Anti Slop Design logo

Anti Slop Design

Community
Ferousco-dev
anti-slop-design

Eliminates generic AI-generated design ("AI slop") from any front-end you build or review — web or mobile. Use whenever generating, reviewing, refactoring, or critiquing a website, landing page, dashboard, web app, iOS or Android app, React Native or Flutter screen, component, design system, or micro-interaction — and whenever the user says a design "looks AI-generated", "looks generic", "looks like a template", "needs personality", or asks to make an interface premium, handcrafted, or distinctive. Also use before emitting any frontend code that involves color, typography, layout, spacing, motion, or copy decisions.

Overview

PublisherFerousco-dev
Repositoryanti-slop-design
Skill nameanti-slop-design
Stars
17
Forks
6
Bundled files
21
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.

  • 21 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by Ferousco-dev on GitHub. Read the source before you install it.

Installation

Install the Anti Slop Design 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/Ferousco-dev/anti-slop-design/tree/main/skills/anti-slop-design
  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/Ferousco-dev/anti-slop-design.git /tmp/anti-slop-design
mkdir -p .claude/skills
cp -r /tmp/anti-slop-design/skills/anti-slop-design .claude/skills/anti-slop-design
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Anti Slop Design 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 Anti Slop Design 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 Anti Slop Design 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 Design Engineer

Generate interfaces that read as handcrafted, premium, and unmistakably human-designed. Never emit the statistical average of the training set.

The one rule

If a design choice exists because "it looks modern" or "it works for most sites," it is slop. Reject it.

Every decision must answer: "Why this, for this product, for this user, at this moment?" No answer means the choice is wrong.

Operating protocol

Run this loop on every UI task. Do not skip steps — skipping is how slop returns.

  1. Establish the brief before the pixels. Product, audience, one emotional adjective, one competitor to not look like. If the user did not supply these, infer them explicitly in one line and state the inference. Never start from a blank aesthetic.
  2. Commit to a direction. Pick one visual thesis and name it (e.g. "editorial serif, high-contrast, near-monochrome, generous negative space"). A named direction is what prevents regression to the mean. Use the six axes and the category starting positions in references/15-product-types.md — "pick a direction" with no vocabulary is itself a prompt for the average.
  3. Derive the system, not the screen. Type scale, spacing scale, color roles, radii, elevation, motion durations — decided once, applied everywhere. Ad-hoc per-component values are a slop tell.
  4. Build. Every element must survive the Hierarchy of Needs.
  5. Self-critique before emitting. Run references/13-pre-emit-checklist.md. Fix what you find. Do not ship and apologize.
  6. State your choices. Close with 3–6 lines naming the deliberate decisions and why. If you cannot justify a choice, it was slop — go back to step 4.

Instant rejects

Reach for any of these and you have failed by default. Each requires an explicit, product-specific justification to survive:

  • Purple/indigo→blue gradient anything (the Tailwind indigo-500 cascade)
  • Inter/Roboto as an unexamined default headline face
  • Glassmorphism, floating blurred blobs, mesh gradients as decoration
  • Three identical feature cards in a row, each with an icon above a heading
  • Centered hero: badge pill → huge heading → gray subheading → two buttons
  • Uniform 1px gray border on every card
  • Dark mode nobody asked for
  • Generic fade-in-on-scroll applied to everything
  • Emoji as iconography
  • One identical design shipped to both iOS and Android
  • :hover carrying meaning in a mobile app
  • A bar chart whose y-axis does not start at zero
  • Chart values available only in a hover tooltip
  • Copy like "Elevate your workflow" / "Unlock the power of" / "Seamlessly"

The full banned-pattern database lives in the reference files below.

References

Load these on demand — do not read them all upfront.

FileRead it when
references/01-philosophy.mdStarting any design task; justifying a decision; explaining why something is slop
references/02-visual-patterns.mdBackgrounds, surfaces, shadows, borders, badges, decorative elements
references/03-color-patterns.mdChoosing a palette, defining tokens, building ramps, dark mode, contrast
references/04-typography-patterns.mdChoosing typefaces, type scales, measure, line height, tracking
references/05-layout-patterns.mdPage structure, hero design, grids, information architecture
references/06-component-patterns.mdCards, pricing, forms, social proof, loading, empty and error states
references/07-animation-patterns.mdAny transition, entrance, hover, scroll behavior, or page transition
references/08-copywriting-patterns.mdAny user-facing words: headlines, body, CTAs, testimonials, errors, release notes
references/09-code-patterns.mdMarkup, tokens, styling architecture, performance, accessibility wiring
references/10-image-media-patterns.mdPhotography, illustration, icons, screenshots, video, alt text
references/11-craft-list.mdKnowing what to add once the slop is gone
references/12-section-rules.mdConcrete rules for a specific page region — nav, hero, pricing, footer, forms
references/13-pre-emit-checklist.mdAlways, before emitting. The gate.
references/14-workflow.mdFull protocol, module routing, and the review / existing-product / constrained-scope modes
references/15-product-types.mdChoosing the direction: personality axes and the register each product category needs
references/16-mobile-app-patterns.mdAny native or cross-platform mobile app: iOS, Android, React Native, Flutter, SwiftUI, Compose
references/17-app-screen-rules.mdA specific app screen — onboarding, feed, profile, settings, paywall, checkout
references/18-trust-signals.mdDeciding what proof to show, or a page that is clean and still not converting
references/19-data-visualisation.mdAny chart, dashboard, metric tile or table
references/20-worked-example.mdSeeing the whole protocol run end to end on a real brief, wrong turns included

To pin your own product's brief, palette, and voice so they stop being re-decided every session, copy assets/project-context.template.md to references/00-project-context.md, fill it in, and add it to this table as "read first, always."

When the product's category is not in module 15, research it rather than guessing. Falling back to B2B SaaS is what produces the generic page. Module 15 §4 has the search protocol.

On the examples. This skill was written while building AppMD, a mobile app analysis tool, so APK/permission/security examples appear throughout. They are illustrations of the principle, never requirements. Substitute the user's actual product and domain — an example that mentions APKs applies identically to invoices, patient records, or freight manifests.

Each taxonomy module ends with a Quick audit block — a list of strings to grep your own output for. Run it before emitting.

Severity: CRITICAL = automatic fail, regenerate · HIGH = regenerate unless defensible in one specific sentence · MEDIUM = justify or replace · LOW = question the default.

Non-negotiables

Regardless of aesthetic direction, output must be:

  • Accessible — WCAG AA contrast minimum, visible focus states, semantic HTML, keyboard-operable, prefers-reduced-motion respected.
  • Performant — no decorative work that costs layout thrash, oversized images, or blocking fonts.
  • Durable — defensible in two years, not tied to a 2024–2026 trend cycle.
  • Specific — communicating something true about this product.

Craft is not decoration. If in doubt, remove.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Anti Slop Design AI skill do?

Eliminates generic AI-generated design ("AI slop") from any front-end you build or review — web or mobile. Use whenever generating, reviewing, refactoring, or critiquing a website, landing page, dashboard, web app, iOS or Android app, React Native or Flutter screen, component, design system, or micro-interaction — and whenever the user says a design "looks AI-generated", "looks generic", "looks like a template", "needs personality", or asks to make an interface premium, handcrafted, or distinctive. Also use before emitting any frontend code that involves color, typography, layout, spacing,...

Why use Anti Slop Design on TypingMind?

Because you install it once and use it with any model. Anti Slop Design 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 Anti Slop Design in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Ferousco-dev/anti-slop-design/tree/main/skills/anti-slop-design. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Anti Slop Design?

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 Anti Slop Design?

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

Is the Anti Slop Design AI skill free?

Yes. It is published on GitHub by Ferousco-dev 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 👇