Interface Design logo

Interface Design

Community
creativedeals
interface-design

Design a page or UI on request that follows professional web interface guidelines and does not look AI-generated. Use when asked to design, build, or mock up a page, landing page, screen, component, or interface, or to improve how something looks. Commits to a specific visual direction and token system, builds to a strict guideline set, then runs a self-check and fixes every issue before presenting.

Overview

Publishercreativedeals
Repositoryfree-claude-skill-interface-design
Skill nameinterface-design
Stars
4
Forks
0
Bundled files
8
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 creativedeals on GitHub. Read the source before you install it.

Installation

Install the Interface 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/creativedeals/free-claude-skill-interface-design/tree/main
  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/creativedeals/free-claude-skill-interface-design.git \
  .claude/skills/interface-design
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Interface 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 Interface 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 Interface 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.

Interface Design

Designs a page that looks like a deliberate choice for this product, not an AI template, and that follows a strict set of web interface guidelines (interaction, accessibility, motion, forms, performance, content). What makes it reliable is the rule that a design is never presented until it has passed an automated self-check and every issue has been fixed.

Two failures are designed out from the start. First, the "AI look", the default indigo gradient, round-everything, stock-card-grid page that appears no matter the brief; references/anti-ai-look.md names the tells and how to escape them. Second, the invisible-quality failures (no focus ring, motion that ignores reduced-motion preferences, layout-shifting images); the bundled scanner proves those before the design ships.

When to use

Trigger for any "design/build/mock up a page, landing page, screen, component, or interface", or "make this look better / redesign this". For a quick guideline check of an existing page, run scripts/ui-scan.mjs on it directly.

Inputs

  • what to design — the page or component, its purpose, and the audience (required).
  • brand / design system — existing colours, fonts, tokens, or components. If they exist, they win over any default choice.
  • content — the real copy and data, if available. If not, real copy is written; never lorem ipsum.
  • target — a self-contained HTML file (default) or the project's stack/component.

Process (the loop is mandatory)

1. Direction (references/agents/direction.md). Pin the subject, honour any existing brand or system, and commit to a specific visual direction and a token system (type scale, 8pt spacing, semantic colours grounded in the real brand, radius, elevation, motion) per references/design-tokens.md. Name the AI-look traps being avoided.

2. Build (references/agents/build.md). Produce the design against references/guidelines.md and the tokens: semantic HTML, one <h1>, real <button>/<a>, labelled forms, visible focus, contrast, reduced-motion-aware motion, explicit image dimensions, real content.

3. Self-check (do not skip). Save the design and run:

node scripts/ui-scan.mjs design.html

Then run the critique agent (references/agents/critique.md), a different agent than the builder, for the AI-look and judgement checks the script cannot make.

4. Fix, then re-check. Apply every high and medium finding and every guideline violation yourself, now, before showing anything. Re-run ui-scan.mjs until it exits clean and the critique passes. Never present a design with known issues and a "you could improve X" note; make the improvement.

5. Present only after it passes: the design first, then a short rationale (the direction and why it fits this product), then a one-line note on what the self-check covered and what still needs a human eye.

Principles

  • Deliberate, not default. The design must fail the "could this be any product?" test. Ground the palette, type, and layout in the subject; spend boldness in one place and keep the rest quiet.
  • Honour what exists. The user's wishes first, then the project's design system, then your choices. Never override a brand with a default.
  • Guidelines are gates, not tips. Visible focus, keyboard operability, reduced motion, contrast, real content, no layout shift, these are required, not optional polish.
  • Test then fix then present. A design is finished when the checks pass and the fixes are in, not when it is drawn. The builder never signs off its own work.
  • Honest about limits. The scan proves mechanical rules; taste, hierarchy, and copy are judgement, and real-device and screen-reader testing still matter.

Output

The working design (self-contained HTML by default, or the project's component), with real content, that passed the self-check. Plus a short rationale and a note on what was verified versus what still needs a human eye. See references/output-format.md.

What this skill will not do

  • It will not present an unchecked or unfixed design. The self-check and fixes are mandatory.
  • It will not ship lorem ipsum, a default AI look, or a design that ignores the accessibility and interaction guidelines.
  • It will not claim the design is perfect; it states what the scan covered and what still needs human review. For a deep accessibility audit of the finished page, use the accessibility-audit skill.

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 Interface Design AI skill do?

Design a page or UI on request that follows professional web interface guidelines and does not look AI-generated. Use when asked to design, build, or mock up a page, landing page, screen, component, or interface, or to improve how something looks. Commits to a specific visual direction and token system, builds to a strict guideline set, then runs a self-check and fixes every issue before presenting.

Why use Interface Design on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/creativedeals/free-claude-skill-interface-design/tree/main. 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 Interface 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 Interface Design?

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

Is the Interface Design AI skill free?

It is published on GitHub by creativedeals. Check the repository for licensing terms. 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 👇