Skip to content
SkillModel-led7,085 tokens in use

Antislop UI

Names the generic patterns AI agents put in interfaces, from gradients and bento grids to stat-card dashboards, and gives a fix for each.

9,688 stars on the repository MIT Licensemiqdadbadjuber/anti-slop · skills/antislop-ui
npx skills add miqdadbadjuber/anti-slop
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing Antislop UI costs

37tokens idle
7,085tokens in use
9,395tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

writes filesdeclared

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Good
  • Frontmatter12/15
  • Structure17/25
  • Examples6/15
  • Output10/15
  • Size13/15
  • Resources15/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity100
  • Maintenance100
  • Community52
  • Maturity20
  • Momentum40

Antislop UI is the visual skill of the antislop rulebook. It loads when a task builds or edits a website, web app or dashboard, and covers color, layout, components, decoration, structure, motion and page performance.

Each entry gives a tell, a reason and a fix tied to a core rule. App screens get their own section, with the default dashboard shell, invented stat cards, filler feeds and placeholder empty states.

What You Get

  • A pattern catalog with a tell, a reason and a fix for each visual and layout default
  • Dose caps for glass, glow, shadow and radius
  • An app and dashboard section that builds the screen around the decision the user makes
  • Rules for empty, loading and error states that name the cause and next action
  • Performance checks for sized media, the hero image and render-blocking scripts, plus two reference files

Common Use Cases

  • Redesigning a landing page that follows the stock hero, cards and testimonials order
  • Reworking an admin dashboard that is a sidebar, four stat cards, a chart and a table
  • Removing decorative emoji, badges, status dots and arrows from a UI
  • Checking a page for layout shift and a lazy-loaded hero image

What Makes It Unique

The skill treats a pattern as slop only when it has no written purpose, and it keeps techniques such as gradients and bento grids available when they serve the content. Its app section goes beyond landing pages, naming the sidebar shell, invented deltas and filler activity feeds. It also warns that a sterile result is a direction problem and not a reason to add more bans.

Under The Hood

The skill is a single SKILL.md with two reference files, a web baseline checklist and a Core Web Vitals note, and no scripts. The frontmatter allows the agent to read, write and edit files and to search with glob and grep, so it can change your UI code. It does not run commands, fetch web pages or call APIs. It loads with the core antislop skill and cites that skill’s rules by number.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers