dryui-build

dryui-build is a skill for Claude Code, Codex from rob-balfre/dryui. It costs 39 tokens per session (850 once invoked), scanned A, original, MIT.

An experimental workflow for building a complete DryUI page from an app mockup image and repairing it through screenshot-based checks.

In plain words
What is it for?
Choosing a page layout, implementing it in Svelte files, and running the required build step for a DryUI experiment.
Why use it?
It helps resolve uncertain layout choices and catch visual problems before the page is finished, including on desktop, tablet, and mobile.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Choosing a page layout, implementing it in Svelte files, and running the required build step for a DryUI experiment.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rob-balfre/dryui/v11e-qa-tournament
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add rob-balfre/dryui --skill v11e-qa-tournament
Clone the repo
git clone --depth 1 https://github.com/rob-balfre/dryui

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for dryui-build

README.md
[![agentmods](https://agentmods.dev/badge/skills/rob-balfre/dryui/v11e-qa-tournament/github.svg)](https://agentmods.dev/skills/rob-balfre/dryui/v11e-qa-tournament)
Your own site
<a href="https://agentmods.dev/skills/rob-balfre/dryui/v11e-qa-tournament"><img src="https://agentmods.dev/badge/skills/rob-balfre/dryui/v11e-qa-tournament/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for dryui-build

Your own site · 80×15
<a href="https://agentmods.dev/skills/rob-balfre/dryui/v11e-qa-tournament"><img src="https://agentmods.dev/badge/skills/rob-balfre/dryui/v11e-qa-tournament.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 850 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00039 $0.00850
Opus 5 $0.00019 $0.00425
Sonnet 5 $0.00008 $0.00170
Haiku 4.5 $0.00004 $0.00085

Measured 11d ago against content hash 712904426eef, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

dryui-build scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

reports/skill-experiments/2026-05-11/batch-8/v11e-qa-tournament/SKILL.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DryUI Full Page: QA Tournament

Build a finished DryUI page from the supplied app mockup image. Use a short internal tournament before coding: consider three layouts, pick the strongest, then implement and repair.

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, and src/app.css if necessary.

Internal Tournament

Consider three candidates:

  • Faithful: closest to the visual shell in the image.
  • Dense: best use of desktop and tablet space.
  • Mobile-first: best mobile order and reduction.

Pick the candidate that best satisfies:

  • primary task is obvious;
  • responsive behavior is clear;
  • desktop fills the canvas;
  • mobile is useful;
  • DryUI components can represent the details without brittle APIs.

Do not write the tournament into the UI.

Implementation Stages

Stage 1: layout map

  • classify page as dashboard, board, CRM, settings, or knowledge;
  • choose shell regions;
  • choose mobile order, tablet split, desktop grid;
  • decide guttered vs contiguous sections.

Stage 2: real DryUI page

  • import @dryui/ui;
  • use at least three of Button, Input, Badge, Table, Tabs, Separator;
  • use simple static blocks for charts, document surfaces, boards, and previews;
  • use concise invented content aligned to the app type;
  • avoid copying exact mockup numbers, dates, names, and paragraphs.

Stage 3: repair

  • run bun run build;
  • check 390px, 820px, and 1440px;
  • repair overflow, blank space, dark-on-dark surfaces, over-large side panels, and poor mobile order.

Required Shell Contract

<main data-layout="<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>

Read the full file on GitHub · 104 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 104 lines · 39 tokens per session scan A 712904426eef

Subscribe to this mod's changes

dryui-build is a skill published in the GitHub repository rob-balfre/dryui (9 stars, last pushed 3mo ago), licensed MIT. It adds 39 tokens to every session and 850 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

frontend-design

Create distinctive, production-grade frontend interfaces with high design quality and accessible markup. Use this skill when the user asks to build or beautify web components, pages, applications, landing pages, dashboards, artifacts, or React/HTML/CSS UI. Generates creative, polished code that avoids generic AI…

spinspire/pocketbase-sveltekit-starter · 76 tokens

shadcn-sveltekit-design

Use when building, redesigning, beautifying, or refactoring SvelteKit pages and reusable components with shadcn-svelte, Bits UI, or the shadcn-svelte MCP. Trigger on landing pages, dashboards, marketing sites, app shells, forms, navbars, tables, dialogs, responsive layouts, theming, icon selection, and requests to…

Michael-Obele/shadcn-svelte-mcp · 99 tokens

popular-web-designs

54 real design systems (Stripe, Linear, Vercel) as HTML/CSS.

NousResearch/hermes-agent · 23 tokens

oat-css

Our preferred CSS framework — ultra-lightweight, semantic HTML UI library (8KB). Style web UIs with semantic HTML and minimal classes. Override with app-level SCSS only when necessary.

spinspire/pocketbase-sveltekit-starter · 42 tokens

component-search

Search 21st.dev component registry for production-ready React components. Finds components by natural language description, filters by framework and style system, returns ranked results with install instructions. Use when looking for UI components, finding alternatives to existing components, or sourcing design system…

yonatangross/orchestkit · 57 tokens

polish-ui

Design-quality workflow that combines design taste, aesthetic direction, image-to-code, a Web Interface Guidelines audit, and real-browser verification. Use when building or polishing a UI surface, implementing a mockup/screenshot, or when asked to make a page "look great".

fpindej/netrock · 53 tokens