Latest Agent Skills

Read and write large cuPyNumeric arrays to HDF5 files using Legate's parallel, distributed HDF5 I/O.

Guides users through installing, configuring, and calling the NVIDIA cuOpt SDK for routing and optimization problems, with emphasis on clarifying requirements and safe execution.

Manage NVIDIA Brev GPU instances for TAO training, evaluation, and inference using the Brev CLI and Docker.

Runs NV-Segment-CTMR segmentation on CT or MRI NIfTI volumes and records label-map evidence.

Routes NVIDIA Nemotron Speech (Riva) NIM tasks for ASR, TTS, and NMT, covering cloud-hosted inference, self-hosted Docker deployment, and custom model builds.

Modify, build, test, debug, and contribute to the NVIDIA cuOpt codebase (C++/CUDA, Python, server, CI). Includes guidance for solver internals, pull requests, DCO signoff, and code conventions.

Trains, evaluates, exports, and runs inference for person re-identification models using TAO, learning discriminative embeddings for cross-camera matching.

Train, evaluate, export, distill, quantize, or run inference for a TAO DINO 2D object detector using transformer-based detection with denoising training and multi-scale features.

Run automated hyperparameter optimization for NVIDIA TAO models using AutoMLRunner, supporting multiple search algorithms and experiment tracking.

Generates synthetic body MRI volumes using NVIDIA's NV-Generate-CTMR rflow-mr model. Wraps the upstream diffusion inference pipeline with config staging, output validation, and NIfTI volume summarization.

Index folders of PDFs and other documents into LanceDB for vector search, then query them with semantic search, page filters, verbatim quotes, and cross-document aggregation.

Split a large pull request into multiple smaller PRs to reduce the number of required CODEOWNERS reviewer groups.

Launch, monitor, stop, and debug NeMo-RL recipes on a Kubernetes cluster using the nrl-k8s CLI, supporting ephemeral and long-lived RayCluster modes.

Selects Jetson-compatible containers, vLLM runtime images, and Jetson AI Lab PyPI indexes based on Orin SM 8.7 vs Thor SM 11.0 and JetPack version.

Inspects the host system, assesses platform compatibility, and recommends the correct Holoscan SDK installation method, then delegates to a method-specific install skill.

Build video analytics pipelines using NVIDIA DeepStream SDK 9.0 with Python pyservicemaker API, including GStreamer-based video processing, TensorRT inference integration, object detection/tracking, and Kafka/message broker integration.

Ask visual questions about video clips using a VSS agent's video_understanding tool, requiring a fresh look at frames rather than prior metadata or search results.

Deploy, configure, troubleshoot, and manage NVIDIA RAG Blueprint deployments across Docker, Helm, and library setups.

Segments abdominal organs from CT NIfTI volumes using the NV-Segment-CT VISTA3D model, producing label maps and structured evidence JSON.

Runs chest X-ray reasoning smoke tests using the NV-Reason-CXR-3B model via local inference or a public Hugging Face Space API.

Guides testing Megatron-LM: test layout, recipe YAML, adding and running unit/functional tests, golden values, marker filters, and CI parity.

Build synthetic datasets and data generation pipelines using the Data Designer library.

Install cuOpt for Python, C, or REST server via pip, conda, or Docker, and verify the installation.

Update docs/index.md and write Google-style docstrings for NeMo-RL documentation changes.

Runs deep research queries through a reachable NVIDIA AI-Q Blueprint backend, handling health checks, job submission, polling, and report retrieval.

Guide users through installing CUDA-Q, writing quantum kernels, running GPU-accelerated simulations, connecting to QPU hardware, and exploring built-in applications.

Installs, deploys, runs, validates, troubleshoots, and stops NVIDIA AI-Q Blueprint infrastructure for local or self-hosted servers.

Set up the Holoscan Sensor Bridge demo environment end-to-end: clone the repo, configure the host per platform, build and run the demo container, and verify connectivity to the sensor board.

Flash FPGA firmware on HSB Lattice boards and Leopard Imaging VB1940 cameras connected to NVIDIA devkits, with safety checks and multi-step upgrade/downgrade procedures.

Run config-driven performance benchmarks against a deployed NVIDIA RAG Blueprint server, including profiling and load testing, with a unified report.

Evaluates RAG pipelines using a filesystem-based benchmark with corpus/ and train.json, running evaluate_rag.py to tune retrieval and generation flags and interpret RAGAS metrics.

Execute QA test plans on Holoscan Sensor Bridge hardware by reading a test document, filtering tests by setup, running automatable tests with pass/fail evaluation, and producing a structured report.

Discover, select, and run Holoscan Sensor Bridge example applications on a connected devkit over SSH, filtering by platform, board type, and sensors.

Build, optimize, backtest, rebalance, or analyze stock portfolios using NVIDIA-accelerated Mean-CVaR optimization with cuOpt GPU solver.

Store, retrieve, and automatically rotate credentials, API keys, and other secrets using AWS Secrets Manager.

Design, build, and manage AWS Step Functions state machines for serverless workflow orchestration, including error handling, parallel execution, and integration with AWS services.

Manage AWS infrastructure as code with CloudFormation templates, stacks, change sets, and nested stacks.

Create and manage Amazon EventBridge event buses, rules, event patterns, and targets for event-driven architectures.

Manage AWS API Gateway for creating, publishing, and securing REST, HTTP, and WebSocket APIs using CLI commands, SAM templates, and best practices.

Monitor AWS resources and applications using CloudWatch logs, metrics, alarms, and dashboards with CLI and boto3 examples.

Design DynamoDB table schemas, write queries, configure indexes, manage capacity, and troubleshoot performance issues using AWS CLI and boto3 examples.

Set up and manage AWS Cognito user pools, identity pools, OAuth flows, and user authentication with CLI commands and Python SDK examples.

Access AWS Bedrock foundation models for generative AI, including text generation, embeddings, and image generation, with CLI and Python examples.

Create, configure, and manage AWS Lambda serverless functions for event-driven compute, including triggers, debugging, cold start optimization, and layers.

Manage AWS SQS queues, send and receive messages, configure dead-letter queues, and integrate with Lambda using CLI commands and Python boto3 examples.

Create and manage SNS topics, subscriptions, and message publishing for pub/sub messaging patterns.

Manage AWS RDS relational databases: provision instances, configure backups, manage replicas, troubleshoot connectivity, and optimize performance.

Manage AWS Identity and Access Management for users, roles, policies, and permissions. Create IAM policies, configure cross-account access, set up service roles, troubleshoot permission errors, and enforce least-privilege security.

Manage Amazon EKS clusters, node groups, IRSA, add-ons, and deployments using AWS CLI and eksctl.

Deploy and manage Docker containers on AWS ECS with Fargate or EC2, including task definitions, services, auto scaling, and troubleshooting.

Manage AWS EC2 virtual machines — instances, security groups, key pairs, AMIs, EBS volumes, Auto Scaling Groups, Spot Instances, Session Manager, placement groups, and instance lifecycle automation.

Manage AWS S3 buckets and objects: create buckets, upload/download files, configure lifecycle policies, set up static websites, manage permissions, and implement cross-region replication.

Extend Microsoft Entra ID authentication flows with custom claims, attribute collection, and OTP delivery using Azure Functions triggers.

Assess Kubernetes workloads and cluster configurations for AKS Automatic compatibility, identify incompatibilities, generate fixes, and guide migration from AKS Standard to AKS Automatic.

Migrate Slack bots to Microsoft Teams, build dual-platform bots, and convert between Block Kit and Adaptive Cards using a routed expert system with 100+ micro-expert files.

Guides through interactive deployment of Azure OpenAI models with full control over version, SKU, capacity, content filtering, and advanced options.

Discovers available Azure OpenAI model capacity across regions and projects, analyzes quota limits, and recommends optimal deployment locations.

Manage Arize AI Observability and Evaluation resources on Azure using the .NET SDK. Create, read, update, and delete Arize organizations via Azure Marketplace.

Run Playwright tests at scale using Azure Playwright Workspaces with cloud-hosted browsers and integrated Azure portal reporting.

Provision and manage Azure Durable Task Scheduler resources, task hubs, and retention policies using the .NET Azure Resource Manager SDK.