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 1,201–1,230 of 3,352

  1. Raw verbs inside DOCA Core (doca-verbs): direct control of QP, CQ, PD, SRQ and address-handle objects through doca_verbs_context and doca_ve

    • Open source
    • 4K GitHub stars
  2. DOCA version handling: detect the installed release and validate the four-way match across pkg-config doca-common, applications/VERSION, doc

    • Open source
    • 4K GitHub stars
  3. Validate that a Dynamo deployment's NIXL/UCX/NCCL interconnect is ready for disaggregated serving over RDMA/NVLink

    • Open source
    • 4K GitHub stars
  4. Select, validate, patch, and deploy existing NVIDIA Dynamo Kubernetes recipes

    • Open source
    • 4K GitHub stars
  5. Start or patch Dynamo router modes and run router endpoint smoke checks

    • Open source
    • 4K GitHub stars
  6. Create and validate Earth2Studio data source wrappers (DataSource, ForecastSource, DataFrameSource, ForecastFrameSource) from remote stores

    • Open source
    • 4K GitHub stars
  7. Create Earth2Studio diagnostic model wrappers for single-step data transformations, including simple derived diagnostics, packaged AutoModel

    • Open source
    • 4K GitHub stars
  8. Fetch weather/climate data via Earth2Studio data sources for specific variables and times

    • Open source
    • 4K GitHub stars
  9. Find Earth2Studio models, data sources, and examples for a weather/climate use case

    • Open source
    • 4K GitHub stars
  10. Guide installing Earth2Studio via uv or pip, selecting model extras, and configuring the environment

    • Open source
    • 4K GitHub stars
  11. Captures what an AI agent is supposed to do — its purpose, boundaries, and success criteria — as a durable snapshot for anyone building, eva

    • Open source
    • 4K GitHub stars
  12. Entry point for an AI agent's ETHOS.md: a durable snapshot of what the agent is for, what it must not do, and what success looks like

    • Open source
    • 4K GitHub stars
  13. Writes an AI agent's ethos.md — a durable snapshot of its purpose, intended behavior, boundaries, and success criteria — from the answers ga

    • Open source
    • 4K GitHub stars
  14. Implement and validate a new NVIDIA FastGen training method or objective (distillation, consistency, adversarial or fine-tuning variants) fr

    • Open source
    • 4K GitHub stars
  15. Extend NVIDIA FastGen to a new generated or conditioning modality beyond the existing image, video, audio, camera and text paths: representa

    • Open source
    • 4K GitHub stars
    • Design and media
  16. Integrate a new diffusion or flow model, or a task variant such as I2V, editing or causal generation, into NVIDIA FastGen as a FastGenNetwor

    • Open source
    • 4K GitHub stars
  17. Create or adapt an NVIDIA FastGen experiment config for a network, task, dataset and training objective, and pick a distillation method when

    • Open source
    • 4K GitHub stars
  18. Prepare, register or repair datasets for NVIDIA FastGen loaders: class-conditional ZIPs, WebDataset shards of images, prompts, latents, vide

    • Open source
    • 4K GitHub stars
    • Design and media
  19. Implement, refactor or review NVIDIA FastGen library code using its shared design, formatting, documentation and testing conventions

    • Open source
    • 4K GitHub stars
  20. Generate and inspect NVIDIA FastGen teacher or distilled-student outputs with the inference scripts or ComfyUI nodes: config, checkpoint, pr

    • Open source
    • 4K GitHub stars
  21. Resolve the execution context for an NVIDIA FastGen command: checkout and interpreter, config path and override syntax, output/cache/data ro

    • Open source
    • 4K GitHub stars
  22. Set up or repair an NVIDIA FastGen environment for a chosen task: Docker or Conda installation, credentials and model access, weight and dat

    • Open source
    • 4K GitHub stars
  23. Run, resume or troubleshoot NVIDIA FastGen training: SFT or distillation with train.py, bounded smoke tests, distributed launches, checkpoin

    • Open source
    • 4K GitHub stars
  24. Validate NVIDIA FastGen integrations and training quality: numerical parity against reference implementations, seeded side-by-side media, gr

    • Open source
    • 4K GitHub stars
  25. Adapt BOP datasets, run the FoundationPose perception pipeline with TAO depth, and evaluate or re-score pose results

    • Open source
    • 4K GitHub stars
  26. Install or repair the FoundationPose perception pipeline and build its FoundationStereo TensorRT engines

    • Open source
    • 4K GitHub stars
  27. Use this skill to check or change this machine's NVIDIA display and GPU settings, such as resolution, refresh rate, V-Sync, G-SYNC, brightne

    • Open source
    • 4K GitHub stars