a final AutoML pass for PCB AOI

    • Open source
    • 4K GitHub stars
    • AI models and LLM tooling
  16. Runs iterative DINOv3 self-supervised data selection and retraining from an unlabeled pool

    • Open source
    • 4K GitHub stars
    • AI models and LLM tooling
  17. Runs TAO model checkpoints as local inference microservices with start, query and stop

    • Open source
    • 4K GitHub stars
    • AI models and LLM tooling
  18. Runs TAO training, evaluation and inference containers on Brev GPU instances

    • Open source
    • 4K GitHub stars
    • Cloud and infrastructure
  19. Runs NVIDIA TAO container jobs on a local or SSH-reached Docker host with GPUs

    • Open source
    • 4K GitHub stars
    • Developer tools
  20. Runs TAO GPU jobs on a remote SLURM cluster over SSH with sbatch and Pyxis containers

    • Open source
    • 4K GitHub stars
    • Cloud and infrastructure
  21. Trains, evaluates, exports and runs TAO models that classify actions in video clips

    • Open source
    • 4K GitHub stars
    • Computer vision
  22. Guides an agent through training, evaluating and running BEVFusion LiDAR-camera 3D

    • Open source
    • 4K GitHub stars
    • Design and media
  23. Trains, evaluates and runs TAO CenterPose models for 6-DoF object pose estimation

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

    • Open source
    • 4K GitHub stars
    • Computer vision
  25. Trains, evaluates, exports and runs NVIDIA TAO Deformable DETR object detectors

    • Open source
    • 4K GitHub stars
    • AI models and LLM tooling
  26. Trains, evaluates and exports TAO monocular depth models from single RGB images

    • Open source
    • 4K GitHub stars
    • Computer vision
  27. Trains, evaluates, exports and runs DINO 2D object detectors via TAO in Docker

    • Open source
    • 4K GitHub stars
    • AI models and LLM tooling
  28. Continues self-supervised DINOv3 pre-training on unlabeled images to adapt vision

    • Open source
    • 4K GitHub stars
    • AI models and LLM tooling