nvidia · Agent Skills

共 55 个 Skill，均有经来源核对的实质文档。打开卡片可阅读原始说明，了解包内文件和安装方式。

nvidia

官方

debug-openshell-cluster

Debug why an OpenShell gateway deployment is unhealthy, unreachable, or unable to create sandboxes. Use for gateway health failures, Docker/Podman runtime issues, Helm failures, Kubernetes scheduling, TLS or auth, gateway interceptors, supervisor middleware startup or runtime failures, external compute-driver sockets, VM drivers, or sandbox startup. Trigger keywords - debug gateway, gateway failing, deployment failing, helm install failing, cluster health, gateway health, gateway not starting, h

1小时安装量

3

GitHub Stars

2.1万

最近更新

10月30日

Apache-2.02 文件

查看详情 →

nvidia

官方

openshell-cli

Guide agents through using the OpenShell CLI (openshell) for sandbox management, gateway registration, provider configuration and refresh, profile management, policy iteration, settings, service exposure, BYOC workflows, and attached-provider inference. Covers basic through advanced multi-step workflows. Trigger keywords - openshell, sandbox create, sandbox exec, sandbox connect, logs, provider create, profile list, profile describe, provider refresh, policy set, policy get, settings, service ex

1小时安装量

3

GitHub Stars

2.1万

最近更新

10月30日

Apache-2.01 文件

查看详情 →

nvidia

官方

accelerated-computing-cudf

Official 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.

1小时安装量

3

GitHub Stars

3733

最近更新

10月26日

CC-BY-4.0 AND Apache-2.034 文件

查看详情 →

nvidia

官方

rag-blueprint

NVIDIA 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).

1小时安装量

3

GitHub Stars

3733

最近更新

10月26日

Apache-2.038 文件

查看详情 →

nvidia

官方

skill-inspector

Review AI agent skills before installation using NVIDIA SkillSpector and source-aware semantic review. Use when asked whether a skill or downloaded skill folder is safe, trustworthy, installable, over-permissioned, or malicious.

1小时安装量

3

GitHub Stars

2.3万

最近更新

10月28日

Apache-2.01 文件

查看详情 →

nvidia

官方

debug-inference

Debug inference clients that use an attached provider and its native endpoint, including hosted APIs and host-local Ollama, vLLM, SGLang, TRT-LLM, LM Studio, or NIM. Use for provider attachment, endpoint policy, credential substitution, topology, and migration from the removed managed inference endpoint. Trigger keywords - debug inference, managed inference endpoint, local inference, ollama, lm studio, vllm, sglang, trtllm, NIM, inference failing, model server unreachable, credentialendpointmism

1小时安装量

2

GitHub Stars

1.6万

最近更新

10月13日

Apache-2.01 文件

查看详情 →

nvidia

官方

generate-sandbox-policy

Generate sandbox security policies from plain-language requirements and optional REST API documentation. Produces L4 or fine-grained L7 network policies and ordered network middleware configuration. Use for API access rules, middleware host selection, failure behavior, or built-in and operator-run middleware attachment. Trigger keywords - generate policy, create policy, update policy, change policy, sandbox policy, network policy, API policy, security policy, allow API, restrict API, network mid

1小时安装量

2

GitHub Stars

1.6万

最近更新

10月13日

Apache-2.02 文件

查看详情 →

nvidia

官方

cuopt-install

Install cuOpt for Python, C, or server via pip, conda, or Docker; verify the install. For building cuOpt from source, see cuopt-developer.

1小时安装量

2

GitHub Stars

3733

最近更新

10月26日

Apache-2.07 文件

查看详情 →

nvidia

官方

cuopt-numerical-optimization-api

LP, MILP, and QP (beta) with cuOpt — Python, C, and CLI. Use when the user is solving LP, MILP, or QP with any cuOpt interface.

1小时安装量

2

GitHub Stars

3733

最近更新

10月26日

Apache-2.052 文件

查看详情 →

nvidia

官方

data-designer

Use when the user wants to create a dataset, generate synthetic data, or build a data generation pipeline.

1小时安装量

2

GitHub Stars

3733

最近更新

10月26日

Apache-2.011 文件

查看详情 →

nvidia

官方

nvidia-skill-finder

Use for NVIDIA-related requests where an NVIDIA skill might help, even if the user did not ask for a skill. Trigger on NVIDIA products, hardware, software, SDKs, GPUs, Jetson/JetPack/L4T/BSP/SDK Manager/driver/flashing/setup, CUDA, NIM, NeMo, Omniverse/OpenUSD/SimReady, Isaac, RAPIDS/cuDF, cuPyNumeric, cuOpt, Dynamo, Holoscan, TensorRT, DeepStream, VSS, TAO, NGC/NVCF. Do not use for generic non-NVIDIA route, optimize, deploy, AI, video, data, or infrastructure tasks.

1小时安装量

2

GitHub Stars

3733

最近更新

10月26日

CC-BY-4.0 AND Apache-2.07 文件

查看详情 →

nvidia

官方

cuopt-numerical-optimization-api

LP, MILP, and QP (beta) with cuOpt — Python, C, and CLI. Use when the user is solving LP, MILP, or QP with any cuOpt interface.

1小时安装量

1

GitHub Stars

1067

最近更新

10月20日

Apache-2.052 文件

查看详情 →

nvidia

官方

osmo-user

Drive OSMO through its CLI or a connected MCP for cloud-robotics compute on behalf of an end user: check resources, submit/monitor/debug/explain workflows, fetch logs and Grafana/Kubernetes links, inspect direct data storage, manage workflow apps, and set workflow credentials. Use whenever the user asks about OSMO pools, quota, GPUs, or nodes, or about submitting, listing, querying, monitoring, or troubleshooting workflows — including failed, PENDING, queued, stuck, or image-pull-blocked workflo

1小时安装量

1

GitHub Stars

268

最近更新

10月8日

Apache-2.066 文件

查看详情 →

nvidia

官方

cudaq-guide

Use for CUDA-Q setup, simulation targets, QPU access, and @cudaq.kernel authoring guidance.

1小时安装量

1

GitHub Stars

3400

最近更新

9月22日

Apache-2.09 文件

查看详情 →

nvidia

官方

cuopt-multi-objective-exploration

Trace, complete, and interpret the Pareto frontier across competing objectives using repeated single-objective cuOpt solves (weighted-sum and ε-constraint).

1小时安装量

1

GitHub Stars

3587

最近更新

10月14日

Apache-2.05 文件

查看详情 →

nvidia

官方

deepstream-dev

NVIDIA 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.

1小时安装量

1

GitHub Stars

3400

最近更新

9月22日

CC-BY-4.0 AND Apache-2.021 文件

查看详情 →

nvidia

官方

deepstream-import-vision-model

Use 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.

1小时安装量

1

GitHub Stars

3400

最近更新

9月22日

CC-BY-4.0 AND Apache-2.056 文件

查看详情 →

nvidia

官方

foundationpose-pipeline

Adapt BOP datasets, run the FoundationPose perception pipeline with TAO depth, and evaluate or re-score pose results. Use for dataset runs and result comparisons; environment installation belongs to foundationpose-setup.

1小时安装量

1

GitHub Stars

3469

最近更新

9月25日

Apache-2.09 文件

查看详情 →

nvidia

官方

i4h-lerobot-viz

Serve and visually inspect a converted LeRobot dataset in the browser. Use for videos and state/action timelines; do not use for raw workflow HDF5 or incomplete conversion output.

1小时安装量

1

GitHub Stars

3469

最近更新

9月25日

Apache-2.05 文件

查看详情 →

nvidia

官方

i4h-workflow

Orient users to the i4h workflow runtime and route them to the correct stage skill. Use for architecture, support, or where-to-start questions; do not execute a known stage.

1小时安装量

1

GitHub Stars

3469

最近更新

9月25日

Apache-2.06 文件

查看详情 →

nvidia

官方

i4h-workflow-dataset-annotate

Grade or filter workflow HDF5 episodes with an OpenAI-compatible vision model. Use for visual success labels; do not use for replay, policy evaluation, or recordings without frames.

1小时安装量

1

GitHub Stars

3469

最近更新

9月25日

Apache-2.05 文件

查看详情 →

nvidia

官方

i4h-workflow-dataset-replay

Replay a workflow HDF5 episode through its original Scene. Use for visual trajectory and recording verification; do not use for policy evaluation or LeRobot data.

1小时安装量

1

GitHub Stars

3469

最近更新

9月25日

Apache-2.05 文件

查看详情 →

nvidia

官方

i4h-workflow-dataset-teleop

Record demonstrations through a workflow's teleop Task into workflow HDF5. Use for keyboard, leader, VR, or bus input; do not use for policy evaluation or autonomous rule-based Tasks.

1小时安装量

1

GitHub Stars

3469

最近更新

9月25日

Apache-2.05 文件

查看详情 →

nvidia

官方

i4h-workflow-scene-edit

Edit an existing workflow Scene or task contract. Use for assets, layout, cameras, randomization, task text, or success rules; do not use to create a new workflow.

1小时安装量

1

GitHub Stars

3469

最近更新

9月25日

Apache-2.08 文件

查看详情 →