Skip to content

Agent skills

Agent skills are folders of instructions and scripts that teach Claude Code, Codex, Cursor and other agents a task. Each one lists what it can run and how to install it.
  1. Choose a physics engine and integration for robot learning, manipulation, assembly, differentiable optimization, or other Physical AI simula

    • Open source
    • 4K GitHub stars
  2. Use when running video data augmentation and auto-labeling workflows on OSMO: flow selection, preflight, submit-time interpolation, monitori

    • Open source
    • 4K GitHub stars
    • Design and media
  3. Check whether a host is ready for requested NVIDIA PVA work

    • Open source
    • 4K GitHub stars
  4. Generate, change, or repair a complete vectorized NVIDIA PVA operator from a validated pva-spec handoff

    • Open source
    • 4K GitHub stars
  5. Create and validate an NVIDIA PVA operator specification, test matrix, evidence manifest, and deterministic OpGen handoff

    • Open source
    • 4K GitHub stars
  6. Audit GPU quota fairness across a Run:ai cluster — find which projects are starved and which are borrowing over their deserved quota in each

    • Open source
    • 4K GitHub stars
  7. Use to diagnose failed, crashed, stopped, OOMKilled, CrashLoopBackOff, ImagePullBackOff, init, mount, node, or policy-terminated Run:ai work

    • Open source
    • 4K GitHub stars
  8. Point-in-time Run:ai cluster and node-health check: a HEALTHY, DEGRADED, or STUCK verdict per node pool with the dominant blocker — NotReady

    • Open source
    • 4K GitHub stars
    • Health and science
  9. GPU efficiency check for a Run:ai cluster: are the GPUs that projects, departments, and node pools hold actually computing? Classifies holde

    • Open source
    • 4K GitHub stars
  10. Use only to generate or update a governance skill card for a specified existing agent skill directory

    • Open source
    • 4K GitHub stars
  11. Performs deep Root Cause Analysis (RCA) on NVIDIA TAO Visual ChangeNet classification experiments with

    • Open source
    • 4K GitHub stars
  12. Run TAO Data Services KPI analysis for object detection, comparing inference annotations against ground truth to compute per-class TP/FP/FN/

    • Open source
    • 4K GitHub stars
  13. Run TAO Data Services object-detection gap analysis from ground-truth and inference annotations

    • Open source
    • 4K GitHub stars
  14. Performs gap analysis on NVIDIA TAO VCN Classify (Visual Component Net) experiments by invoking the pinned TAO data-services container direc

    • Open source
    • 4K GitHub stars
  15. Extract false-positive and false-negative gaps from VLM binary-classification-question (BCQ, yes/no) predictions.

    • Open source
    • 4K GitHub stars
  16. The contract home for TAO's SDK-free execution pipeline — authoritative JSON Schemas for the four typed artifacts (spec-bundle, job-record,

    • Open source
    • 4K GitHub stars
  17. The data-mover for TAO jobs — decides the storage tier (A pre-positioned mount with zero fetch / B volume-from-S3 / C ephemeral in-compute f

    • Open source
    • 4K GitHub stars
    • Developer tools
  18. Validate a user AnomalyGenNext dataset and recipe, freeze its validation set, and prepare a canonical texture fine-tuning recipe

    • Open source
    • 4K GitHub stars
  19. Shared Cosmos3 frontend that explicitly routes Cosmos Framework and Cosmos-RL, validates runtime model/video-dataset/SLURM inputs, consumes

    • Open source
    • 4K GitHub stars
    • Design and media
  20. Run TAO Data Services image embedding to turn a parquet of image filepaths into an embedding parquet using CLIP, SigLIP, or a TAO checkpoint

    • Open source
    • 4K GitHub stars
    • Design and media
  21. Run AnomalyGenNext 1.1 inference from a native testcase or a prepared generation plan, then publish validated fine-grained and binary COCO l

    • Open source
    • 4K GitHub stars
  22. Multi-step video annotation pipeline that turns raw videos into Chain-of-Thought training data — multi-level captions, structured descriptio

    • Open source
    • 4K GitHub stars
    • Design and media
  23. Runs the DEFT embed-then-mine workflow for VCN AOI iterations — embeds the gap-analysis target parquet, embeds a source pool, and mines near

    • Open source
    • 4K GitHub stars
    • Design and media
  24. Run TAO Data Services TMM nearest-neighbor mining from embedding parquet files

    • Open source
    • 4K GitHub stars
  25. Run TAO Data Services TMM unique-neighbor matching mining from embedding parquet files for object detection workflows

    • Open source
    • 4K GitHub stars
    • Design and media
  26. Prepare normalized object-detection false negatives, source masks, and clean-image embedding inputs for AnomalyGenNext

    • Open source
    • 4K GitHub stars
  27. Run container-backed AutoML / hyperparameter optimization (HPO) for NVIDIA TAO networks using AutoMLRunner

    • Open source
    • 4K GitHub stars