Claude Skills for a Data Scientist / ML — Page 4
NeMo MBridge CPU Offload
Configure, validate, and troubleshoot CPU offloading in Megatron Bridge to relieve GPU memory pressure.
NeMo MBridge CUDA Graphs
Configure, validate, and benchmark CUDA Graph capture in Megatron Bridge to reduce host-driver overhead.
NeMo Relay Call Instrumentation
Wrap tool and LLM calls with Relay lifecycle events, middleware, and guardrails.
NeMo Relay Context Isolation
Keeps NeMo Relay scope stacks independent across concurrent requests and async workflows while preserving ancestry propagation.
NeMo Relay Typed Wrappers & Codecs
Add typed boundaries to NeMo Relay integrations while preserving predictable JSON middleware semantics and caller-visible behavior.
Omniverse Realtime Viewer
Routes USD viewer requests to the right architecture and guides rendering, interaction, UI, and validation.
NVIDIA Physical AI Defect Image Generation
Orchestrate defect-image generation, augmentation, inference, and labeling for AOI datasets on OSMO.
NVIDIA NuRec Neural Reconstruction Router
Routes NuRec requests to the right upstream workflow skill.
TAO CLIP Fine-Tuning and Deployment
Train and deploy NVIDIA TAO CLIP for image-text retrieval, zero-shot classification, and embedding extraction.
TAO Platform Execution SDK
Submit, monitor, and manage NVIDIA TAO GPU training jobs across supported platforms.
TAO FastFoundationStereo Real-Time Stereo Depth
Run TAO FastFoundationStereo workflows that produce low-latency disparity maps from stereo images.
CUDA-Q Quantum Onboarding
Guides developers from CUDA-Q installation to quantum kernels, GPU simulation, and real QPU execution.
cuOpt Numerical Optimization API
Guide agents through GPU-accelerated LP, MILP, and QP modeling with cuOpt
cuOpt Numerical Optimization Formulation
Turn natural-language problems into clear LP, MILP, or QP mathematical formulations.
cuPyNumeric Parallel Shard Loader
Builds processor-sized parallel loading paths from sharded on-disk data into distributed cuPyNumeric arrays.
Clinical ASR Flywheel: Environment Setup
Validate that a clinical ASR evaluation environment can complete a TTS-to-ASR round trip through NVIDIA-hosted speech services.
DOCA DMA Development Guide
Guides hands-on DOCA DMA memory-copy development on BlueField and ConnectX systems.
DOCA Flow Performance Measurement
Guides reproducible, defensible measurements of host-side and DPU-CPU DOCA Flow control-plane rule rates.
DOCA Flow Tune
Guides engineers through snapshotting, analyzing, and optimizing live or captured DOCA Flow pipelines.
DOCA Programming Guide
Guides developers through building, testing, and debugging library-agnostic DOCA applications from shipped samples.
NVIDIA DOCA Public Knowledge Map
Routes agents to authoritative DOCA docs, samples, versions, and install paths.
DOCA SPCX Programmable Congestion Control
Operate and evaluate SPCX congestion-control algorithms on BlueField DPA before production rollout.
Jetson Fan Curve Customizer
Safely maintain nvfancontrol fan profiles and boot defaults in a Jetson BSP.
Jetson Target Knowledge Base Generator
Scans a Jetson BSP and source tree to create a target-specific knowledge snapshot.