Skill Claude Code
Use when the user asks about CUDA kernel optimization, GPU memory hierarchy, kernel scheduling, GEMM or attention implementations, PTX or CUDA DSL techniques, or wants concrete PR-backed kernel references. The deepest coverage is NVIDIA Blackwell and Hopper, but the navigation patterns are useful for broader…
Skill Claude CodeCodex
Profile correct CUDA kernels emitted by Python DSLs with Nsight Compute on B200 / sm100. Use when the user asks to analyze performance, diagnose bottlenecks, read an ncu report, or write an optimization plan for a Python-DSL-generated kernel that already passes correctness checks.
Skill Claude CodeCodex
Guides writing and refactoring GPU kernels across CUDA and DSLs. Invoke when implementing kernel files that must stay importable, independently testable, profileable, and optimizable.
Skill Claude CodeCodex
Profiles TileLang and mixed PyTorch+TileLang workloads with torch.profiler. Invoke when users want traces, operator breakdowns, memory profiling, or a lightweight first-pass performance diagnosis.
Skill Claude CodeCodex
A local, code-grounded TileLang reference skill for DSL semantics, kernel authoring, API lookup, tuning, debugging, examples, and compiler/runtime behavior. Use whenever you need to write, modify, explain, optimize, validate, or troubleshoot TileLang programming work.
Skill Claude CodeCodex
Write optimized Triton GPU kernels for deep learning operations. Covers the full spectrum from basic vector ops to Flash Attention, persistent matmul, fused normalization, quantized GEMM, and memory-efficient patterns.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: