Iterative CUDA kernel optimization using NVIDIA profiling tools (nsys, ncu). Use when optimizing kernels, improving throughput, reducing bandwidth, analyzing roofline, comparing benchmarks, or investigating register pressure and occupancy.
Quickly install cuda-kernel-refine AI skill to your development environment via command line
Source: trevors/dot-claude.
One change per cycle: baseline → profile → classify → optimize → verify → compare → loop. Multiple simultaneous changes make it impossible to attribute improvement. Revert on regression.
Discover the project's benchmark infrastructure before running anything:
Run with enough iterations for stable results — coefficient of variation <5%.
Iterative CUDA kernel optimization using NVIDIA profiling tools (nsys, ncu). Use when optimizing kernels, improving throughput, reducing bandwidth, analyzing roofline, comparing benchmarks, or investigating register pressure and occupancy. Source: trevors/dot-claude.
Stable fields and commands for AI/search citations.
npx skills add https://github.com/trevors/dot-claude --skill cuda-kernel-refineIterative CUDA kernel optimization using NVIDIA profiling tools (nsys, ncu). Use when optimizing kernels, improving throughput, reducing bandwidth, analyzing roofline, comparing benchmarks, or investigating register pressure and occupancy. Source: trevors/dot-claude.
Open your terminal or command line tool (Terminal, iTerm, Windows Terminal, etc.) Copy and run this command: npx skills add https://github.com/trevors/dot-claude --skill cuda-kernel-refine Once installed, the skill will be automatically configured in your AI coding environment and ready to use in Claude Code, Cursor, or OpenClaw
https://github.com/trevors/dot-claude