Install one, then just prompt in plain English. The FLOW.md fires the right skill at the right moment. No re-orchestration, no babysitting.
Featured
Tensors and Dynamic neural networks in Python with strong GPU acceleration
@pytorchAdd unsigned integer (uint) type support to PyTorch operators by updating AT_DISPATCH macros. Use when adding support for uint16, uint32, uint64 types to…
@pytorchDebug AOTInductor (AOTI) errors and crashes. Use when encountering AOTI segfaults, device mismatch errors, constant loading failures, or runtime errors from…
@pytorchConvert PyTorch AT_DISPATCH macros to AT_DISPATCH_V2 format in ATen C++ code. Use when porting AT_DISPATCH_ALL_TYPES_AND*, AT_DISPATCH_FLOATING_TYPES*, or…
@pytorchQuery PyTorch CI, GitHub Actions, HUD, Grafana, and infrastructure metrics. Use when users ask about CI duration, job failures, queue times, workflow trends,…
@pytorchChoose 32-bit vs 64-bit index math in PyTorch CUDA kernels. Use when fixing large-tensor indexing overflows, deciding whether to use int64_t,…
@pytorchSub-triages issues in the oncall:distributed queue by assigning distributed module labels, routing to sub-oncalls, and marking triaged. Use when an issue has…
@pytorch© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic
