No Slop Ui logo

No Slop Ui

Community
LeoStehlik
no-slop-ui

Build or review frontend UI for clean, restrained, human-designed interfaces without generic AI visual patterns.

Overview

PublisherLeoStehlik
Repositoryno-slop-ui
Skill nameno-slop-ui
Stars
11
Forks
0
Bundled files
8
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.

  • 8 bundled files

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

  • Open source

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

Installation

Install the No Slop Ui 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/LeoStehlik/no-slop-ui/tree/master
  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/LeoStehlik/no-slop-ui.git \
  .claude/skills/no-slop-ui
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable No Slop Ui 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 No Slop Ui 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 No Slop Ui 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.

No Slop UI

You are building UI for a human audience. The goal is functional, honest, clean. Not impressive. Not dramatic. Normal.

If a design decision feels like the easy AI default — it probably is. Pick the harder, cleaner option.

Read references/banned-patterns.md for the full banned list before writing any UI code. Read references/colour-palettes.md when you need to pick colours.

Activation Boundary

Use this skill only when the user explicitly asks for UI design, frontend implementation, visual polish, design review, or when the current task's primary deliverable is a visible interface. Do not activate it for backend-only tasks, copywriting, diagrams, infrastructure, or general code review.

Treat this skill as a visual-quality layer. It must not override product requirements, accessibility, security, localization, data correctness, or the repository's existing design system. If those conflict with a no-slop rule, preserve the user requirement and explain the tradeoff.

The Standard

Think Linear. Raycast. Stripe. GitHub. They don't try to grab attention. They just work.

What normal looks like:

  • Sidebar: 240–260px fixed, solid background, 1px border-right. No floating shells, no rounded outer corners.
  • Cards: 8–12px radius max, subtle 1px border, shadow max 0 2px 8px rgba(0,0,0,0.08). No glow, no float.
  • Buttons: solid fill or simple border, 6–10px radius max. No pills, no gradients.
  • Typography: clear hierarchy, 14–16px body, system font or single sans-serif. No mixed serif/sans.
  • Spacing: 4/8/12/16/24/32px scale. Consistent. No random gaps.
  • Borders: 1px solid, subtle colour. No thick decorative borders, no gradient borders.
  • Transitions: 100–200ms ease. Opacity or colour only. No bouncy, no transforms.
  • Inputs: solid border, simple focus ring. Labels above fields.
  • Icons: 16–20px, monochrome or subtle colour, no decorative backgrounds.

Colour Priority

  1. Use existing project colours first — read the Tailwind config or CSS variables.
  2. If no palette exists — pick from references/colour-palettes.md.
  3. Never invent random colour combinations.

Stack-Specific Notes

shadcn/ui + Tailwind:

  • Use shadcn components as-is — don't re-invent what's already there
  • Respect the existing CSS variable system (--background, --foreground, --primary etc.)
  • Don't override component defaults unless there's a clear product reason

Plain HTML dashboards:

  • Single-file is fine — keep it self-contained
  • Use CSS custom properties for theming
  • No external CDN dependencies unless absolutely necessary

Hard Rules

  • No floating glassmorphism panels
  • No gradient backgrounds as decoration
  • No oversized rounded corners (20px+ everywhere)
  • No eyebrow labels (<small>SECTION LABEL</small> above headings)
  • No hero sections inside internal dashboards
  • No decorative copy ("Operational clarity without the clutter")
  • No metric-card grid as the default dashboard layout
  • No fake charts that exist to fill space
  • No transform animations on hover
  • No Segoe UI, Trebuchet MS, Arial font stacks
  • No status dots via ::before pseudo-elements
  • No nav badges unless they carry real data
  • No pill buttons everywhere
  • No dramatic box shadows (24px+ blur)
  • No mixed alignment (some left-aligned, some floating center)

Full banned list with examples: references/banned-patterns.md

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 No Slop Ui AI skill do?

Build or review frontend UI for clean, restrained, human-designed interfaces without generic AI visual patterns.

Why use No Slop Ui on TypingMind?

Because you install it once and use it with any model. No Slop Ui 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 No Slop Ui in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/LeoStehlik/no-slop-ui/tree/master. 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 No Slop Ui?

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 No Slop Ui?

As many as you like. As long as a model supports skills, you can use No Slop Ui with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the No Slop Ui AI skill free?

Yes. It is published on GitHub by LeoStehlik 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 👇