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 2,191–2,220 of 3,419

  1. Use for agent-assisted Auto-FL optimization of an existing NVFLARE job in simulation, POC, or production

    • Open source
    • 4K GitHub stars
  2. Generate a reproducible final report, literature-outcome synthesis, JSON summary, and refreshed progress plot for a stopped or interrupted N

    • Open source
    • 4K GitHub stars
  3. Convert existing Hugging Face Transformers Trainer or TRL SFTTrainer training code into an NVFLARE federated job using flare.patch(trainer),

    • Open source
    • 4K GitHub stars
    • AI models and LLM tooling
  4. Convert existing PyTorch Lightning training code into an NVFLARE federated job using the Lightning Client API patch, local validation, and j

    • Open source
    • 4K GitHub stars
  5. Convert existing plain or manual PyTorch training code into an NVFLARE federated job using Client API model exchange, local validation, and

    • Open source
    • 4K GitHub stars
  6. Use when the user asks why a reported NVFLARE job failure signal occurred: the job failed, stalled, timed out, lost clients, ended with EXEC

    • Open source
    • 4K GitHub stars
  7. Compute federated statistics over tabular data (count, sum, mean, stddev, var, histogram, quantile, noise-protected min/max) and image data

    • Open source
    • 4K GitHub stars
  8. Route open-ended NVFLARE advice and only conversion requests whose preliminary source inspection reports unresolved or conflicting ownership

    • Open source
    • 4K GitHub stars
  9. Internal NVFLARE conversion references and templates

    • Open source
    • 4K GitHub stars
  10. NVIDIA App MCP: drivers, games, laptops, overlay

    • Open source
    • 4K GitHub stars
  11. Use when controlling NVIDIA Broadcast through MCP to apply effects, process local media, select devices, or change camera resolution, or whe

    • Open source
    • 4K GitHub stars
  12. Query Auto Ontology and validate generated SQL, rows, and answers

    • Open source
    • 4K GitHub stars
  13. Collect and package NVSHMEM put/get bandwidth, latency, and other perftest results with system and topology evidence for performance sanity

    • Open source
    • 4K GitHub stars
  14. Find version-aware official NVSHMEM and NVSHMEM4Py documentation for releases, installation, APIs, runtime settings, transports, containers,

    • Open source
    • 4K GitHub stars
  15. Prepare or review NVSHMEM CUDA kernels for TMA SMEM registration and direct-SMEM transfers

    • Open source
    • 4K GitHub stars
  16. Use when NVSHMEM beginners want a tutorial-style overview on assessment, mental models, first C/C++ or Python NVSHMEM programs, compilation,

    • Open source
    • 4K GitHub stars
  17. Plan and validate NVSHMEM and NVSHMEM4Py installations

    • Open source
    • 4K GitHub stars
  18. Diagnose NVSHMEM runtime failures and prepare bug reports for launch, crashes, hangs, correctness, transport, or topology issues.

    • Open source
    • 4K GitHub stars
  19. Route NVSHMEM tuning to data collection, remote transport, NIC-to-PE mapping, or TMA

    • Open source
    • 4K GitHub stars
  20. Omniverse Content Services, also discoverable as Omniverse Content Workspace or USD Content Workspace

    • Open source
    • 4K GitHub stars
  21. Use as the top-level router for Omniverse Realtime Viewer USD apps, XR delivery, SPG GPU processing, stylized rendering, and focused viewer

    • Open source
    • 4K GitHub stars
  22. Diagnose and optimize USD stages for slow loading, high memory, low FPS or validation; preserve asset boundaries and reuse shared definition

    • Open source
    • 4K GitHub stars
  23. Connect the Newton physics engine to an Omniverse simulation or ovstage with ovnewton

    • Open source
    • 4K GitHub stars
  24. Prepare and run PAIDF Cosmos Predict video generation for DEFT media samples.

    • Open source
    • 4K GitHub stars
  25. Use when the user wants to orchestrate defect image generation with NVIDIA Cosmos AnomalyGen (Cosmos-Predict2-derived) on OSMO for PCBA, met

    • Open source
    • 4K GitHub stars
    • Design and media