What problem does it solve? Code reviews often conflate two separate questions — does the code follow the repo's standards, and does it implement what was actually asked for — letting one axis mask failures in the other. This Skill separates them into parallel sub-agent reviews over the diff between HEAD and a fixed point, then aggregates the findings side by side. ## Core Features & Use Cases - Two-axis review: A Standards axis checks the diff against documented repo standards plus a fixed baseline of Fowler code smells, while a Spec axis checks the diff against the originating issue or spec. - Parallel sub-agents: Both axes run as isolated sub-agents so their contexts do not pollute each other, and findings are reported separately without reranking. - Gate and tier integration: Reads the latest quality gate report and router tier to scope the review (full, sampling, or auto-skip) and avoid re-litigating metrics the gate already covers. - Use Case: Before merging a feature branch, ask for a review since the main branch; the Skill pins the merge-base diff, locates the linked issue, runs both reviews, and saves an aggregated report bound to the gate's source hash so the commit gate can verify it. ## Quick Start Ask the assistant to review the changes since main using the code-review skill and report standards and spec findings separately.
