Four frontend skills are on sale now. Pay once, download straight away with your licence key.

See the catalogue
AI Skill Up
Browse skills

A rubric for judging what a skill produced

Some qualities cannot be checked by a script: does the screen look designed, is the copy specific. A five-line rubric makes that judgement repeatable.

Scripts can check that a token was used. They cannot tell you whether a page looks designed. For that you need a person, and a person needs a short list so two reviews mean the same thing.

A rubric for a design skill

  1. Would a stranger say this page had a designer? Yes or no.
  2. Is the accent used only on the primary action?
  3. Is every number in a mono, tabular face?
  4. Is the hero showing the product rather than an illustration?
  5. Is there anything from the skill's banned list?

Each question maps to a rule in the skill, so a failing answer points straight at what to fix. The anti-generic list behind several of these is in why AI-generated UI all looks the same. Pair the rubric with automated property checks from golden outputs.

Questions

Why use a rubric instead of just looking?

Because looking drifts. A short rubric makes two reviews comparable, and makes it obvious which rule the output broke.

How long should a rubric be?

Five or six yes-or-no questions drawn from the skill's own rules. Longer rubrics stop being used.

Can a model grade against the rubric?

It can help as a first pass, but check its judgements against your own on a few cases before trusting it on many.

Or skip the afternoonand drop one in.

Every skill in the catalogue is a folder you drop into your skills directory. Each ships with its design rules, worked examples and a troubleshooting table, and downloads the moment you pay.