Ui Like Corbin logo

Ui Like Corbin

Community
crutchcorn
ui-like-corbin

Build and revise user interfaces using Corbin Crutchley's accessibility and visual consistency preferences. Use for changes to interactive UI, responsive layouts, themes, or visual styling. Treat keyboard access, screen-reader behavior, focus, and zoom as correctness; verify the changed interface in the running app without expanding the task into a full accessibility audit.

Overview

Publishercrutchcorn
Repositoryskills
Skill nameui-like-corbin
Stars
56
Forks
0
Bundled files
2
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.

  • 2 bundled files

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

  • Open source

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

Installation

Install the Ui Like Corbin 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/crutchcorn/skills/tree/main/ui-like-corbin
  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/crutchcorn/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/ui-like-corbin .claude/skills/ui-like-corbin
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ui Like Corbin 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 Like Corbin 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 Like Corbin 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 Like Corbin

Make the requested interface usable across input methods, display sizes, and user preferences. Reuse the existing design system and verify the result as a user would experience it.

Follow the design system

  • Reuse existing components and design tokens for spacing, colors, and radii before introducing new values or variants.
  • Match the surrounding interface's interaction and layout conventions. Add a new pattern only when the requested behavior needs it.
  • Use proper icon components from the project's icon system instead of Unicode characters as UI icons. Give meaningful icons accessible names through the control or appropriate labeling; keep decorative icons from adding redundant announcements.
  • Keep changes scoped to the requested interface. Do not introduce a design-system migration as part of an ordinary UI edit.

Treat accessibility as behavior

Keyboard interaction, screen-reader behavior, focus, and zoom are part of correctness, not optional polish.

  • Prefer native semantic controls and existing accessible components. Expose the name, role, state, and relationships users need to understand the interaction.
  • Make the changed flow work with a keyboard. Verify that each focused control has a visible indicator in the changed interface, including reused design-system controls. Moving, trapping, or restoring focus does not establish that its indicator is visible. Keep focus in a logical order and manage it deliberately when content opens, closes, or changes context.
  • Make errors, status changes, and required input understandable without relying on color or visual position alone.
  • Ensure text resizing and browser zoom preserve access to content and controls. Check that the changed layout can reflow without hiding essential actions.
  • Use screen-reader verification for interactions whose announcements or focus behavior changed when the environment supports it. An accessibility-tree inspection can help, but does not by itself demonstrate the full screen-reader experience.

Apply these checks to the behavior being changed. Do not expand a focused implementation into an unsolicited audit of the entire product.

Respect user preferences and customization

  • Honor reduced-motion preferences in the motion being introduced or changed. Preserve understandable state changes without requiring unnecessary movement.
  • Honor contrast preferences and maintain readable contrast and visible control and focus states across the supported themes.
  • Respect light/dark preferences and preserve an explicit in-app theme selection when one exists. Do not force a theme change as a side effect of an unrelated UI edit.
  • Prefer CSS custom properties for theme values over JavaScript effects that synchronize styles. JavaScript can retain responsibility for the user's selected preference and persistence.
  • When theme customization is part of the feature, keep its controls keyboard and screen-reader accessible, and ensure the resulting themes preserve readable text, discernible controls, and visible focus.

These preferences guide the feature in scope; they do not require adding a new theme editor or preference system to every application.

Review the running interface

Verify the changed flow with this sequence:

  1. Launch the real application and open its existing route or preview. Inspect the changed interface at both mobile and larger viewport sizes, with the surrounding context visible.
  2. Exercise the actual interaction and relevant loading, empty, error, and success states. Check keyboard operation, visible focus, and focus movement.
  3. Check layout, content overflow, zoom, and text, control, and focus-indicator contrast across the supported themes affected by the work. Verify relevant motion preferences too.

If execution is unavailable, report that limitation and what was checked instead, then give this same sequence as the concrete work still pending. Do not describe source inspection or an unlaunched preview as a completed visual review.

Visual review can include temporary screenshots for inspection. Do not introduce screenshot regression tests unless the user specifically asks for them.

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 Ui Like Corbin AI skill do?

Build and revise user interfaces using Corbin Crutchley's accessibility and visual consistency preferences. Use for changes to interactive UI, responsive layouts, themes, or visual styling. Treat keyboard access, screen-reader behavior, focus, and zoom as correctness; verify the changed interface in the running app without expanding the task into a full accessibility audit.

Why use Ui Like Corbin on TypingMind?

Because you install it once and use it with any model. Ui Like Corbin 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 Like Corbin in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/crutchcorn/skills/tree/main/ui-like-corbin. 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 Ui Like Corbin?

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 Like Corbin?

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

Is the Ui Like Corbin AI skill free?

It is published on GitHub by crutchcorn. 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 👇