# skills: a set by nvidia

The nvidia/skills repository on GitHub: 312 cards with a description and an install command. Inside: 311 skills and 1 plugin. They install into Claude Code, Codex and Cursor.

312 cards · page 1 of 8

- HTML: https://affpapa.org/en/nevibecode/by/nvidia/skills
- Instructions for agents: https://affpapa.org/en/nevibecode/agents.md

- [rag-blueprint](https://affpapa.org/en/nevibecode/skills/rag-blueprint.md) — skill · NVIDIA RAG · Claude Code, Codex, Cursor +5 · 3500 installs — This skill deploys, configures, troubleshoots, and manages NVIDIA RAG Blueprint.
- [accelerated-computing-cudf](https://affpapa.org/en/nevibecode/skills/accelerated-computing-cudf.md) — skill · NVIDIA · Claude Code, Codex, Cursor +5 · 3200 installs — accelerated-computing-cudf is a Claude Code skill that guides cuDF and dask-cuDF use to move pandas-style data work to GPUs and check result semantics.
- [cuopt-developer](https://affpapa.org/en/nevibecode/skills/cuopt-developer.md) — skill · NVIDIA cuOpt Team · Claude Code, Codex, Cursor +5 · 2800 installs — cuopt-developer guides AI coding assistants through modifying and building NVIDIA cuOpt internals, covering C++/CUDA and Python bindings.
- [dynamo-recipe-runner](https://affpapa.org/en/nevibecode/skills/dynamo-recipe-runner.md) — skill · Dan Gil · Claude Code, Codex, Cursor +5 · 2600 installs — dynamo-recipe-runner is a Claude Code skill that finds, validates, patches, and deploys NVIDIA Dynamo Kubernetes recipes for model serving with vLLM or SGLang.
- [cuopt-install](https://affpapa.org/en/nevibecode/skills/cuopt-install.md) — skill · NVIDIA cuOpt Team · Claude Code, Codex, Cursor +5 · 2600 installs — cuopt-install installs NVIDIA cuOpt for Python, C, or as a REST server via pip, conda, or Docker, then verifies the setup.
- [data-designer](https://affpapa.org/en/nevibecode/skills/data-designer.md) — skill · NVIDIA · Claude Code, Codex, Cursor +5 · 2600 installs — The data-designer skill builds synthetic datasets and Python generation pipelines from a plain-language brief.
- [deepstream-dev](https://affpapa.org/en/nevibecode/skills/deepstream-dev.md) — skill · NVIDIA CORPORATION · Claude Code, Codex, Cursor +5 · 2500 installs — deepstream-dev teaches the agent to write NVIDIA DeepStream SDK code in Python: GStreamer pipelines, TensorRT inference, tracking and broker output.
- [nemo-retriever](https://affpapa.org/en/nevibecode/skills/nemo-retriever.md) — skill · NVIDIA · Claude Code, Codex, Cursor +5 · 2500 installs — Indexes and queries document collections using the NeMo Retriever 26.8.1 CLI.
- [rag-eval](https://affpapa.org/en/nevibecode/skills/rag-eval.md) — skill · NVIDIA RAG · Claude Code, Codex, Cursor +5 · 2500 installs — rag-eval evaluates filesystem RAG datasets built around corpus/ and train.json.
- [cudaq-guide](https://affpapa.org/en/nevibecode/skills/cudaq-guide.md) — skill · CUDA-Q Team · Claude Code, Codex, Cursor +5 · 2500 installs — cudaq-guide walks you through CUDA-Q installation, simulation targets, QPU access and Python kernel authoring.
- [omniverse-usd-performance-tuning](https://affpapa.org/en/nevibecode/skills/nvidia-omniverse-omniverse-usd-performance-tuning.md) — skill · NVIDIA Omniverse · Claude Code, Codex, Cursor +5 · 2400 installs — omniverse-usd-performance-tuning is a Claude Code skill that diagnoses and optimizes USD stages with slow loading, high memory use, low FPS or validation failures.
- [omniverse-realtime-viewer](https://affpapa.org/en/nevibecode/skills/nvidia-omniverse-omniverse-realtime-viewer.md) — skill · NVIDIA Omniverse · Claude Code, Codex, Cursor +5 · 2300 installs — The omniverse-realtime-viewer Claude Code skill routes work on Omniverse USD viewer apps to the relevant architecture and implementation references.
- [skill-card-generator](https://affpapa.org/en/nevibecode/skills/skill-card-generator.md) — skill · Trustworthy AI Projects · Claude Code, Codex, Cursor +5 · 2300 installs — skill-card-generator turns a skill folder that already exists into a draft governance card: it reads the files, writes a context, renders markdown and checks that review markers are gone.
- [cuopt-routing-api-python](https://affpapa.org/en/nevibecode/skills/cuopt-routing-api-python.md) — skill · NVIDIA cuOpt Team · Claude Code, Codex, Cursor +5 · 2300 installs — cuopt-routing-api-python — a skill that walks your agent through vehicle routing with the cuOpt Python API: TSP, VRP and pickup-delivery.
- [deepstream-import-vision-model](https://affpapa.org/en/nevibecode/skills/deepstream-import-vision-model.md) — skill · Tushar Khinvasara · Claude Code, Codex, Cursor +5 · 2300 installs — The deepstream-import-vision-model skill takes an object-detection model from HuggingFace or NGC through a full NVIDIA DeepStream pipeline: ONNX, TRT engine, bbox parser, benchmark, PDF report.
- [cuopt-numerical-optimization-formulation](https://affpapa.org/en/nevibecode/skills/cuopt-numerical-optimization-formulation.md) — skill · NVIDIA cuOpt Team · Claude Code, Codex, Cursor +5 · 2200 installs — cuopt-numerical-optimization-formulation turns a written problem into a clean LP, MILP or QP formulation: variables, constraints, objective.
- [nemotron-customize](https://affpapa.org/en/nevibecode/skills/nemotron-customize.md) — skill · NVIDIA Nemotron Team · Claude Code, Codex, Cursor +5 · 2200 installs — nemotron-customize is a Claude Code skill that plans Nemotron customization workflows.
- [physical-ai-neural-reconstruction](https://affpapa.org/en/nevibecode/skills/nvidia-physical-ai-physical-ai-neural-reconstruction.md) — skill · NVIDIA Physical AI · Claude Code, Codex, Cursor +5 · 2200 installs — The physical-ai-neural-reconstruction skill routes NVIDIA NuRec and NRE requests to the right companion skill for datasets, conversion, training, or rendering.
- [cuopt-server-api-python](https://affpapa.org/en/nevibecode/skills/cuopt-server-api-python.md) — skill · NVIDIA cuOpt Team · Claude Code, Codex, Cursor +5 · 2200 installs — cuopt-server-api-python deploys the NVIDIA cuOpt REST server and guides client requests via Python or curl.
- [rag-perf](https://affpapa.org/en/nevibecode/skills/rag-perf.md) — skill · NVIDIA RAG · Claude Code, Codex, Cursor +5 · 2200 installs — rag-perf runs a profiling pass and an aiperf load test against a deployed NVIDIA RAG Blueprint server, all driven by one YAML config.
- [nemotron-retrieval-recipes](https://affpapa.org/en/nevibecode/skills/nemotron-retrieval-recipes.md) — skill · NVIDIA Nemotron Team · Claude Code, Codex, Cursor +5 · 2100 installs — nemotron-retrieval-recipes helps plan, debug, tune, export, and deploy public NVIDIA Nemotron embedding and reranking retrieval recipes.
- [nemo-rl-session-memory](https://affpapa.org/en/nevibecode/skills/nemo-rl-session-memory.md) — skill · NVIDIA · Claude Code, Codex, Cursor +5 · 2100 installs — nemo-rl-session-memory keeps a durable, human-readable record of a working session under session/, so another agent can resume after a disconnect or a VS Code restart.
- [nemotron-speech](https://affpapa.org/en/nevibecode/skills/nemotron-speech.md) — skill · Nemotron Speech Team · Claude Code, Codex, Cursor +5 · 2100 installs — A skill that walks your agent through NVIDIA Nemotron Speech (formerly Riva) NIM work: deploying, running and testing ASR, TTS and NMT in the cloud or self-hosted.
- [dali-dynamic-mode](https://affpapa.org/en/nevibecode/skills/dali-dynamic-mode.md) — skill · DALI Team · Claude Code, Codex, Cursor +5 · 2100 installs — dali-dynamic-mode — a skill that steers the agent through NVIDIA DALI's imperative mode: direct ndd calls instead of pipeline graphs, plus help migrating existing pipelines.
- [nemo-automodel-model-onboarding](https://affpapa.org/en/nevibecode/skills/nemo-automodel-model-onboarding.md) — skill · NVIDIA · Claude Code, Codex, Cursor +5 · 2000 installs — nemo-automodel-model-onboarding walks you through adding a new model architecture to NeMo AutoModel, from reading config.json to registering the class and writing tests.
- [nemo-automodel-recipe-development](https://affpapa.org/en/nevibecode/skills/nemo-automodel-recipe-development.md) — skill · NVIDIA · Claude Code, Codex, Cursor +5 · 2000 installs — nemo-automodel-recipe-development guides the agent in creating and editing NeMo AutoModel training and evaluation recipes.
- [nemo-automodel-distributed-training](https://affpapa.org/en/nevibecode/skills/nemo-automodel-distributed-training.md) — skill · NVIDIA · Claude Code, Codex, Cursor +5 · 2000 installs — nemo-automodel-distributed-training picks a distributed training strategy for NeMo AutoModel and lists the YAML fields to set.
- [physical-ai-defect-image-generation](https://affpapa.org/en/nevibecode/skills/physical-ai-defect-image-generation.md) — skill · NVIDIA · Claude Code, Codex, Cursor +5 · 2000 installs — physical-ai-defect-image-generation prepares automated defect synthesis pipelines for optical quality inspection.
- [physical-ai-video-data-augmentation](https://affpapa.org/en/nevibecode/skills/physical-ai-video-data-augmentation.md) — skill · NVIDIA · Claude Code, Codex, Cursor +5 · 2000 installs — physical-ai-video-data-augmentation is a Claude Code skill for OSMO video augmentation and auto-labeling jobs.
- [tilegym-adding-cutile-kernel](https://affpapa.org/en/nevibecode/skills/tilegym-adding-cutile-kernel.md) — skill · TileGym Team · Claude Code, Codex, Cursor +5 · 1900 installs — tilegym-adding-cutile-kernel guides AI coding agents through adding cuTile GPU kernel operators to TileGym.
- [nemo-mbridge-perf-moe-optimization-workflow](https://affpapa.org/en/nevibecode/skills/nemo-mbridge-perf-moe-optimization-workflow.md) — skill · NVIDIA · Claude Code, Codex, Cursor +5 · 1900 installs — nemo-mbridge-perf-moe-optimization-workflow guides MoE throughput tuning and regression diagnosis in Megatron Bridge.
- [nemo-mbridge-multi-node-slurm](https://affpapa.org/en/nevibecode/skills/nemo-mbridge-multi-node-slurm.md) — skill · NVIDIA · Claude Code, Codex, Cursor +5 · 1900 installs — nemo-mbridge-multi-node-slurm is a Claude Code skill that turns single-node scripts into multi-node Slurm jobs and helps diagnose launch and NCCL failures.
- [nemo-mbridge-perf-moe-vlm-training](https://affpapa.org/en/nevibecode/skills/nemo-mbridge-perf-moe-vlm-training.md) — skill · NVIDIA · Claude Code, Codex, Cursor +5 · 1900 installs — nemo-mbridge-perf-moe-vlm-training is a Claude Code skill with practical guidance for training MoE VLMs in Megatron Bridge, configuring FSDP or 3D parallelism, and debugging OOM failures.
- [nemo-mbridge-mlm-bridge-training](https://affpapa.org/en/nevibecode/skills/nemo-mbridge-mlm-bridge-training.md) — skill · NVIDIA · Claude Code, Codex, Cursor +5 · 1900 installs — The nemo-mbridge-mlm-bridge-training skill runs Megatron-LM and Megatron Bridge training, compares loss curves, and helps investigate divergence after code changes.
- [nemo-mbridge-perf-parallelism-strategies](https://affpapa.org/en/nevibecode/skills/nemo-mbridge-perf-parallelism-strategies.md) — skill · NVIDIA · Claude Code, Codex, Cursor +5 · 1900 installs — nemo-mbridge-perf-parallelism-strategies is a Claude Code skill for selecting parallelism settings in Megatron Bridge.
- [nemo-mbridge-perf-activation-recompute](https://affpapa.org/en/nevibecode/skills/nemo-mbridge-perf-activation-recompute.md) — skill · NVIDIA · Claude Code, Codex, Cursor +5 · 1900 installs — nemo-mbridge-perf-activation-recompute guides activation recomputation setup in Megatron Bridge to resolve GPU memory OOMs during LLM training.
- [dynamo-troubleshoot](https://affpapa.org/en/nevibecode/skills/dynamo-troubleshoot.md) — skill · Dan Gil · Claude Code, Codex, Cursor +5 · 1900 installs — dynamo-troubleshoot is a Claude Code skill that investigates unhealthy Dynamo deployments.
- [nemo-mbridge-recipe-recommender](https://affpapa.org/en/nevibecode/skills/nemo-mbridge-recipe-recommender.md) — skill · NVIDIA · Claude Code, Codex, Cursor +5 · 1900 installs — nemo-mbridge-recipe-recommender — a skill for Claude Code selects and tunes Megatron Bridge training recipes based on model architecture, GPU count, and workload.
- [launch-nemo-rl](https://affpapa.org/en/nevibecode/skills/launch-nemo-rl.md) — skill · NVIDIA · Claude Code, Codex, Cursor +5 · 1900 installs — launch-nemo-rl is a Claude Code skill for launching, monitoring, and debugging NeMo-RL recipes on Kubernetes with the nrl-k8s CLI.
- [nemo-mbridge-perf-memory-tuning](https://affpapa.org/en/nevibecode/skills/nemo-mbridge-perf-memory-tuning.md) — skill · NVIDIA · Claude Code, Codex, Cursor +5 · 1900 installs — nemo-mbridge-perf-memory-tuning is a Claude Code skill for lowering GPU memory peaks and diagnosing OOM during Megatron Bridge training.

Next: https://affpapa.org/en/nevibecode/by/nvidia/skills.md?page=2

## Narrow this list
Parameters: `?platform=<claude-code|codex|cursor|copilot|gemini-cli|windsurf|…>`, `&topic=<…>`, `&sort=installs|stars|new|updated` — values in https://affpapa.org/en/nevibecode/agents.md

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
