agentleFS
sukirman1901sukirman1901/frontend-expert/skills/anti-slop-design/SKILL.md

anti-slop-design

Skill9 starsChanged 2 months agoMITView on GitHub

Detect and fix AI aesthetic anti-patterns (purple/indigo defaults, gradients, rounded-2xl everywhere, generic heroes, Lorem ipsum, shadow-heavy cards). Use whenever building, restyling, or reviewing visual UI quality — including "terlalu generik", "AI slop", "rapihin UI", or design audit requests — without requiring /design.

10 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 9 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Before finishing any /ui build

    line 19
  2. Distinctive:

    When visual output looks generic or template-like

    line 21
  3. Distinctive:

    Re-scan: before marking work done

    line 33

“Common” is measured: kept by at least 6 in 10 of the 9 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Anti AI Slop

Overview

AI-generated UI has recognizable tells. Scan for them before shipping; fix with tokens and purpose-driven layout.

When to Use

  • Before finishing any /ui build
  • During /design audits
  • When visual output looks generic or template-like

When to skip

  • Generated hooks/any/empty wrappers → anti-slop-code
  • Generic sentences with no visual tell → content-design
  • Frame-by-frame / “kenapa animasinya aneh” → motion-inspection

Workflow

  1. Scan for the patterns below (and detail in references/anti-patterns.md)
  2. Fix using design tokens and content-first layout
  3. Re-scan before marking work done

Pattern Table

PatternDetectionFix
Purple/indigo defaults#7c3aed, bg-purple-*, text-indigo-*Token colors only (via decision tree — never invent purple token file)
Excessive gradientsbg-gradient-to-*, linear-gradientFlat token colors
Rounded everythingrounded-2xl / rounded-3xl everywhereToken --radius
Generic heroTemplate layout, no content connectionContent-first layout
Hero-only landingPlasma/hero + thin footer, no section stackmarketing recipe (logo cloud → features → … → CTA)
Block-registry default“Install @tailark / shadcn blocks” as first answerHand-roll from landing-sections.md (same as motion vocabulary)
Lorem ipsumPlaceholder copyRealistic content
Oversized paddingp-8/p-12 on everythingSpacing hierarchy
Stock card gridsUniform grids, no priorityPurpose-driven layout
Shadow-heavyLayered competing shadowsSubtle or no shadow
Loud nav “active bar”Thick left/right accent stripe on selected itemsQuiet fill + weight/contrast only
Theme under sidebarLabeled Dark mode in sidebar footerTopbar moon/sun icon
Header account metaAlways-on name + email in topbarAvatar → account menu
Native filter <select>OS chrome / cramped caret on dashboardsCustom select / combobox
Decorative motion spamHero+3D+Text+Spotlight+Carousel stacked; typewriter on forms≤2 families / ≤2–3 motions; see motion-families.md

Checklist

  • No purple/indigo outside the chosen token source (scored / explicit / hard-gate / project system — not a vibe-picked purple file)
  • No loud left-accent “selected” bars on nav (prefer quiet fill + type weight)
  • No unjustified gradients
  • Radius consistent with tokens
  • No Lorem ipsum
  • Spacing hierarchy present (not equal generous padding)
  • Layout serves content, not a stock template
  • Motion not decorative spam (≤2–3 intentional motions / viewport)

Depth

Full catalog and fixes: references/anti-patterns.md. Evidence-aware craft principles for spacing, color, type, controls, and common surfaces: references/good-ui-principles.md. Token source: references/token-preset-scoring.md (Plasma/neutral-purple only with brand cue). Motion vocabulary: references/motion-families.md.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.