nvidia · Agent Skills

55 Skill con documentazione sostanziale e fonti verificate. Apri una scheda per leggere le istruzioni originali e verificare pacchetto e installazione.

nvidia

Ufficiale

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

Installazioni / 1h

3

GitHub Stars

20,7K

Aggiornato

30 ott

Apache-2.02 File

Vedi dettagli →

nvidia

Ufficiale

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

Installazioni / 1h

3

GitHub Stars

20,7K

Aggiornato

30 ott

Apache-2.01 File

Vedi dettagli →

nvidia

Ufficiale

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.

Installazioni / 1h

3

GitHub Stars

3,7K

Aggiornato

26 ott

CC-BY-4.0 AND Apache-2.034 File

Vedi dettagli →

nvidia

Ufficiale

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).

Installazioni / 1h

3

GitHub Stars

3,7K

Aggiornato

26 ott

Apache-2.038 File

Vedi dettagli →

nvidia

Ufficiale

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.

Installazioni / 1h

3

GitHub Stars

23,1K

Aggiornato

28 ott

Apache-2.01 File

Vedi dettagli →

nvidia

Ufficiale

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

Installazioni / 1h

2

GitHub Stars

16,1K

Aggiornato

13 ott

Apache-2.01 File

Vedi dettagli →

nvidia

Ufficiale

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

Installazioni / 1h

2

GitHub Stars

16,1K

Aggiornato

13 ott

Apache-2.02 File

Vedi dettagli →

nvidia

Ufficiale

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.

Installazioni / 1h

2

GitHub Stars

3,7K

Aggiornato

26 ott

Apache-2.07 File

Vedi dettagli →

nvidia

Ufficiale

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.

Installazioni / 1h

2

GitHub Stars

3,7K

Aggiornato

26 ott

Apache-2.052 File

Vedi dettagli →

nvidia

Ufficiale

data-designer

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

Installazioni / 1h

2

GitHub Stars

3,7K

Aggiornato

26 ott

Apache-2.011 File

Vedi dettagli →

nvidia

Ufficiale

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.

Installazioni / 1h

2

GitHub Stars

3,7K

Aggiornato

26 ott

CC-BY-4.0 AND Apache-2.07 File

Vedi dettagli →

nvidia

Ufficiale

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.

Installazioni / 1h

1

GitHub Stars

1,1K

Aggiornato

20 ott

Apache-2.052 File

Vedi dettagli →

nvidia

Ufficiale

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

Installazioni / 1h

1

GitHub Stars

268

Aggiornato

8 ott

Apache-2.066 File

Vedi dettagli →

nvidia

Ufficiale

cudaq-guide

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

Installazioni / 1h

1

GitHub Stars

3,4K

Aggiornato

22 set

Apache-2.09 File

Vedi dettagli →

nvidia

Ufficiale

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).

Installazioni / 1h

1

GitHub Stars

3,6K

Aggiornato

14 ott

Apache-2.05 File

Vedi dettagli →

nvidia

Ufficiale

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.

Installazioni / 1h

1

GitHub Stars

3,4K

Aggiornato

22 set

CC-BY-4.0 AND Apache-2.021 File

Vedi dettagli →

nvidia

Ufficiale

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.

Installazioni / 1h

1

GitHub Stars

3,4K

Aggiornato

22 set

CC-BY-4.0 AND Apache-2.056 File

Vedi dettagli →

nvidia

Ufficiale

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.

Installazioni / 1h

1

GitHub Stars

3,5K

Aggiornato

25 set

Apache-2.09 File

Vedi dettagli →

nvidia

Ufficiale

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.

Installazioni / 1h

1

GitHub Stars

3,5K

Aggiornato

25 set

Apache-2.05 File

Vedi dettagli →

nvidia

Ufficiale

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.

Installazioni / 1h

1

GitHub Stars

3,5K

Aggiornato

25 set

Apache-2.06 File

Vedi dettagli →

nvidia

Ufficiale

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.

Installazioni / 1h

1

GitHub Stars

3,5K

Aggiornato

25 set

Apache-2.05 File

Vedi dettagli →

nvidia

Ufficiale

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.

Installazioni / 1h

1

GitHub Stars

3,5K

Aggiornato

25 set

Apache-2.05 File

Vedi dettagli →

nvidia

Ufficiale

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.

Installazioni / 1h

1

GitHub Stars

3,5K

Aggiornato

25 set

Apache-2.05 File

Vedi dettagli →

nvidia

Ufficiale

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.

Installazioni / 1h

1

GitHub Stars

3,5K

Aggiornato

25 set

Apache-2.08 File

Vedi dettagli →