Expand successful workflow recordings stored in HDF5 by copying episodes and adding small variations to recorded actions. Limit changes to a requested node segment and check generated counts, data dimensions, success flags, and preserved segments.
Check and change NVIDIA display and GPU settings through natural-language requests using G-Assist tools. Inspect current settings, adjust supported display controls and frame-rate limits, or plot GPU and CPU metrics on the current machine.
Read hardware counters, values describing device activity, from BlueField or ConnectX in a DOCA application. The skill guides supported-counter checks, reader setup, sampling, and error handling across six domains, including PCC, DPA, PHY, and PCI.
Load, configure, run, observe, and stop custom congestion control algorithms on BlueField using doca_spcx_cc. The skill guides comparisons with doca-pcc, evaluation under controlled network contention, and diagnosis of loading errors or unchanged traffic behavior.
Run an Isaac for Healthcare workflow from robot recordings through dataset preparation, policy training, and checkpoint validation. Uses the maintained pipeline driver, checks the planned commands first, and verifies artifacts and logs at each stage.
Set up or repair the FoundationPose perception pipeline and build FoundationStereo TensorRT engines for depth estimation. It checks system requirements, resolves dependency and CUDA library issues, and verifies engines against the intended scene dimensions.
Build and troubleshoot NVMe-oF storage targets that expose local disks over a network using DOCA STA. Guides device support checks, I/O queue sizing, and error diagnosis on BlueField or ConnectX hardware.
Consolidate DOCA installation details, device capabilities, and host versus DPU differences into a consistent report. The skill defines structured output formats and manual fallback checks, including how to report unavailable tools and validation limits.
Prepare BOP datasets and run depth estimation, image segmentation, and FoundationPose to estimate object positions and orientations. Evaluate completed runs, compare accuracy and coverage, or change scoring settings without repeating inference.
Set up Earth2Studio with uv or pip using commands matched to your environment and planned models. The skill guides optional dependency selection, cache configuration, installation checks, and dependency troubleshooting while leaving package installation to the user.
Find Earth2Studio models, data sources, and examples for weather or climate tasks. Filters options by region, forecast type, and GPU memory, then checks whether data sources supply the variables required by each model using current documentation and source files.
Select an existing NVIDIA Dynamo Kubernetes deployment recipe for a model, inference framework, and GPU setup. The skill validates requirements, patches necessary settings, deploys the recipe, and checks the endpoint with an OpenAI-compatible test request.
Replay an episode stored in HDF5, a structured data file, using its original workflow Scene. Check the full recorded motion visually, inspect segment boundaries and camera views, and report agreement or the first mismatch.
Create a new data source wrapper, code that connects remote weather data to Earth2Studio. The skill covers source selection, variable mapping, implementation, tests, and validation with real data, with further steps for documentation and pull request submission.
Build Python scripts for a single weather forecast with Earth2Studio. Choose a model, compatible input data, and an output format based on the forecast period, region, requested variables, and available GPU memory.
Build Earth2Studio wrappers for transformations at a single time point, from calculating wind speed to using pretrained or diffusion models. The workflow covers input and output coordinates, model loading, tests, and supporting documentation.
Find suitable Earth2Studio sources for weather and climate variables at specified times, verify variable support, and generate a Python script that retrieves historical or forecast data as an xarray DataArray, an array with labeled dimensions.
Integrate a machine learning weather model into Earth2Studio for forecasts that advance through time. The skill guides wrapper implementation, coordinate handling, model loading, tests, dependency declarations, and documentation updates using a reference inference script.
Diagnose failed Dynamo deployments using Kubernetes status, events, and logs. Gather evidence without changing the cluster, identify the likely failure layer, and return a specific command or patch to try next.
Build custom emulated PCIe devices that a host recognizes as peripherals while BlueField DPU code handles their operation. Get guidance on DOCA sub-library selection, capability checks, setup within an installed environment, and debugging device visibility or driver binding.
Build and run the GPUNetIO benchmark to measure sustained RDMA WRITE bandwidth, a remote-memory transfer rate driven by a CUDA kernel. Interpret results, investigate run-to-run variation, and identify GPU, network adapter, or link bottlenecks.
Measure DOCA Flow rule update and disable rates when work runs on the device's DPA processor. Configure workloads, interpret repeated measurements in thousands of operations per second, and investigate zero-operation results or failed self-tests.
Configure and troubleshoot DOCA Firefly time synchronization on BlueField. The skill helps decide whether high-precision PTP synchronization is needed, choose service settings, and check that the host clock follows BlueField's hardware clock.
Build and debug DOCA RDMI applications that let a DPA accelerator directly access remote memory. Get guidance on connections, completion notifications, kernel handles, and API availability using the installed DOCA version and its reference samples.
Is this your account? Link GitHub to bring it onto your creator page (Japanese)