Skip to content

Agent skills for AI models and LLM tooling

227 agent skills that call other AI models, manage prompts and orchestrate LLM workflows. Each one shows what it can run and how to install it in Claude Code, Codex, Cursor and other agents.
  1. Guides an agent through enabling Megatron FSDP sharded training in Megatron-Bridge

    • Open source
    • 4K GitHub stars
    • AI models and LLM tooling
  2. Guides an agent through reducing peak GPU memory in Megatron Bridge training runs

    • Open source
    • 4K GitHub stars
    • Knowledge and memory
  3. Guides long-context MoE training in Megatron Bridge: CP sizing, recompute and dispatcher

    • Open source
    • 4K GitHub stars
    • AI models and LLM tooling
  4. Guidance for choosing FSDP or 3D parallelism when training MoE vision-language models

    • Open source
    • 4K GitHub stars
    • AI models and LLM tooling
  5. Guides Megatron-Bridge sequence packing and long-context training setup and validation

    • Open source
    • 4K GitHub stars
    • AI models and LLM tooling
  6. Picks Megatron Bridge training recipes and resizes parallelism for your GPU allocation

    • Open source
    • 4K GitHub stars
    • AI models and LLM tooling
  7. Runs iterative NeMo-RL experiments with git branches and TSV logs as a research ledger

    • Open source
    • 4K GitHub stars
    • Developer tools
  8. Guides an agent through improving NVIDIA Riva/NeMo speech recognition for a domain

    • Open source
    • 4K GitHub stars
    • AI models and LLM tooling
  9. Plans and configures chained Nemotron customization steps like SFT, RL, and evaluation

    • Open source
    • 4K GitHub stars
    • AI models and LLM tooling
  10. Guides an agent through NVIDIA Nemotron embed and rerank retrieval recipes safely

    • Open source
    • 4K GitHub stars
    • Knowledge and memory
  11. Guides an agent through deploying and testing NVIDIA Nemotron Speech ASR, TTS and NMT

    • Open source
    • 4K GitHub stars
    • Design and media
  12. Builds and fixes NVIDIA speech-to-speech voice agents on Pipecat or LiveKit

    • Open source
    • 4K GitHub stars
    • Design and media
  13. Finetunes NV-Segment-CT VISTA3D on your CT NIfTI image and label datasets

    • Open source
    • 4K GitHub stars
    • Health and science
  14. Runs a guarded agent loop that tunes an existing NVFLARE federated job for a metric

    • Open source
    • 4K GitHub stars
    • AI models and LLM tooling
  15. Builds a final report and JSON summary for a stopped NVFLARE Auto-FL campaign

    • Open source
    • 4K GitHub stars
    • AI models and LLM tooling
  16. Converts Hugging Face Trainer or TRL SFTTrainer code into an NVFLARE federated job

    • Open source
    • 4K GitHub stars
    • AI models and LLM tooling
  17. Converts existing PyTorch Lightning training code into a federated NVFLARE job

    • Open source
    • 4K GitHub stars
    • AI models and LLM tooling
  18. Converts plain PyTorch training code into a federated NVFLARE job

    • Open source
    • 4K GitHub stars
    • AI models and LLM tooling
  19. Shared NVFLARE reference files and templates that other NVFLARE skills load on demand

    • Open source
    • 4K GitHub stars
    • AI models and LLM tooling
  20. Runs NVIDIA PAIDF Cosmos Predict to generate videos from a media sample list

    • Open source
    • 4K GitHub stars
    • AI models and LLM tooling
  21. Benchmarks a RAG pipeline's answer quality on local corpus and train.json datasets

    • Open source
    • 4K GitHub stars
    • Knowledge and memory
  22. Finds false-positive and false-negative yes/no VLM predictions for root-cause analysis

    • Open source
    • 4K GitHub stars
    • AI models and LLM tooling
  23. Prepares and validates a dataset and recipe for fine-tuning AnomalyGenNext LoRA weights

    • Open source
    • 4K GitHub stars
    • AI models and LLM tooling
  24. Fine-tunes and runs NVIDIA CLIP models for image-text retrieval and zero-shot

    • Open source
    • 4K GitHub stars
    • AI models and LLM tooling
  25. Runs Cosmos-Embed1 video-text embedding for search, dedup and fine-tuning in Docker

    • Open source
    • 4K GitHub stars
    • AI models and LLM tooling

See every kind of AI for ai models and llm tooling: tools, agents, MCP servers and skills.Ranked: the best AI for ai models and llm tooling.