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 2,011–2,040 of 3,419

  1. Use this skill when the operator is driving the DOCA Socket Relay to bridge a socket-oriented host application onto a BlueField DPU peer wit

    • Open source
    • 4K GitHub stars
  2. Use this skill when the user is invoking `doca_spcx_cc` (the host-side CLI under /opt/mellanox/doca/tools/) to load, parameterize, start, ob

    • Open source
    • 4K GitHub stars
  3. Use this skill when the user builds an NVMe-over-Fabrics storage target on BlueField with DOCA STA — instantiating doca_sta, declaring doca_

    • Open source
    • 4K GitHub stars
  4. Use this skill to read DOCA hardware-counter events from a `doca_dev` through the per-domain Telemetry reader libraries: `doca_telemetry_pcc

    • Open source
    • 4K GitHub stars
  5. Use this skill when the user is doing hands-on DOCA Telemetry Exporter programming on a host where DOCA is installed — defining a doca_telem

    • Open source
    • 4K GitHub stars
  6. Use this skill when the operator is driving the DOCA Telemetry Traceback application to monitor telemetry data locally on a BlueField DPU or

    • Open source
    • 4K GitHub stars
  7. doca_telemetry_utils command line on a host with DOCA: discover the diagnostic-counter schema, translate counter names to binary Data IDs an

    • Open source
    • 4K GitHub stars
  8. Changing DOCA versions safely: upgrading or downgrading the host DOCA packages, refreshing the BlueField BFB, bumping the NGC DOCA container

    • Open source
    • 4K GitHub stars
  9. Host-side DOCA UROM library (doca_urom_*): offload an HPC / UCX / MPI application's remote memory operations (puts, gets, atomics, collectiv

    • Open source
    • 4K GitHub stars
  10. Operate the DOCA UROM Service container on BlueField Arm for remote memory operations (puts, gets, atomics, collectives) enqueued by a paire

    • Open source
    • 4K GitHub stars
    • Design and media
  11. 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
  12. 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
  13. Validate that a Dynamo deployment's NIXL/UCX/NCCL interconnect is ready for disaggregated serving over RDMA/NVLink

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

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

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

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

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

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

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

    • Open source
    • 4K GitHub stars
  21. 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
  22. 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
  23. 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
  24. Implement and validate a new NVIDIA FastGen training method or objective (distillation, consistency, adversarial or fine-tuning variants) fr

    • Open source
    • 4K GitHub stars
  25. 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
  26. 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