Saltar al contenido
Marketplace

nvidia

101 skills en el marketplaceEn GitHub

Skills de los repositorios de nvidia, las más instaladas primero.

Skills

  1. rag-blueprintnvidiaNVIDIA RAG Blueprint — deploy, configure, troubleshoot, and manage. Handles any RAG action: deploy, install, start, enable, disable, toggle, change, configure, troubleshoot, debug, fix, shutdown, stop, or tear down any RAG feature or service (Agentic RAG, VLM, guardrails, query rewriting, models, search, ingestion, observability, summarization, reasoning, and more).3,100 instalaciones en skills.sh0
  2. accelerated-computing-cudfnvidiaOfficial NVIDIA-authored guidance for NVIDIA cuDF GPU DataFrames, pandas acceleration, dask-cuDF, ETL, joins, groupby, CSV/Parquet I/O, nullable semantics, and multi-GPU DataFrame workloads.3,000 instalaciones en skills.sh0
  3. cuopt-developernvidiaModify, build, test, debug, and contribute to NVIDIA cuOpt (C++/CUDA, Python, server, CI). Use for solver internals, PRs, DCO, and code conventions.2,600 instalaciones en skills.sh0
  4. cudaq-guidenvidiaUse for CUDA-Q setup, simulation targets, QPU access, and @cudaq.kernel authoring guidance.2,500 instalaciones en skills.sh0
  5. cuopt-installnvidiaInstall cuOpt for Python, C, or server via pip, conda, or Docker; verify the install. For building cuOpt from source, see cuopt-developer.2,500 instalaciones en skills.sh0
  6. data-designernvidiaUse when the user wants to create a dataset, generate synthetic data, or build a data generation pipeline.2,400 instalaciones en skills.sh0
  7. deepstream-devnvidiaNVIDIA DeepStream SDK development with Python pyservicemaker API. Use when building video analytics pipelines, GStreamer-based video processing, TensorRT inference integration, object detection/tracking, or Kafka/message broker integration.2,400 instalaciones en skills.sh0
  8. nemo-retrievernvidiaUse when searching, extracting, ingesting, or querying a document collection with the NeMo Retriever 26.8.1 CLI, including local LanceDB indexes and deployed Retriever services. Use for PDFs, images, Office files, HTML, text, audio, and video; not for editing documents or web search.2,300 instalaciones en skills.sh0
  9. omniverse-cad-to-simreadynvidiaCoordinate the end-to-end CAD/source-asset to SimReady workflow. Use for broad requests such as CAD to SimReady, source asset to simulation-ready USD, or prop packaging that require conversion, material/physics assignment, SimReady conformance, validation, and optional package creation; deploy or verify Content Agents services first when property assignment is enabled; route single-stage work through nested references.2,300 instalaciones en skills.sh0
  10. rag-evalnvidiaFilesystem RAG benchmarks: corpus/, train.json, evaluate_rag.py (RAGAS quality). Not for prod monitoring, latency/throughput benchmarking (use rag-perf), or evals outside this repo layout.2,300 instalaciones en skills.sh0
  11. cuopt-routing-api-pythonnvidiaVehicle routing (VRP, TSP, PDP) with cuOpt — Python API only. Use when the user is building or solving routing in Python.2,200 instalaciones en skills.sh0
  12. deepstream-import-vision-modelnvidiaUse this skill to bring a supported object-detection vision model from HuggingFace or NVIDIA NGC into an NVIDIA DeepStream pipeline with end-to-end automation: ONNX download, SafeTensors export, TRT engine build, custom nvinfer bbox parser, multi-stream benchmark, and PDF report. Object detection models only.2,200 instalaciones en skills.sh0
  13. omniverse-usd-performance-tuningnvidiaTop-level workflow skill for USD performance diagnosis and optimization. Handles slow loading, high memory, low FPS, and broad scene-optimization requests; delegates auth/runtime setup to Phase 0 owners.2,200 instalaciones en skills.sh0
  14. skill-card-generatornvidiaUse only to generate or update a governance skill card for a specified existing agent skill directory. Do not use for explaining, listing, comparing, or discussing skill capabilities.2,200 instalaciones en skills.sh0
  15. cuopt-numerical-optimization-formulationnvidiaLP, MILP, QP — concepts, problem-text parsing, and formulation patterns (parameters, constraints, decisions, objective). Concepts only; no API.2,100 instalaciones en skills.sh0
  16. cuopt-server-api-pythonnvidiacuOpt REST server — start server, endpoints, Python/curl client examples. Use when the user is deploying or calling the REST API.2,100 instalaciones en skills.sh0
  17. dali-dynamic-modenvidiaDALI imperative dynamic mode (`nvidia.dali.experimental.dynamic`, ndd): use when working on ndd code or migrating pipelines; skip pipeline-only tasks.2,100 instalaciones en skills.sh0
  18. dynamo-recipe-runnernvidiaSelect, validate, patch, and deploy existing NVIDIA Dynamo Kubernetes recipes. Use for model/backend/GPU/deployment-mode recipe bring-up; use router-starter for router-only mode work and troubleshoot for broken deployments.2,100 instalaciones en skills.sh0
  19. nemotron-customizenvidiaPlan, configure, and chain repo-native Nemotron customization steps into single-step or multi-step pipelines: curation, translation, SFT/PEFT (AutoModel or Megatron-Bridge), pretraining/CPT, RL alignment (DPO/RLVR/GRPO/RLHF), BYOB/MCQ benchmarks, checkpoint conversion, ModelOpt optimization, env profiles, and evaluation of trained checkpoints or existing/hosted endpoints. Use when a request names a Nemotron step or workflow, or asks to clean, translate, train, fine-tune, align, convert, optimize, evaluate, or compose these into a pipeline. Do NOT use for frontend/dashboard/visualization work, generic ML advice, billing/access, or non-Nemotron coding tasks.2,100 instalaciones en skills.sh0
  20. omniverse-realtime-viewernvidiaUse as the top-level router for Omniverse Realtime Viewer USD app requests and focused viewer reference documents.2,100 instalaciones en skills.sh0
  21. physical-ai-neural-reconstructionnvidiaRouter for NVIDIA NuRec/NRE: USDZ rendering, NCore conversion, 3DGS, gRPC sensor sim, carline adaptation, PhysicalAI HF datasets. Do NOT use for SimReady or infra setup.2,100 instalaciones en skills.sh0
  22. rag-perfnvidiaPerformance benchmarking for a deployed NVIDIA RAG Blueprint server: profiling pass + aiperf load test driven by a single YAML config. Not for accuracy / RAGAS scoring (use rag-eval) or for deploying / repairing services (use rag-blueprint).2,100 instalaciones en skills.sh0
  23. nemo-rl-session-memorynvidiaManage durable working-session memory for coding agents. Use when a user asks to preserve or recover agent context across disconnects, VS Code restarts, long-running work, handoffs, or any session where important state should be written periodically under the repo's session directory. Do NOT use for: simple questions, short tasks, one-off commands, linting, or code review.2,000 instalaciones en skills.sh0
  24. nemotron-retrieval-recipesnvidiaUse when planning, debugging, tuning, evaluating, exporting, or deploying public Nemotron `embed`/`rerank` retrieval recipes.2,000 instalaciones en skills.sh0
  25. nemotron-speechnvidiaRoutes NVIDIA Nemotron Speech (Formerly Riva) NIM tasks — deploys, runs, and tests ASR, TTS, and NMT NIMs on build.nvidia.com or self-hosted.2,000 instalaciones en skills.sh0
  26. physical-ai-defect-image-generationnvidiaUse when the user wants to orchestrate defect image generation with NVIDIA Cosmos AnomalyGen (Cosmos-Predict2-derived) on OSMO for PCBA, metal surface, and glass inspection. The Day 0 path handles cold-start with USD-to-ROI, image-edit augmentation, and AnomalyGen to create initial PCBA datasets. The Day 1 path performs inference and labeling on real images. This skill helps with first-time asset setup, creation of finetuning checkpoints, and configuring deployment.2,000 instalaciones en skills.sh0
  27. physical-ai-infrastructure-setup-and-resilient-scalingnvidiaUse when the user wants to set up, scale, validate, or harden NVIDIA physical AI infrastructure for synthetic data generation workflows across local MicroK8s or Azure AKS, including Kubernetes clusters, inference endpoint deployment, OSMO deployment, workload submission readiness, and infrastructure failure recovery. Trigger keywords: physical ai infrastructure, resilient scaling, SDG infrastructure, microk8s, azure aks, NVCF deployment, NIM Operator, OSMO deploy, workflow scaling. Don't trigger for: OSMO log summarization or workload-only operations unless infrastructure setup, scaling, validation, or recovery is requested.2,000 instalaciones en skills.sh0
  28. physical-ai-video-data-augmentationnvidiaUse when running video data augmentation and auto-labeling workflows on OSMO: flow selection, preflight, submit-time interpolation, monitoring, and output retrieval. Trigger keywords: video data augmentation, data enrichment, auto labeling, VDA demo, OSMO workflow, pseudo labeling.2,000 instalaciones en skills.sh0
  29. dicom-metadata-extractnvidiaUsed for extracting selected metadata from one DICOM file and flagging standard-tag PHI presence. Not for anonymization or clinical use.1,900 instalaciones en skills.sh0
  30. dicom-series-preflightnvidiaUsed for header-only preflight of one DICOM series folder before conversion or inference. Not for de-identification or clinical clearance.1,900 instalaciones en skills.sh0
  31. dicom-series-to-volumenvidiaUsed for converting one CT DICOM series folder to a HU NIfTI volume with affine evidence. Not for multi-frame DICOM or clinical use.1,900 instalaciones en skills.sh0
  32. digital-health-clinical-asr-buildnvidiaStage 2 of the Clinical ASR Flywheel. Use when curating clinical terms, tagging IPA, and synthesizing a NeMo manifest. NOT for scoring (use /digital-health-clinical-asr-eval).1,900 instalaciones en skills.sh0
  33. digital-health-clinical-asr-evalnvidiaStage 3 of Clinical ASR Flywheel. Score a NeMo manifest, produce the five-section KER leaderboard (by-ipa_source diagnostic). Not for ASR auth (/riva-asr).1,900 instalaciones en skills.sh0
  34. digital-health-clinical-asr-finetunenvidiaStage 4 of the Clinical ASR Flywheel. Use when priority KER is above 0.3 to run stock NeMo SFT on Parakeet TDT v2 and offline cycle N+1 re-eval. NOT for generic word boosting (use /finetune-asr).1,900 instalaciones en skills.sh0
  35. digital-health-clinical-asr-setupnvidiaStage 1 of Clinical ASR Flywheel. Use when bootstrapping a cycle: NVCF+MW disclosure, NVIDIA_API_KEY check, deps install, TTS+ASR smoke test.1,900 instalaciones en skills.sh0
  36. dynamo-interconnect-checknvidiaValidate that a Dynamo deployment's NIXL/UCX/NCCL interconnect is ready for disaggregated serving over RDMA/NVLink. Use after recipe-runner brings a deployment up (especially disagg/multi-node) to confirm the KV transport is correct; use troubleshoot for diagnosing already-failed pods.1,900 instalaciones en skills.sh0
  37. dynamo-router-starternvidiaStart or patch Dynamo router modes and run router endpoint smoke checks. Use for round-robin, KV-aware, least-loaded, or device-aware routing setup; use recipe-runner for recipe deployment and troubleshoot for failure diagnosis.1,900 instalaciones en skills.sh0
  38. dynamo-troubleshootnvidiaDiagnose failed or unhealthy Dynamo deployments. Use when pods, model-cache jobs, PVCs, workers, frontend/router health, endpoints, or benchmark jobs fail; use recipe-runner/router-starter before this for normal bring-up.1,900 instalaciones en skills.sh0
  39. earth2studio-discovernvidiaFind Earth2Studio models, data sources, and examples for a weather/climate use case. Do NOT use for writing inference code, downloading data, or installation.1,900 instalaciones en skills.sh0
  40. earth2studio-installnvidiaGuide installing Earth2Studio via uv or pip, selecting model extras, and configuring the environment. Do NOT use for writing inference code, choosing models, or PhysicsNeMo questions.1,900 instalaciones en skills.sh0
  41. launch-nemo-rlnvidiaPlaybook for launching, monitoring, stopping, and debugging NeMo-RL recipes on a Kubernetes cluster via the nrl-k8s CLI. Covers ephemeral vs long-lived RayCluster modes, iterating on runs, and debugging hung or failed training jobs.1,900 instalaciones en skills.sh0
  42. nemo-automodel-distributed-trainingnvidiaGuide for selecting and configuring distributed training strategies in NeMo AutoModel, including FSDP2, Megatron FSDP, DDP, and parallelism settings.1,900 instalaciones en skills.sh0
  43. nemo-automodel-launcher-confignvidiaConfigure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.1,900 instalaciones en skills.sh0
  44. nemo-automodel-model-onboardingnvidiaGuide for onboarding new model architectures into NeMo AutoModel, including architecture discovery, implementation patterns, registration, and validation.1,900 instalaciones en skills.sh0
  45. nemo-automodel-recipe-developmentnvidiaCreate and modify NeMo AutoModel training and evaluation recipes, including YAML structure, builders, and execution flow.1,900 instalaciones en skills.sh0
  46. nemo-mbridge-perf-cuda-graphsnvidiaValidate and use CUDA graph capture in Megatron Bridge, including local full-iteration graphs and Transformer Engine scoped graphs for attention, MLP, and MoE modules.1,900 instalaciones en skills.sh0
  47. nemo-mbridge-perf-memory-tuningnvidiaTechniques for reducing peak GPU memory in Megatron Bridge — expandable segments, PEFT + SP input re-gather, parallelism resizing, activation recompute, CPU offloading constraints, and common OOM fixes.1,900 instalaciones en skills.sh0
  48. nemo-rl-auto-researchnvidiaAutonomous NeMo-RL research agent workflow for directed hypothesis testing and open-ended discovery. Guides agents through the full experiment lifecycle: understanding recipes and environments, wiring RL or NeMo-gym runs, launching reproducible baselines and iterations, analyzing results, preserving human oversight, and using git plus TSV logs as the research ledger. Do NOT use for: bug fixes, code review, documentation, refactoring, dependency updates, or single-file changes.1,900 instalaciones en skills.sh0
  49. vss-ask-videonvidiaUse this skill to ask the VSS agent's video_understanding tool a fresh visual question about a recorded clip. Not for prior tool output, search hits, or metadata-answerable questions.1,900 instalaciones en skills.sh0
  50. vss-generate-video-reportnvidiaUse this skill when producing a VSS analysis report — Mode A per-clip VLM, Mode B incident-range via video-analytics. Not for standalone video summarization, real-time alerts or ad-hoc Q&A.1,900 instalaciones en skills.sh0
  51. vss-search-archivenvidiaUse this skill to run top-level VSS fusion search on archived video, or to ingest video files / RTSP streams for search. Do NOT use for ad-hoc visual Q&A (use vss-ask-video), live captioning (use vss-deploy-dense-captioning), or video summarization and reports (use vss-summarize-video).1,900 instalaciones en skills.sh0
  52. vss-summarize-videonvidiaUse to summarize a recorded video via the LVS summarization microservice (HITL-gated) with a VLM fallback. Not for report generation or live RTSP captioning.1,900 instalaciones en skills.sh0
  53. earth2studio-data-fetchnvidiaFetch weather/climate data via Earth2Studio data sources for specific variables and times. Do NOT use for inference pipelines, model discovery, or installation.1,800 instalaciones en skills.sh0
  54. earth2studio-deterministic-forecastnvidiaBuild deterministic forecast scripts with Earth2Studio (model, data source, IO, inference). Do NOT use for ensemble, diagnostics, data-only fetch, or install.1,800 instalaciones en skills.sh0
  55. holoscan-install-condanvidiaInstall Holoscan SDK v4.3+ via Conda in a CUDA 13 environment. Use for Conda installs; redirect CUDA 12 hosts to container/wheel.1,800 instalaciones en skills.sh0
  56. holoscan-install-containernvidiaInstall Holoscan SDK via the NGC Docker container. Use for container-based installs; not for native apt/pip/Conda installs.1,800 instalaciones en skills.sh0
  57. holoscan-install-debiannvidiaInstall Holoscan SDK natively on Ubuntu via apt. Use for C++ installs on Ubuntu; pair with /holoscan-install-wheel for Python.1,800 instalaciones en skills.sh0
  58. holoscan-install-sourcenvidiaBuild Holoscan SDK from source via the in-tree ./run script. Use only when published packages don't meet the user's needs.1,800 instalaciones en skills.sh0
  59. holoscan-install-wheelnvidiaInstall Holoscan SDK Python wheel via pip into a venv. Use for Python installs; not for native C++/apt or Conda installs.1,800 instalaciones en skills.sh0
  60. holoscan-setupnvidiaGuides Holoscan SDK installation: inspects the host, assesses platform compatibility, recommends an install method, and delegates to the matching install skill.1,800 instalaciones en skills.sh0

Deska lista estas skills; las escribieron sus autores. Una skill corre con los permisos de tu agente, así que lee lo que hace antes de instalarla.

¿Falta una skill? Sugiere su repositorio desde tu cuenta y el equipo de Deska la agregará. Sugerir un repositorio