Dryui Build logo

Dryui Build

Community
rob-balfre
dryui-build

Experimental DryUI layout-only skill that preserves visual hierarchy and region proportions from app screenshots using weighted colored blocks. Use when testing page layout extraction for dashboards, workspaces, boards, readers, and admin pages.

Overview

Publisherrob-balfre
Repositorydryui
Skill namedryui-build
Stars
9
Forks
0
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by rob-balfre on GitHub. Read the source before you install it.

Installation

Install the Dryui Build 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/rob-balfre/dryui/tree/main/reports/skill-experiments/2026-05-11/batch-6/v3-proportion-weights
  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/rob-balfre/dryui.git /tmp/dryui
mkdir -p .claude/skills
cp -r /tmp/dryui/reports/skill-experiments/2026-05-11/batch-6/v3-proportion-weights .claude/skills/dryui-build
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Dryui Build 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 Dryui Build 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 Dryui Build 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.

DryUI Layout Blocks: Proportion Weights

Create only labelled colored layout blocks. The output proves region hierarchy, not finished UI.

Allowed edits:

  • src/routes/+page.svelte
  • src/layout.css

No imports, components, icons, images, charts, tables, forms, buttons, inputs, avatars, or realistic widgets.

Region Weighting

Before coding, classify every visible region:

  • primary: the dominant workspace, board, reader, canvas, or form.
  • secondary: inspector, AI panel, account detail, task detail, help panel.
  • chrome: top bar, nav, rails, tabs, action bar.
  • summary: KPI strips, filters, quick stats.
  • utility: activity, recent updates, footer tools.

The generated layout must preserve these weights:

  • primary is largest at every breakpoint.
  • Desktop primary normally gets minmax(0, 1fr) or larger.
  • secondary is narrower than primary unless the reference shows equal panes.
  • chrome is compact but persistent when visible in the reference.
  • Utility regions must not push the primary workspace below the fold on desktop.

Page Structure

Use exactly one shell:

svelte
<main data-layout="<name>-shell">
	<div data-layout-area="page">...</div>
</main>

Use direct semantic child regions with meaningful data-layout-area names.

Layout CSS

Only src/layout.css may contain grid/flex/container rules.

css
[data-layout='<name>-shell'] {
	container: <name> / inline-size;
}

[data-layout='<name>-shell'] [data-layout-area='page'] {
	display: grid;
	grid-template-areas:
		'topbar'
		'navigation'
		'primary'
		'secondary';
}

@container <name> (min-width: 48rem) {
}
@container <name> (min-width: 72rem) {
}

Container name and query name must match exactly.

Proportion Tools

Use these in src/layout.css when they match the reference:

  • grid-template-columns: minmax(0, 1fr) minmax(14rem, 0.32fr);
  • grid-template-columns: 14rem minmax(0, 1fr) 18rem;
  • grid-template-rows: auto auto minmax(24rem, 1fr) auto;
  • min-block-size on primary reader/board/workspace regions.
  • align-items: stretch for pane layouts.

Do not make desktop all regions equal-height or equal-width unless the reference clearly does.

Responsive Rules

  • Mobile base: one column only.
  • Tablet 48rem: introduce two-column content only after top chrome/summary.
  • Desktop 72rem: use desktop pane proportions from the reference. If the design has a reader/document/workspace pane, it must be tall and dominant.

Spacing

Preserve reference spacing as contiguous, guttered, or mixed. Guttered uses tokenized gaps; contiguous uses gap: 0 and no unintended body background.

Styling

Route <style> handles only color, borders, readable labels, and typography. Use distinct colors with strong contrast.

Failure Gates

  • Primary workspace is not visually dominant.
  • Desktop reader/board/workspace is a shallow horizontal strip.
  • Desktop side panels consume more space than the primary region.
  • Missing matched container: and @container names.
  • Imports, components, icons, images, charts, tables, forms, buttons, inputs.
  • Horizontal overflow or clipped labels at 390px, 820px, or 1440px.

Frequently asked questions

What does the Dryui Build AI skill do?

Experimental DryUI layout-only skill that preserves visual hierarchy and region proportions from app screenshots using weighted colored blocks. Use when testing page layout extraction for dashboards, workspaces, boards, readers, and admin pages.

Why use Dryui Build on TypingMind?

Because you install it once and use it with any model. Dryui Build 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 Dryui Build in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/rob-balfre/dryui/tree/main/reports/skill-experiments/2026-05-11/batch-6/v3-proportion-weights. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Dryui Build?

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 Dryui Build?

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

Is the Dryui Build AI skill free?

Yes. It is published on GitHub by rob-balfre 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 👇