TypingMindTypingMindThe best frontend for AI
Dryui Build Experiment B logo

Dryui Build Experiment B

Community
rob-balfre
dryui-build-experiment-b

Experimental DryUI UI build workflow using mandatory gates and checklists. Use when testing whether explicit gates improve low-reasoning layout reliability.

Overview

Publisherrob-balfre
Repositorydryui
Skill namedryui-build-experiment-b
Stars
9
Forks
0
Bundled files
1
LicenseMIT
Links
Skill sourceRepositoryHomepage
  • 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.

  • 1 bundled files

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

  • Open source

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

Installation

Install the Dryui Build Experiment B 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/variant-b-gated-workflow
  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/variant-b-gated-workflow .claude/skills/dryui-build-experiment-b
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Dryui Build Experiment B 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 Experiment B 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 Experiment B 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 Build Experiment B: Gated Workflow

Gate 1: Target Brief

Write this before implementation:

text
Target brief: type=<page|section|component|form|polish>, subtype=<dashboard|marketing|docs|settings|other>, user=<role>, primary_task=<task>, density=<compact|standard|spacious>, required_states=<states>.

If type=page, continue to Gate 2. If subtype=dashboard, apply the dashboard add-on in Gate 3.

Gate 2: Page Layout Contract

For any full page:

  • One page root owns data-layout="<name>".
  • That root creates container: <name> / inline-size.
  • Every structural child gets data-layout-area.
  • src/layout.css owns page and section structure.
  • Route/component <style> blocks do not contain display: grid, display: flex, layout breakpoints, inline style, or Svelte style:.
  • Responsive structure uses @container <name> only.
  • Base layout is mobile-first.
  • src/layout.css contains structure only: display, grid/flex, container, gap, alignment, spacing, and block-size constraints.

Stop and fix the plan if any bullet cannot be satisfied.

Gate 3: Dashboard Add-On

For dashboard/data pages:

  • Primary task is one of monitor, compare, triage, report, configure, or act.
  • Metrics are grouped by meaning, not decoration.
  • The largest region belongs to the most important data view.
  • Filters/actions sit before the data they affect.
  • A table uses Table or DataGrid; a chart uses Chart or Sparkline.
  • Cards are allowed for KPIs, alerts, and distinct comparison units; cards are not allowed as page scaffolding.
  • Dense data must not depend on hover-only controls.
  • Include loading, empty, error, and dense-data states.

Gate 4: Markup Draft

Draft markup in this order:

  1. Page root.
  2. Semantic regions.
  3. DryUI components.
  4. Raw structural elements with data-layout or data-layout-area.
  5. State branches.

Avoid generic names: wrapper, container, box, layout, inner, outer.

Gate 5: Layout CSS Draft

Draft src/layout.css in this order:

  1. Page root selector with container.
  2. Mobile base grid.
  3. Area selectors.
  4. Container queries for tablet/desktop.
  5. State-safe constraints for media/text overflow.

Do not add visual styling to src/layout.css.

Gate 6: Self-Review

Before finishing, answer:

  • Does the route have no page-level layout CSS in component styles?
  • Does every raw structural element have a matching layout reason?
  • Does the dashboard still have a clear primary task on mobile?
  • Are loading, empty, error, and dense-data states represented?
  • Would DryUI lint reject any rule?

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 Dryui Build Experiment B AI skill do?

Experimental DryUI UI build workflow using mandatory gates and checklists. Use when testing whether explicit gates improve low-reasoning layout reliability.

Why use Dryui Build Experiment B on TypingMind?

Because you install it once and use it with any model. Dryui Build Experiment B 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 Experiment B 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/variant-b-gated-workflow. 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 Dryui Build Experiment B?

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 Experiment B?

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

Is the Dryui Build Experiment B 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.

Related AI Skills

View all
openclaw logo

Openclaw Test Heap Leaks

openclaw
OrganizationPopular

Investigate OpenClaw pnpm test memory growth, Vitest OOMs, RSS spikes, and heap snapshot deltas.

82.2K
391K
2 files
View
openclaw logo

Prototype Openclaw Tui

openclaw
OrganizationPopular

Build throwaway, fixture-driven OpenClaw Clack or Pi TUI prototypes and compare multiple interactive variants side by side in tmux without running the full application or touching live state.

82.2K
391K
2 files
View
openclaw logo

Slacrawl

openclaw
OrganizationPopular

Slack archive: search, sync freshness, threads/DMs, SQL counts, and Slacrawl repo work.

82.2K
391K
1 files
View
openclaw logo

Obsidian Vault Maintainer

openclaw
OrganizationPopular

Maintain an Obsidian-friendly memory wiki vault with wikilinks, frontmatter, and official Obsidian CLI awareness.

82.2K
391K
Instructions
View

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇