aura-review

Aura Review

An objective, code-level audit of Aura usage in a generated app: did the app use Aura where Aura applies, and did it use the Aura components it did reach for correctly?

This skill never asks the user anything. It is designed to run unattended — inside a CI job on a nightly schedule, or by hand — and to always finish with a machine-readable review.json plus a human-readable markdown report.

Never run this against an app that's still being built

Only invoke this once the app is functionally complete, as a separate step after building finishes — never while scaffolding or implementing it, and never in the same context as the build. This isn't a linter; it's an eval of how well a build agent reaches for Aura unprompted. A build agent that can see this skill's grading criteria will write code to satisfy those specific checks instead — a high score would then mean "read the answer key," not "uses Aura well." Keep building and reviewing as separate agents with no shared context, the way aura-eval-daily.yml runs them.

The one rule that matters more than any step below

Only flag something as wrong if it is already written down in either DESIGN.md or the public Aura docs. If you notice something that feels wrong but isn't documented anywhere, do not invent a rule to justify flagging it, that isn't a fair test of an app built against documentation that never mentioned the rule. Instead, note it as a suggestion for the docs and move on. This matters because these reports get used to tell people "Aura says you did X wrong" — that claim has to be traceable to something they could have read.

Likewise, when judging whether a custom component "could have been Aura", only say so when you can point at a specific Use when bullet for a named Aura component that matches — otherwise mark it undecided rather than guess.

Sources of truth (v1, Storybook is deliberately out of scope for now)