- name
SKILL.md
The skill file stays in the publisher's repository.
Paste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add enmerasoftware/ai-design-check --skill design-fix -a cursor -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add enmerasoftware/ai-design-check --skill design-fix -a claude-code -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add enmerasoftware/ai-design-check --skill design-fix -a codex -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add enmerasoftware/ai-design-check --skill design-fix -a grok -ySend the copied message in a Grok Bot chat. The Bot fetches this SKILL.md from GitHub and adds it to the skills all your Bots share.
Install this skill: https://github.com/enmerasoftware/ai-design-check/tree/HEAD/skills/design-fixFrom the publisher
The checker finds what can be measured; this skill fixes it and the things only a look at the screen can find. The product stays as it is: its features, data, words and section order. What changes is how each size, colour, label and effect gets chosen. Tidy is not the goal: if the result could sit on a rival's site, keep going.
When the user names a symptom, begin where it points, then carry on from step 1.
Copy the file(s) you will change to *.before.* next to them (or note the git commit), so a before/after can be
rendered at the end.
Run the checker on exactly those files and keep the numbers:
npx @enmera/ai-design-check path/to/screen.tsx --json
Take the mechanical part off the list first: npx @enmera/ai-design-check path/to/screen.tsx --fix moves spacing and
corners to the nearest step and very heavy type to bold, with no judgement. Read the changes it prints, then keep going
on what remains. Run the first count before this, so the report shows the whole change.
If the page runs, npx @enmera/ai-design-check scan <url> reports what only a browser sees: real contrast, tiny text, what
covers what, script errors. Then look at the screen at desktop and phone width (a browser tool, Playwright, or the user's screenshot). The rules
marked review need eyes: one-accent, nested-radius, hero-one-action, show-the-product,
no-badge-spam, selector-language, empty-states, legible-contrast, readable-measure, spacing-rhythm,
one-surface-radius, phone-row-room, trim-screen-header, main-action-apart-from-tabs, content-is-the-surface,
worst-case-data.
On the rendered screen, measure what the eye only feels: the gaps between its blocks and the corner radii of its
surfaces. Write them as numbers (gaps 25, 18, 10, 12; radii 10, 8, 4). Several values at one level is the finding
(spacing-rhythm, one-surface-radius); it is what makes a screen look generated when every rule passes.
Write the audit in one short list: each problem, where it is, which rule. Accessibility comes first and
apart (the checker prints it that way; area in --json), then the other areas, worst first.
A screen that works needs no redesign. Say that, and offer a couple of small improvements.
For a landing page or any screen that has to impress, read proof.md now, and add a card for each section before you edit:
Show the cards to the owner with the brief. Anything you could not find on the site is a question, not a guess.
When the project has no tokens yet (no type scale, no colour variables), generate them from the brief instead of
inventing values: npx @enmera/ai-design-check system --character <calm|precise|friendly|warm|bold|editorial|luxurious|playful|technical|trustworthy> --brand "<hex>" --kind <dashboard|app|marketing|reading>.
It writes CSS, Tailwind, SwiftUI and Compose tokens whose text colours already pass contrast; --json prints them.
For a large change, show the audit and the brief and let the user steer before editing. For a small screen or when the user said "just do it", continue.
Answer one question for every element before you move to the next question. A screen people cannot use or cannot trust is worse than one that looks plain, so looks come last. Reuse the project's components and tokens; see scales.md for starting values when the project has none.
legible-contrast), a visible focus ring, tap targets (tap-target),
keyboard order, reduced motion (reduced-motion), and on phones no sideways scrolling or clipped text
(no-horizontal-overflow, text-not-clipped).numbers-with-context); stat cards read label → value →
change with its period (stat-card-anatomy); charts keep every series neutral but one and label it on the chart
(chart-highlight-one, direct-labels); cents and decimals dim in the headline figure (dim-secondary-digits).no-greeting-headline); buttons say what they do;
no exclamation marks (no-exclamation-copy) or buzzwords; sentence case, no full stop on labels, short placeholders,
plausible sample data.spacing-scale, spacing-rhythm, one-surface-radius, nested-radius): one padding for sibling cards, one row height per list. Type
sizes come from the scale (type-scale), weights stay 400–600 (no-heavy-headings), no tracked uppercase labels,
negative tracking only on large display text, tabular figures, one format per number. Giant type appears once a page
(one-display-size).use-shared-components,
use-shared-looks, no-style-overrides); flat buttons (no-gradient-buttons), surface steps instead of heavy shadows
(no-heavy-card-shadow), one status system (status-system), one neutral ramp, hairline borders at 6–10 % of the text
colour, few and quiet badges. Icons come from one line set, with one size and stroke, in a box of equal width on each row;
no emoji or sparkles (icons-not-emoji, no-sparkle-for-ai).one-primary-action), one card header pattern
(card-header-pattern), one main element leads and stat cards stay compact and equal height; wide tables span the page;
a hero keeps to a main action and, if needed, one quieter one (hero-one-action); readable line length. On phones: room for each cell
(), one job for the header (), the main action apart from the tabs
(). Items on a row share a line (), sibling cards end the same way
(), and neighbouring columns end together ().Run the checker again on the same files and report before → after, accessibility first, then per area (for
example 221 → 0 findings; accessibility 4 → 0, spacing 76 → 0, type 57 → 0). Anything left gets a fix or an inline ignore with a reason.
Render it at phone width with the longest language the product ships (German, Finnish):
npx @enmera/ai-design-check narrow path/to/page.html --width 320 --stress
It reports the page scrolling sideways, cut-off text, text shrunk to fit and content hidden on phones; --stress runs
it again with long names, large numbers and longer text. Fix these by letting the layout give (wrap, stack, hyphenate,
scroll a wide table inside its own box), never by shrinking text, truncating labels or hiding content. Then open the
screen with one item and with none (worst-case-data): "1 members" and a blank panel only show with real data.
Look at the screen again at desktop and phone width. The checkers cannot see contrast, rhythm or hierarchy.
Optional, for sharing: render a square before/after video (Chrome and ffmpeg on the machine, no other dependencies):
npx @enmera/ai-design-check story screen.before.html screen.html --out story.mp4
It takes files or URLs, marks every finding on the before screen, wipes to the after screen and counts down.
references/proof.md).no-nested-cards: it is the showcase object show-the-product asks for. Ask, or leave it with an ignore
comment. This protects that one frame, not the page's look: make the visible changes the rules call for (grounds,
effects, cards, type, layout). What stays is features, data, words and anything the user said they like.{/* ai-design-check-ignore-next-line rule-id -- why */}; directly after => ( or return ( write
// ai-design-check-ignore-next-line rule-id -- why instead, since {/* */} there breaks the JSX.rules.json.Repairs AI-built screens that look generated. Measures them with the ai-design-check rules and checker, writes a short brief from the product, then works through usability, truth, copy, numbers, compo
---name: ai-design-fixdescription: Repairs AI-built screens that look generated. Measures them with the ai-design-check rules and checker, writes…---# skills/design-fix/SKILL.mdOverview
Repairs AI-built screens that look generated. Measures them with the ai-design-check rules and checker, writes a short brief from the product, then works through usability, truth, copy, numbers, components, order and decoration before building the proof. Checks again and reports the counts before and after. Use when the user asks to fix, clean up or improve the design of a screen, or says it looks generated, vibecoded or sloppy. Keeps features, data and content.
FAQ
Download skills/design-fix/SKILL.md from the publisher, or copy the path and open the repository. PlugMCP lists the skill and does not host the file.
The publisher keeps it at https://github.com/enmerasoftware/ai-design-check.
Claude, Cursor, Codex, and Grok Build can read a SKILL.md you add from the publisher's repository. Grok Bot installs it when you send the skill's GitHub folder link in a chat.
phone-row-roomtrim-screen-headermain-action-apart-from-tabsmeasure-alignmentcard-footer-patternbalance-columnskeep-what-works); text on the
brand colour keeps its colour (keep-text-on-brand). Gradients on surfaces and text (no-ai-gradients), glows outside charts (glow-in-charts-only), blurred
blobs (no-blur-blobs), side stripes. The accent appears two or three times. Named transitions only, no hover growth, no
bounce, pulse only for live data, transform and opacity instead of position. What people do many times a day answers
quickly (interface-speed), and what they trigger from the keyboard (a command palette, moving through a list) does not
animate at all. Nothing loops without a reason (no-endless-loop).show-the-product), as in proof.md. To show
five or more items on a landing or product page, build a stage as in motions.md, with its
working example, once per page.