Open source skill library for AI coding agents to write, optimize, and debug high performance compute kernels across CUDA, Triton, and quantized workloads.
This repository also configures its own agents. See what kernel-skills tells them →
Skill Claude CodeCodex
Guide the agent through translating a CUDA kernel to AMD HIP for ROCm-compatible hardware (MI250, MI300, RDNA), preserving correctness and performance intent while adapting to the HIP execution model, memory model, and AMD-specific toolchain.
Skill Claude CodeCodex
Guide the agent through systematically porting an existing CUDA kernel to Triton, mapping the CUDA execution model to Triton's tile-based program model, preserving numerical correctness, and identifying the patterns that do not translate directly.
Skill Claude CodeCodex
Guide the agent through planning a compute kernel that must run correctly and performantly on multiple hardware backends (NVIDIA, AMD, CPU fallback, or future backends) before any backend-specific implementation is written — covering abstraction strategy, feature compatibility mapping, and the tradeoffs between…
Skill Claude CodeCodex
Guide the agent through a systematic process for diagnosing and isolating accuracy degradation in a quantized (INT8, FP8, or low-bit) kernel, from measuring the error to identifying the specific computational step responsible.
Skill Claude CodeCodex
Guide the agent through designing and implementing FP8 compute kernels for inference and training on NVIDIA Hopper (sm90) and Ada Lovelace (sm89) hardware, covering FP8 format selection, scaling strategy, tensor core usage via WGMMA or cuBLAS, and dequantization epilogue design.
Skill Claude CodeCodex
Guide the agent through designing and implementing an INT8 quantized matrix multiplication or linear layer kernel for inference, covering quantization scheme selection, scale computation, int32 accumulation, dequantization epilogue, and the decision between custom code and library solutions.
Skill Claude CodeCodex
Guide the agent through the systematic process of choosing and tuning block size parameters in Triton kernels — BLOCKM, BLOCKN, BLOCKK for GEMM-style kernels; BLOCKSIZE for reduction and pointwise kernels; and the associated numwarps and numstages values that control parallelism and pipeline depth. This is an…
Skill Claude CodeCodex
Guide the agent through implementing a Flash Attention 2-style fused attention kernel in Triton. This covers the outer loop over KV sequence blocks, online softmax with running max and log-sum-exp tracking, numerically stable incremental output accumulation, causal masking, score scaling, output rescaling at the end…
Skill Claude CodeCodex
Guide the agent through implementing a correct, performant blocked matrix multiplication kernel in Triton. This covers tile assignment via programid, pointer arithmetic for A/B/C tiles, accumulation with tl.dot, boundary masking for non-divisible shapes, swizzled tile ordering for L2 reuse, and autotuning for…
Skill Claude CodeCodex
Guide the agent through implementing a correct, numerically stable row-wise layer normalization kernel in Triton. This covers mean and variance computation with fp32 accumulation, epsilon handling, affine transform with gamma/beta, the RMSNorm variant, masking for hidden dimensions not divisible by BLOCKSIZE, and…
Skill Claude CodeCodex
Guide the agent through implementing a numerically stable, performant row-wise softmax kernel in Triton. This covers single-program-per-row assignment, online max+sum reduction with tl.max/tl.sum, masking for rows wider than BLOCKSIZE, fp32 accumulation to avoid overflow and precision loss, and the masked softmax…
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: