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.
  1. Guides choosing a physics engine and Newton/ovnewton integration for Physical AI

    • Open source
    • 4K GitHub stars
    • Developer tools
  2. Checks whether a host and Jetson board are ready for NVIDIA PVA development work

    • Open source
    • 4K GitHub stars
    • Developer tools
  3. Generates, changes, or repairs vectorized NVIDIA PVA operators from a validated spec

    • Open source
    • 4K GitHub stars
    • Developer tools
  4. Writes a validated NVIDIA PVA operator spec, test matrix and OpGen handoff

    • Open source
    • 4K GitHub stars
    • Developer tools
  5. Audits GPU quota fairness in a Run:ai cluster, finding starved and over-borrowing projects

    • Open source
    • 4K GitHub stars
    • Cloud and infrastructure
  6. Diagnoses why a Run:ai workload failed, crashed or stopped, with cited evidence

    • Open source
    • 4K GitHub stars
    • Cloud and infrastructure
  7. Finds Run:ai GPUs held by projects or departments that sit idle or underused

    • Open source
    • 4K GitHub stars
    • Cloud and infrastructure
  8. Drafts a governance skill card for an existing agent skill directory

    • Open source
    • 4K GitHub stars
    • Developer tools
  9. Scores object detection predictions against ground truth to produce per-class mAP metrics

    • Open source
    • 4K GitHub stars
    • Computer vision
  10. Finds object-detection images where a model's predictions miss ground truth per class

    • Open source
    • 4K GitHub stars
    • Computer vision
  11. Validates TAO job artifacts: spec bundles, job records, results layout and best_rec

    • Open source
    • 4K GitHub stars
    • Developer tools
  12. Moves TAO job data to and from compute containers, choosing the storage tier first

    • Open source
    • 4K GitHub stars
    • Developer tools
  13. Prepares and validates a dataset and recipe for fine-tuning AnomalyGenNext LoRA weights

    • Open source
    • 4K GitHub stars
    • AI models and LLM tooling
  14. Guides fine-tuning of NVIDIA Cosmos3 reasoning models with Cosmos Framework or Cosmos-RL

    • Open source
    • 4K GitHub stars
    • Design and media
  15. Computes image embeddings from a parquet of file paths using CLIP, SigLIP or TAO

    • Open source
    • 4K GitHub stars
    • Design and media
  16. Generates synthetic object-detection defect images with COCO labels via AnomalyGenNext

    • Open source
    • 4K GitHub stars
    • Design and media
  17. Mines look-alike source images for VCN augmentation via DEFT embedding

    • Open source
    • 4K GitHub stars
    • Design and media
  18. Mines nearest-neighbor source samples for target embeddings using TAO Data Services

    • Open source
    • 4K GitHub stars
    • Analytics and data
  19. Mines unique source images closest to target samples for object detection datasets

    • Open source
    • 4K GitHub stars
    • Design and media
  20. Prepares false-negative masks and clean-image inputs for AnomalyGenNext generation runs

    • Open source
    • 4K GitHub stars
    • AI models and LLM tooling
  21. Runs container-backed hyperparameter search for NVIDIA TAO networks via AutoMLRunner

    • Open source
    • 4K GitHub stars
    • AI models and LLM tooling
  22. Runs an iterative NVIDIA TAO AOI loop that improves PCB defect-inspection models

    • Open source
    • 4K GitHub stars
    • Computer vision
  23. Runs an iterative DEFT loop that improves Cosmos3 bare OK/NG AOI inspection accuracy

    • Open source
    • 4K GitHub stars
    • AI models and LLM tooling
  24. Runs an iterative mining-based DEFT loop to improve Cosmos Reason traffic-video

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