Open Claude Design Quality logo

Open Claude Design Quality

Community
maxritter
open-claude-design-quality

Apply product-grounded visual quality constraints during user-visible UI changes. Use for layout, styling, content hierarchy, theming, responsive behavior, or interaction affordances. Stay inactive for logic-only changes that preserve the rendered interface.

Overview

Publishermaxritter
Repositoryopen-claude-design
Skill nameopen-claude-design-quality
Stars
38
Forks
4
Bundled files
3
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.

  • 3 bundled files

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

  • Open source

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

Installation

Install the Open Claude Design Quality 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/maxritter/open-claude-design/tree/main/skills/open-claude-design-quality
  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/maxritter/open-claude-design.git /tmp/open-claude-design
mkdir -p .claude/skills
cp -r /tmp/open-claude-design/skills/open-claude-design-quality .claude/skills/open-claude-design-quality
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Open Claude Design Quality 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 Open Claude Design Quality 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 Open Claude Design Quality 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.

UI Design Quality

Apply these stable constraints to user-visible interface work. Preserve the rendered interface during logic-only changes; do not broaden them into redesigns.

When a selected design workflow requires independent assessors or finish reviewers, that workflow requirement plus an exposed agent tool is sufficient authorization to delegate the bounded review. Use the minimum required agents and do not ask a routine permission question.

Start from the product

Preserve the current visual language unless the user asks to change it. Read the relevant components, tokens, theme, screenshots, brand guidance, and neighboring screens before making visual decisions. Exact project values outrank generic design advice.

Precedence when sources disagree: accessibility and interaction safety first, then the product's tokens and components, then the measurable craft rules in references/craft.md, then taste. Read that reference when choosing or checking a concrete value the product does not define: type scale and floors, heading roles, spacing tiers, control rows, nested radii, color budget, or feedback timing.

  • Keep the project's component library, CSS methodology, icon set, typefaces, spacing scale, radii, shadows, and motion language.
  • Reuse real product content and assets. Do not invent testimonials, statistics, features, destinations, or decorative copy to fill space. A missing image, icon, or illustration gets a labeled placeholder, never a hand-drawn SVG substitute.
  • Treat an absent design system as a decision point, not permission to fall back to a generic template. Establish a small coherent direction tied to audience, purpose, and tone.

Make the hierarchy legible

  • A first-time user can identify the page purpose, primary information, and next action without hunting.
  • Use size, weight, color, position, and density deliberately. Do not make every element equally loud or equally muted.
  • Give each screen a clear primary action when the product flow has one. Dashboards and multi-tool workspaces may legitimately support several peer actions.
  • Remove filler and duplicate explanation. Empty space is resolved through composition, not invented content.
  • Use the project's type, color, and spacing scales. New values become tokens or documented variants rather than isolated literals.

Build a system, not a screenshot

  • Prefer reusable components and variants over one-off page markup.
  • Space sibling elements with flex or grid gap on the project's scale rather than per-element margins or inline whitespace.
  • Cover the states the interaction can actually enter: default, hover when applicable, active or selected, focus, disabled, loading, empty, success, and error.
  • Keep current state and action feedback visible. Disabled controls explain unmet prerequisites when the reason is not otherwise clear.
  • Motion communicates change or spatial relationship, remains brief, and respects reduced-motion preferences.
  • Design responsive behavior at content-driven widths, including long copy and narrow containers. Check dark and light themes independently when both exist.

Avoid unearned template language

These are review prompts, not blanket bans. Keep a pattern when it comes from the product's established system or has a clear semantic purpose.

  • Gratuitous gradients, glass surfaces, emoji decoration, and ornamental SVG scenes
  • Repeated icon-heading-paragraph card grids when a list, table, comparison, or prose structure communicates better
  • Colored side borders used as decoration rather than callout, quote, status, or selection semantics
  • Default-model house styles chosen without reference to the brief or product
  • Arbitrary fonts, colors, spacing, and animation values that do not trace to a system
  • Multiple variations that differ only cosmetically rather than in hierarchy, layout, interaction, density, or tone

Completion check

  • Existing design context was inspected and preserved or intentionally changed.
  • Content is real, necessary, and concise.
  • Hierarchy, component reuse, interaction states, responsive behavior, and supported themes are coherent.
  • Accessibility and actual interaction are verified with the repository's named UI driver or the browser, simulator, or device automation available to the active agent.
  • Advisory detector findings were judged against product context rather than applied mechanically.

Impeccable integration

When Impeccable is installed, Open Claude Design remains the owner of the overall design task. Use Impeccable for its named refinements, supporting agents, hook evidence, and deterministic detector; do not start a second competing redesign workflow or rerun a detector whose current hook findings are already available.

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 Open Claude Design Quality AI skill do?

Apply product-grounded visual quality constraints during user-visible UI changes. Use for layout, styling, content hierarchy, theming, responsive behavior, or interaction affordances. Stay inactive for logic-only changes that preserve the rendered interface.

Why use Open Claude Design Quality on TypingMind?

Because you install it once and use it with any model. Open Claude Design Quality 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 Open Claude Design Quality in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/maxritter/open-claude-design/tree/main/skills/open-claude-design-quality. 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 Open Claude Design Quality?

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 Open Claude Design Quality?

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

Is the Open Claude Design Quality AI skill free?

It is published on GitHub by maxritter. 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 👇