Ui Anti Slop logo

Ui Anti Slop

Community
thakur698
ui-anti-slop

Detects and prevents generic AI-generated UI patterns in web and mobile products.

Overview

Publisherthakur698
Repositoryuniversal-ui-skills
Skill nameui-anti-slop
Stars
5
Forks
0
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by thakur698 on GitHub. Read the source before you install it.

Installation

Install the Ui Anti Slop AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/thakur698/universal-ui-skills/tree/main/.agents/plugins/universal-ui/skills/ui-anti-slop
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/thakur698/universal-ui-skills.git /tmp/universal-ui-skills
mkdir -p .claude/skills
cp -r /tmp/universal-ui-skills/.agents/plugins/universal-ui/skills/ui-anti-slop .claude/skills/ui-anti-slop
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ui Anti Slop in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Ui Anti Slop on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Ui Anti Slop is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Anti-Slop UI Review

Mission

Prevent the interface from looking like generic "AI slop". AI slop happens when an agent optimizes for "looks modern" instead of "fits the product".

Anti-Slop Categories

CATEGORY A — Generic Structure

Reject or reconsider:

  • every section becoming a card
  • nested cards (cards inside cards)
  • side-stripe borders (e.g. border-l-4 border-primary on cards/callouts)
  • repeated three-card layouts
  • generic SaaS dashboard grids
  • centered hero copied everywhere
  • excessive symmetrical layouts
  • arbitrary floating elements
  • kicker / eyebrow pill above every section heading

CATEGORY B — Generic Styling

Reject or reconsider:

  • random purple/blue gradients
  • excessive glassmorphism
  • giant blur effects
  • excessive glow or zero-offset glow halos masquerading as depth
  • giant soft shadows
  • ghost cards (competing border + heavy shadow on the same element)
  • pills of any kind (pill badges, tags, chips, floating pill eyebrows, or rounded-full containers are strictly banned)
  • background colors or tinted containers behind icons (colored circles, rounded square tiles, or icon boxes are strictly banned)
  • excessive rounded rectangles
  • monospace used as a decorative costume for "technical" feel

CATEGORY C — Generic Content Treatment

Reject or reconsider:

  • unnecessary badges and pill tags
  • excessive labels
  • excessive helper text
  • emoji used as primary product icons
  • repetitive icon + label combinations
  • icon substitution instead of rich imagery (using generic icons where real photos, product renders, UI captures, or technical diagrams should carry the story)
  • background color behind icons (icons must sit directly on the surface without container boxes or tinted backdrops)

CATEGORY D — Generic Motion

Reject or reconsider:

  • animation on every component
  • long entrance animations
  • unnecessary bounce
  • perpetual decorative movement
  • motion that delays interaction
  • animating images on hover directly (provide feedback on the container or trigger instead)

CATEGORY E — Generic Implementation

Reject or reconsider:

  • default component-library appearance becoming the entire product identity
  • copied component patterns without contextual variation
  • arbitrary magic numbers
  • visual duplication instead of a design system

Anti-Patterns (Code Examples)

When auditing code, strictly reject the following structures. Agents learn best from concrete examples:

1. Icon Background Containers (Strictly Forbidden)

❌ SLOP (Reject):

html
<div class="bg-blue-100 rounded-lg p-2 flex items-center justify-center">
  <svg class="w-5 h-5 text-blue-600">...</svg>
</div>

✅ ANTI-SLOP (Accept):

html
<svg class="w-6 h-6 text-blue-600">...</svg>

Icons must sit cleanly on the surface. No containers, no boxes, no tinted backdrops.

2. Ghost Cards

❌ SLOP (Reject):

html
<div class="border border-gray-200 shadow-xl rounded-xl">...</div>

✅ ANTI-SLOP (Accept):

html
<!-- Either Border OR Shadow, never both -->
<div class="border border-gray-200 rounded-xl">...</div>
<!-- OR -->
<div class="shadow-xl border-transparent rounded-xl">...</div>

Anti-Slop Review Questions

Before declaring success, you MUST explicitly output a markdown checklist answering these 10 questions. You cannot pass the review unless question 8 (Pills) and 9 (Icon Backgrounds) are explicitly answered 'No':

  1. Could this UI belong to 20 unrelated products?
  2. Which visual decisions are actually specific to the product?
  3. Which elements exist only because AI commonly generates them?
  4. Is decoration doing useful work?
  5. Is hierarchy stronger than decoration?
  6. Is the typography doing enough visual work?
  7. Is the screen memorable without effects?
  8. Are there any pills or rounded-full pill badges/chips? (If yes, eliminate them; use clean typographic hierarchy).
  9. Is there any background color, tinted container, or box behind icons? (If yes, remove container backgrounds so icons sit cleanly on the surface).
  10. Does the design use more and more images than icons? (If it leans on generic icon grids, replace them with rich photography, product renders, live UI captures, or architectural diagrams).

Enforcement

If the result is generic, you must redesign it instead of simply reporting success. Remove unnecessary decorations, eliminate pills, remove icon background colors, prioritize rich imagery over icons, restore product context, and prioritize hierarchy over trends.

Frequently asked questions

What does the Ui Anti Slop AI skill do?

Detects and prevents generic AI-generated UI patterns in web and mobile products.

Why use Ui Anti Slop on TypingMind?

Because you install it once and use it with any model. Ui Anti Slop is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Ui Anti Slop in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/thakur698/universal-ui-skills/tree/main/.agents/plugins/universal-ui/skills/ui-anti-slop. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Ui Anti Slop?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Ui Anti Slop?

As many as you like. As long as a model supports skills, you can use Ui Anti Slop with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Ui Anti Slop AI skill free?

Yes. It is published on GitHub by thakur698 under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇