Agent Skills by romaosir
Showing 7 vetted skills indexed across 1 GitHub repositories.
Romaosir3
cuda-kernel-techniques
Identify CUDA kernel optimization techniques by profiler symptoms and hardware context.
Community
Intermediate
Romaosir3
cuda-roofline-strategy
Classify CUDA kernel bottlenecks from NCU roofline profiles and experiment phase.
Community
Intermediate
Romaosir3
b200-moe-kernel-optimization
Optimize Mixture-of-Experts CUDA kernels for NVIDIA B200 with FP8/FP16 grouped-GEMM pipelines.
Community
Advanced
Romaosir3
cuda-agent-team
Coordinate parallel CUDA kernel optimization across multiple GPU-pinned worker agents.
Community
Advanced
Romaosir3
cuda-kernel-autodev
Optimize CUDA kernels through correctness-checked keep-or-revert autotuning loops with NCU profiling.
Community
Advanced
Romaosir3
ncu-cuda-profiling
Automate Nsight Compute profiling and classify CUDA kernel bottlenecks.
Community
Advanced
Romaosir3
cuda-b200
Optimizes and debugs CUDA kernels for NVIDIA B200 using compute-sanitizer, nsys, and ncu.
Community
Advanced