Hub of the CV-CUDA op-tools bundle — the operator-lifecycle command families (make-op, review-op, optimize-op, refactor-op, device-code-proof) and their shared operating contract. Use when asked which op command applies to a task or how the op tooling fits…
Prove an operator refactor changed nothing in the device code, without a build tree and without a GPU, by compiling the changed translation unit before and after and classifying the SASS/PTX difference. Use when asked to show a refactor is bit-exact, to…
Scaffold a new CV-CUDA operator — a complete, wired, building skeleton — and delegate the implementation to a human or another AI. Use when asked to set up / stub out a new operator without implementing it, or to bootstrap one for someone else to finish.…
Add a new CV-CUDA operator end-to-end per .agents/guidance/MAKE_OP_GUIDELINES.md, with a deterministically-enforced definition-of-done. Use when asked to create/add a new operator, scaffold one, or verify that a new operator is complete (approved spec, wired…
Verify a new CV-CUDA operator against the deterministic final regression checklist (the /make-op done-gate). Use when asked whether a new operator is complete/done, or to gate it before merge - gold reference, bit-exact coverage across the declared support…
Check whether a CV-CUDA operator is READY to optimize (correctness + bench coverage + committed baselines + profiling) per .agents/guidance/OPTIMIZATION_GUIDELINES.md. Use before starting an optimization campaign to confirm the readiness gate is clean.
Drive a single-operator optimization campaign per .agents/guidance/OPTIMIZATION_GUIDELINES.md. Use when asked to optimize an operator, run or finish a campaign, update its MR summary, or verify correctness, benchmarks, generalization review, lead disposition,…
Find and safely apply per-operator refactoring / redundancy-reduction opportunities in a CV-CUDA operator (near-duplicate Tensor/VarShape kernels, reinvented shared utilities, dead code). Use when asked to reduce code duplication, de-duplicate or unify an…
Review a CV-CUDA operator's BENCHMARK coverage — drivers, layout axis, baselines, the basic-tier floor, row counts, and coverage statistics. Use when asked whether an operator's benchmarks/baselines are complete or to find/fill bench gaps.
Review a CV-CUDA operator's DOCS & API artifacts — operator_list row, Python autofunction (fn + _into), Limitations-table-vs-code consistency, docstrings, and SPDX headers. Use when asked whether an operator's docs/API surface is complete and consistent.
Review a CV-CUDA operator end-to-end (support / test / bench / docs coverage). Use when the user asks to review an operator, audit its input-type/layout/dtype support, test coverage, benchmark coverage, or docs/API, or to find & fix per-operator coverage…
Review a CV-CUDA operator's input-type, layout, dtype, and channel support matrix. Use when asked which inputs an operator supports, whether required layouts are complete, or whether support is enforced consistently across C, C++, and Python APIs.
Review a CV-CUDA operator's test coverage, including C++ correctness, required cross-layout parity, correctness rigor, and the Python API surface. Use when asked whether an operator is adequately tested or to find and fill test gaps.