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.

Showing 1,831–1,860 of 2,929

  1. Router for NVIDIA NuRec/NRE: USDZ rendering, NCore conversion, 3DGS, gRPC sensor sim, carline adaptation, PhysicalAI HF datasets

    • Open source
    • 4K GitHub stars
  2. Official NVIDIA-authored guidance for navigating PhysicsNeMo — pick the model, datapipe, or example for a SciML/AI4Science task (surrogates,

    • Open source
    • 4K GitHub stars
  3. Official NVIDIA-authored guidance for PhysicsNeMo ShardTensor domain parallelism — integrate domain parallelism into training/inference scri

    • Open source
    • 4K GitHub stars
  4. Use when a user asks to build, optimize, backtest, rebalance, or analyze a stock portfolio with Mean-CVaR, Mean-Variance/SOCP variance caps,

    • Open source
    • 4K GitHub stars
  5. Diagnose and narrowly repair one reproduced NVIDIA PVA operator failure

    • Open source
    • 4K GitHub stars
  6. Install and configure the NVIDIA PVA SDK, NVVPU compiler, and L4T target runtime from the selected installation guide

    • Open source
    • 4K GitHub stars
  7. NVIDIA RAG Blueprint — deploy, configure, troubleshoot, and manage

    • Open source
    • 4K GitHub stars
    • Knowledge and memory
  8. Filesystem RAG benchmarks: corpus/, train.json, evaluate_rag.py (RAGAS quality)

    • Open source
    • 4K GitHub stars
    • Knowledge and memory
  9. Performance benchmarking for a deployed NVIDIA RAG Blueprint server: profiling pass + aiperf load test driven by a single YAML config

    • Open source
    • 4K GitHub stars
    • Knowledge and memory
  10. How to swap the DeepStream CV detection model in the VSS Alerts Blueprint verification (2d_cv) mode - covers ONNX export, custom bbox parser

    • Open source
    • 4K GitHub stars
  11. How to swap the VLM in the VSS Alerts Blueprint — covers RTVI-VLM microservice deployment methods, all three VLM consumers (rtvi-vlm, vlm-as

    • Open source
    • 4K GitHub stars
  12. Mod or remaster a game with RTX Remix - open and edit projects, swap textures and models

    • Open source
    • 4K GitHub stars
  13. Run `tao-daft convert` to convert NVIDIA TAO DAFT datasets between supported formats

    • Open source
    • 4K GitHub stars
  14. CLIP vision-language model for image-text retrieval, zero-shot classification, embedding extraction, ONNX

    • Open source
    • 4K GitHub stars
  15. Cosmos-Embed1 video-text embedding for text-to-video retrieval, video-to-video search, semantic deduplication, and fine-tuning

    • Open source
    • 4K GitHub stars
  16. Fine-tune any HuggingFace CV / VLM / LLM model on local NVIDIA GPUs inside an NGC PyTorch container when no dedicated TAO model skill matche

    • Open source
    • 4K GitHub stars
    • AI models and LLM tooling
  17. Kumo-Anomaly — diffusion-based anomaly detection and fine-tuning for multivariate time series

    • Open source
    • 4K GitHub stars
  18. Kumo-Forecast — transformer-based multivariate time series forecasting with DARR (context-enhanced kNN retrieval), interpretability, and fin

    • Open source
    • 4K GitHub stars
  19. InternVideo2-CLIP L14 (TAO video_clip) for video-text retrieval, zero-shot classification, embedding extraction, LoRA fine-tuning, ONNX expo

    • Open source
    • 4K GitHub stars
    • Design and media
  20. Full PAIDF AnomalyGen pipeline — fine-tune on a new anomaly dataset, generate synthetic anomaly images (SDG), evaluate quality (nn_score), a

    • Open source
    • 4K GitHub stars
  21. "Two-step image grounding pipeline: extracts referring expressions from (image, caption) pairs and grounds them

    • Open source
    • 4K GitHub stars
    • Design and media
  22. "Four-step image referring-expression pipeline: turns images plus KITTI bounding-box labels into region

    • Open source
    • 4K GitHub stars
    • Design and media
  23. The mandatory pre-launch gate and four-verb execution contract for every TAO workflow or action

    • Open source
    • 4K GitHub stars
    • Developer tools
  24. Answer what the TAO Skill Bank plugin can do by generating the response from packaged application, data, model, AutoML, and platform manifes

    • Open source
    • 4K GitHub stars
  25. Integrate a HuggingFace Computer Vision model into the NVIDIA TAO Toolkit ecosystem (tao-core config, tao-pytorch trainer, tao-deploy Tensor

    • Open source
    • 4K GitHub stars
    • AI models and LLM tooling
  26. Run the canonical NVIDIA AOI three-phase training pipeline — Phase 1 AutoML baseline (HPO), Phase 2 DEFT loop (RCA → SDG → mining → plain-tr

    • Open source
    • 4K GitHub stars
  27. Run iterative DINOv3 SSL DEFT data selection and retraining from an unlabeled pool, using GRIT or multi-task weakness and fixed-encoder retr

    • Open source
    • 4K GitHub stars
  28. Start, query, and stop a network-specific TAO inference microservice ({network_arch}-inference-microservice) by delegating container executi

    • Open source
    • 4K GitHub stars
  29. Run a TAO training/evaluation/inference container on an NVIDIA Brev GPU instance

    • Open source
    • 4K GitHub stars
  30. The Docker execution platform for TAO jobs — a local daemon or a remote GPU box via DOCKER_HOST=ssh://user@host

    • Open source
    • 4K GitHub stars
    • Developer tools