UI review

The render is the evidence. A description, DOM text or source code only supports it. Severity, the 13 criteria and the edge cases are in references/criteria.md. An installed design system's own rules come first and count as agreed criteria.

Steps

1. Scope. What the caller names, else the branch's changed screens, else the five top routes.
2. Lint. Run the project's own lint on the scoped files. Record the command and exit code.
3. Capture each screen at each width (the app's narrowest and widest, 390 and 1280 by default) in the states that matter, one fresh navigation per width. With build-design-system installed, build-design-system/scripts/capture.mjs does this behind a guard that blocks every write and saves each capture's accessibility tree. It needs --writes <file> listing the app's writes, or --no-backend, and writes only to its --out folder (keep that under .ui-review/). Otherwise use the host's browser tool and save the tree yourself. Run the project's accessibility scanner too when it has one.
4. Fix the purpose of each screen in one line. Mark it assumed when the caller did not give it.
5. Probe the traps each screen has, on a local build only: keyboard path, focus after close, loading and error states, a throttled tab, reduced motion, and a touch width. Each probe gets a measured result or a reason it did not run. Measure press feedback with the Event Timing API (a PerformanceObserver on event entries, each duration under 100 ms). Do not click anything that writes to shared data.
6. Walk the criteria at each width. Cite each finding by number and name, or by the installed rule's ID.
7. Sort. With more than one reviewer available (a panel), give each the same prompt and no persona, read only. The coordinator then sorts every finding into blocking, should-fix, note or dismissed, naming who raised it and giving one line of reason. A finding raised by two reviewers on their own is the strongest signal. Dismiss nitpicks, hypotheticals nobody traced to a real call site, and "I would have done it differently". Within a bucket, put surfaces that write data first, then order by places hit. Without a panel, do the same alone.
8. Walk the edge cases and mark each shown or not shown.
9. Write the verdict last.

Rules

• A finding has a criterion, a findable location (the element by role and name, with its capture, as in button 'Save changes' (settings-1280.png)), the width, and the evidence. A finding that rests on taste is dropped to Left out.
• Wrong: "The spacing feels tight." Right: "Label sits 24 px from its own field and 8 px from the next one (criterion 4, settings-390.png)."
• An inferred finding is written as the check that settles it. An inferred blocking finding makes the verdict no, pending <the check>.
• A claim that something works or is fixed names a command or capture from this session.
• Contrast, target size and keyboard problems are ranked. A change to the accessibility tree that only adds semantics is ranked. One that removes or restructures semantics goes to a person.
• A finding or pass on responsiveness to input (criterion 13) from a screenshot is invalid. It needs a measured probe. A focus ring is the reverse. Reach the control with real Tab presses and judge the ring from the capture, because a container that draws it through :has(:focus-visible) leaves the focused element reporting no outline.
• Product decisions behind a fix go to For a person to decide. Keeping the user's input is never one.

Output

The first line answers the ask in plain words. The ship line follows: Ready to ship: no. Enter in Email cancels the invite (blocking 1, should-fix 2, 3 questions for a person). Any blocking finding makes the verdict no, an inferred one no, pending <the check>, should-fix alone yes, with fixes, only notes yes.

Then, in order:

1. Review record. Source, tool, widths, date, criteria file, the purpose marked given or assumed, every assumption and gap.
2. Findings by bucket, each with who raised it, what was seen, where, criterion, why it matters here, evidence, and the fix as a check that fails on the current build (Fix Enter in Email so that it sends 1 POST).
3. Edge cases not shown. One line each.
4. For a person to decide.
5. Dismissed and left out. Each with who raised it and the reason.

Run on its own, save the report to .ui-review/<date>-<flow>.md with captures beside it. When a coordinator asks for captures only, return the capture paths, widths and Coverage: line, and no findings. The chat reply gives the answer and ship lines, each command with its exit code, and one prompt the person can paste to take the next step.

Done

Every finding has a criterion, a location, evidence and only the widths where it shows. Every probe has a result or a reason. The first line, the ship line and the summary agree. The last line reads Coverage: with the routes, widths, themes and probes measured, then what was not.