design-critique

design-critique

Judges a built thing against what you said you wanted. One question, asked seriously: does this match the stated intent, and where it doesn't, how does it actually read?

Design feedback from a model fails in two directions and this skill is shaped against both. It flatters — every finding hedged into a suggestion, every section opening with what's working — or it produces a checklist of generic improvements that would apply equally to any interface ever built. Both are useless. What's useful is the thing a good design critic does: name how the thing reads to someone encountering it, then say what to do about it.

The hard gate in Step 1 is this skill's expression of ADR 0021, which closes by naming this skill directly: it "may only review against a written brief, because reviewing against nothing is exactly the generation this decision forbids." Critique is a check, and a check needs something to check against.

Three rules govern this skill:

• Diagnosis before prescription. Every finding must first name how the thing reads — in the form "reads as X rather than Y" — before any fix is proposed. No diagnosis, no finding. This is not a stylistic preference: a fix without a diagnosis is a guess, and it's how critique turns into an arbitrary list of changes. Five chips floating in an empty card "read as browser tabs rather than an iteration canvas." That sentence is the entire value of a critique; the fix follows from it in a way it never does from "consider adjusting the spacing".
• Delete is a verdict, and it's first in the list. Most model critique only ever adds — another affordance, another label, another explanatory line. In practice the most common good design move is removal: the redundant CTA, the feature card promising something that doesn't ship yet, the caption explaining what the UI already shows, the greyed-out button that's never enabled.
• Against intent, not against taste. With no written intent this becomes your aesthetic preferences delivered with authority. That's why the gate in Step 1 is hard rather than advisory.