Loading...
Loading...
Found 24 Skills
XGBoost gradient boosting library. Use for tabular ML.
Use when animation runs slow, janky, or causes frame drops
ONLY for OpenAI Triton (@triton.jit) kernel development. NEVER use for CUDA C++ kernels, TileIR, or profiling tools (ncu, nsys). The user's request must involve Triton explicitly. Covers Triton-specific patterns: fused elementwise, reductions (softmax, LayerNorm, RMSNorm), tiled GEMM with triton.autotune, and flash attention. Workflow: design, write, verify (with fast-path for explicit requests).
Polars fast DataFrame library. Use for fast data processing.
WebGPU fundamentals for high-performance canvas rendering. Covers device initialization, buffer management, WGSL shaders, render pipelines, compute shaders, and web component integration. Use when building GPU-accelerated graphics, particle systems, or compute-intensive visualizations.
GPU-accelerate Python code using CuPy, Numba CUDA, Warp, cuDF, cuML, cuGraph, KvikIO, cuCIM, cuxfilter, cuVS, cuSpatial, and RAFT. Use whenever the user mentions GPU/CUDA/NVIDIA acceleration, or wants to speed up NumPy, pandas, scikit-learn, scikit-image, NetworkX, GeoPandas, or Faiss workloads. Covers physics simulation, differentiable rendering, mesh ray casting, particle systems (DEM/SPH/fluids), vector/similarity search, GPUDirect Storage file IO, interactive dashboards, geospatial analysis, medical imaging, and sparse eigensolvers. Also use when you see CPU-bound Python code (loops, large arrays, ML pipelines, graph analytics, image processing) that would benefit from GPU acceleration, even if not explicitly requested.
Performance optimization coordination playbook. Contains specialist routing table, TileIR two-step pipeline, kernel generation specialist selection, prioritization criteria, and safe modification workflow. Use when the user asks to apply optimizations, write kernels, or improve performance. Covers both user-specified optimization and autopilot-driven iterative optimization.
Use when accelerating existing genomics workflows with NVIDIA Parabricks, improving runtime or price/performance, converting pipeline steps to GPUs, or comparing CPU and GPU workflow outputs. Adds optional GPU steps in-place with runtime toggles (default off). Do NOT use for individual pbrun command routing — use parabricks.
Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HNSW). Use for fast k-NN search, large-scale vector retrieval, or when you need pure similarity search without metadata. Best for high-performance applications.
Pre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment, scaling analysis, or refactor planning. Inspect the user's source code, look up NumPy usage, cross-reference the cuPyNumeric API support manifest, and distinguish distributed-scaling-friendly patterns from blockers such as unsupported APIs, scalar synchronization, host round-trips, Python/object-heavy control flow, shape/data-dependent branching, and in-place mutation hazards. Produce a verdict of READY, LIGHT REFACTOR, SIGNIFICANT REFACTOR, or NOT RECOMMENDED, with concrete refactor pointers.
Walk through omicverse's single-cell preprocessing tutorials to QC PBMC3k data, normalise counts, detect HVGs, and run PCA/embedding pipelines on CPU, CPU–GPU mixed, or GPU stacks.
Configures and implements LiteRT (.tflite) on-device inference on Android in Kotlin using the CompiledModel API on CPU and GPU. Use this skill for any Android LiteRT or .tflite task, including Gradle setup, image classification or vision/audio/embedding helpers, TensorBuffer reuse, CPU memory optimization, Bitmap preprocessing, AndroidViewModel GPU-to-CPU fallback with warm-up on a single-thread dispatcher, LiteRT in Google Play services (play-services-litert), migrating from legacy org.tensorflow.lite.Interpreter, GpuDelegate, or play-services-tflite, and latency benchmarking. Don't use for running generative text LLMs with .litertlm files or for Python model conversion.