triton skills

Dogacel/auto-gpu-kernel

Skill Claude CodeCodex

Generate the repository-specific validation and benchmark adapters that kbench will orchestrate. Use once when harness/prepared.json is absent.

troycheng/cuda-kernel-optimizer

Skill Codex

Use when optimizing or diagnosing GPU workload performance with CUDA, CUTLASS, Triton, PyTorch, vLLM or TensorRT-LLM; interpreting NCU, Nsys or PyTorch Profiler evidence; or preparing the workload and correctness checks for such optimization. General coding, skill maintenance and conceptual GPU questions do not…