Dryui Build logo

Dryui Build

Community
rob-balfre
dryui-build

Experimental DryUI design-to-page skill that runs a three-stage pipeline: layout extraction, real DryUI composition, and visual QA repair. Use when testing full-page implementation from app mockup images.

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-8/v11a-contract-first
  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-8/v11a-contract-first .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 Full Page: Contract First

Build a real DryUI page from the supplied design image. This is not a colored-block skeleton, but the page must start from the same strict layout contract.

Experiment Harness Rule

Run bun run build before finishing. Do not run bun run dev, bun run check, or a long-running screenshot/browser server during the agent step; the experiment harness performs browser capture and visual scoring after you finish.

Only edit:

  • src/routes/+page.svelte
  • src/layout.css
  • src/app.css only for global font/body polish if needed

Stage 1: Extract The Layout

Before coding, classify the target:

  • dashboard: summary, chart/workspace, side insight/activity.
  • board: rail/nav, board columns as primary, inspector/activity as secondary.
  • crm: pipeline/table as primary, detail/forecast/activity as secondary or utility.
  • settings: form/content stack as primary, help/status/actions as secondary/utility.
  • knowledge: reader/workspace as primary, list/navigation and assistant/details around it.

Decide:

  • Mobile order.
  • Tablet grouping.
  • Desktop shell.
  • Whether adjacent sections touch (gap: 0) or have visible gutters.
  • Which region is the largest desktop primary.

Stage 2: Build Real UI

Use DryUI components for controls and UI primitives:

  • Prefer Button, Input, Badge, Table, Tabs, and Separator.
  • Use raw semantic elements for shell regions, headings, text, cards, charts, and decorative rectangles.
  • Do not use raw <button>, <input>, <select>, <textarea>, <form>, or <table> when a DryUI component exists.
  • Use realistic but concise content. Do not copy long mockup text, exact numbers, dates, names, or private-looking data from the image.
  • Keep the UI compact and work-focused. Avoid marketing hero sections, oversized cards, and decorative background blobs.
  • Use app-owned light surfaces for the page unless the reference is explicitly dark.

Markup Contract

Use one page shell:

svelte
<main data-layout="<page-type>-shell">
	<div data-layout-area="page">
		<header data-layout-area="topbar">...</header>
		<nav data-layout-area="navigation">...</nav>
		<section data-layout-area="primary">...</section>
		<aside data-layout-area="secondary">...</aside>
	</div>
</main>

Rules:

  • page, primary, and at least one of topbar or navigation are mandatory.
  • Shell areas may be rail, topbar, navigation, summary, primary, secondary, utility, actions.
  • Each shell area appears once.
  • Use data-layout-area only on [data-layout-area='page'] and direct shell children.
  • All nested elements use data-layout="<specific-name>", never data-layout-area.
  • Every raw interior element has a specific data-layout.

CSS Contract

In src/layout.css, use this exact responsive contract:

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

[data-layout='<page-type>-shell'] [data-layout-area='page'] {
	display: grid;
	grid-template-areas: ...;
	grid-template-columns: minmax(0, 1fr);
}

[data-layout='<page-type>-shell'] [data-layout-area='page'] > [data-layout-area='primary'] {
	grid-area: primary;
}

@container page (min-width: 48rem) {
}
@container page (min-width: 72rem) {
}

Hard rules:

  • Use exactly container: page / inline-size.
  • Use exactly @container page (min-width: 48rem) and @container page (min-width: 72rem).
  • Never use @media for layout.
  • All display, grid, flex, container, and responsive layout rules live in src/layout.css.
  • Route <style> is visual only: colors, borders, radius, shadows, type, internal padding, and block min-size.
  • Select shell areas with direct child selectors: [data-layout-area='page'] > [data-layout-area='<area>'].

Stage 3: Visual QA And Repair

After implementing:

  • Run bun run build.
  • Check 390px, 820px, and 1440px behavior, using screenshots if practical.
  • Repair horizontal overflow, dark-on-dark text, huge blank regions, wrong mobile order, and a non-dominant primary region.
  • The desktop page should use the viewport width; do not leave a small mockup floating in a large blank canvas.
  • The mobile page should collapse to a deliberate summary, not a dump of every desktop primitive.

Final Self-Check

  • @dryui/ui is imported and at least three DryUI components are used.
  • src/layout.css contains the exact page container and both exact container queries.
  • No @media, inline style=, style: directives, :global(), !important, or raw native controls.
  • No class props on DryUI components; style wrappers or use component props.
  • Primary is visually largest on desktop.

Frequently asked questions

What does the Dryui Build AI skill do?

Experimental DryUI design-to-page skill that runs a three-stage pipeline: layout extraction, real DryUI composition, and visual QA repair. Use when testing full-page implementation from app mockup images.

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-8/v11a-contract-first. 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 👇