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 1,351–1,380 of 3,419

  1. Benchmark Jetson LLM/VLM serving performance across vLLM, llama.cpp, and Ollama with structured JSON output.

    • Open source
    • 4K GitHub stars
    • AI models and LLM tooling
  2. Stand up vLLM or SGLang serving on Jetson, using upstream vLLM on Thor and Orin JetPack 7.2+, and NVIDIA-AI-IOT vLLM on older Orin.

    • Open source
    • 4K GitHub stars
    • AI models and LLM tooling
  3. Measure Jetson DRAM/NvMap usage and verify before/after memory reclamation with live audit data.

    • Open source
    • 4K GitHub stars
    • Knowledge and memory
  4. Reclaim DRAM by disabling unused subsystems across MB1 BCT, MB2 BCT, kernel reserved-memory, and SWIOTLB

    • Open source
    • 4K GitHub stars
    • Knowledge and memory
  5. Pick Jetson-compatible containers, vLLM runtime images, and Jetson AI Lab PyPI indexes; maps Orin SM 8.7 vs Thor SM 11.0 and JetPack-specifi

    • Open source
    • 4K GitHub stars
  6. Use when you need to print Jetson BSP info (L4T version, board configs, rootfs state) from a Linux_for_Tegra root on the host PC

    • Open source
    • 4K GitHub stars
  7. Use when you need to print Jetson device info (module model, L4T version, kernel, OS version, current power mode) from a running Jetson targ

    • Open source
    • 4K GitHub stars
  8. Use to promote overlay files and built artifacts into the staged BSP image

    • Open source
    • 4K GitHub stars
    • Design and media
  9. Entry skill for Jetson / IGX BSP customization

    • Open source
    • 4K GitHub stars
  10. Switch the active Jetson target-platform pointer to an existing profile YAML

    • Open source
    • 4K GitHub stars
  11. Add EAGLE-3 or draft-model speculative decoding to a Jetson vLLM server when TPOT is the bottleneck.

    • Open source
    • 4K GitHub stars
  12. Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both

    • Open source
    • 4K GitHub stars
    • Design and media
  13. Use when measuring Jetson Video Codec SDK or PyNvVideoCodec encode/decode throughput, comparing presets or surfaces, testing codec-worker ca

    • Open source
    • 4K GitHub stars
    • Design and media
  14. Use when Jetson codec, profile, chroma, bit-depth, dimension, engine-count, or operational support must be reconciled from live APIs, authen

    • Open source
    • 4K GitHub stars
    • Design and media
  15. Use when planning, executing, and independently validating Jetson Video Codec SDK or PyNvVideoCodec encode/decode, transcode, segmentation,

    • Open source
    • 4K GitHub stars
    • Design and media
  16. Use when turning a Jetson encoder use case into one surface-neutral recipe with native Video Codec SDK and PyNvVideoCodec projections.

    • Open source
    • 4K GitHub stars
    • Design and media
  17. Use when installing, repairing, reusing, inspecting, or verifying readiness of the native NVIDIA Video Codec SDK or PyNvVideoCodec on Jetson

    • Open source
    • 4K GitHub stars
    • Design and media
  18. Playbook for launching, monitoring, stopping, and debugging NeMo-RL recipes on a Kubernetes cluster via the nrl-k8s CLI

    • Open source
    • 4K GitHub stars
    • Developer tools
  19. Investigate a failing GitHub Actions run or job and create a GitHub issue for the failure.

    • Open source
    • 4K GitHub stars
  20. How to launch distributed Megatron-LM training jobs on a SLURM cluster

    • Open source
    • 4K GitHub stars
  21. Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.

    • Open source
    • 4K GitHub stars
  22. Exports sanitized metadata, parameters, reproducibility details, quality metrics, and optional review artifacts from Medical AI inference ru

    • Open source
    • 4K GitHub stars
    • Health and science
  23. Guide for selecting and configuring distributed training strategies in NeMo AutoModel, including FSDP2, Megatron FSDP, DDP, and parallelism

    • Open source
    • 4K GitHub stars
  24. Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.

    • Open source
    • 4K GitHub stars
  25. Guide for onboarding new model architectures into NeMo AutoModel, including architecture discovery, implementation patterns, registration, a

    • Open source
    • 4K GitHub stars
  26. Create and modify NeMo AutoModel training and evaluation recipes, including YAML structure, builders, and execution flow.

    • Open source
    • 4K GitHub stars
  27. Build, migrate, review, and maintain third-party NVIDIA NeMo Fabric adapters against the public adapter contract

    • Open source
    • 4K GitHub stars
  28. Use this skill when integrating NVIDIA NeMo Fabric into a consumer application, service, evaluation harness, or platform through the typed P

    • Open source
    • 4K GitHub stars