ui-composition

ui-composition is a skill for Claude Code from Owl-Listener/designpowers. It costs 39 tokens per session (1,048 once invoked), scanned A, original, MIT.

A visual design guide for arranging screens, choosing colours and type, and making layouts work across screen sizes. It also keeps accessibility in view, such as readable contrast and sensible zoom behaviour.

In plain words
What is it for?
Use it when creating page layouts, colour palettes, typography, spacing, responsive breakpoints, visual hierarchy, dark mode, or high-contrast versions.
Why use it?
It reduces guesswork in visual decisions and helps prevent designs that look good but are difficult for some people to read or use.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the designpowers plugin — 36 skills, 10 agents, 1 hook shipped together

Good fit Use it when creating page layouts, colour palettes, typography, spacing, responsive breakpoints, visual hierarchy, dark mode, or high-contrast versions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/owl-listener/designpowers/ui-composition
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 Owl-Listener/designpowers --skill ui-composition
Clone the repo
git clone --depth 1 https://github.com/Owl-Listener/designpowers

Made for: Claude Code.

Or install designpowers, the plugin that ships this one along with the rest of its 36 skills, 10 agents, 1 hook.

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 ui-composition

README.md
[![agentmods](https://agentmods.dev/badge/skills/owl-listener/designpowers/ui-composition/github.svg)](https://agentmods.dev/skills/owl-listener/designpowers/ui-composition)
Your own site
<a href="https://agentmods.dev/skills/owl-listener/designpowers/ui-composition"><img src="https://agentmods.dev/badge/skills/owl-listener/designpowers/ui-composition/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 ui-composition

Your own site · 80×15
<a href="https://agentmods.dev/skills/owl-listener/designpowers/ui-composition"><img src="https://agentmods.dev/badge/skills/owl-listener/designpowers/ui-composition.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 1,048 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 $0.01048
Opus 5.5 $0.00016 $0.00419
Sonnet 5.5 $0.00008 $0.00210
Haiku 4.5 $0.00004 $0.00105

Measured 1mo ago against content hash 0ccf865f5ec2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ui-composition 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 1mo 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.

skills/ui-composition/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UI Composition

Visual design is where intent becomes tangible. Every colour, every spacing decision, every typographic choice either includes or excludes people. This skill ensures visual decisions are principled, systematic, and inclusive.

When to Use

  • Designing screen layouts or page structures
  • Choosing or refining colour palettes
  • Setting typography systems
  • Establishing spacing and grid systems
  • Designing for responsive breakpoints
  • Creating or modifying visual hierarchy
  • Designing dark mode or high contrast variants

Process

Step 1: Reference the Foundation

Before making visual decisions, confirm you have:

  • Design brief or strategy (from earlier phases)
  • Personas (especially ability spectrum considerations)
  • Existing design system (invoke design-system-alignment if one exists)

Step 2: Layout and Structure

Grid system:

  • Define columns, gutters, and margins
  • Ensure the grid adapts across breakpoints (mobile, tablet, desktop)
  • Test that content reflows sensibly when zoomed to 200%

Visual hierarchy:

  • Establish a clear reading order that works both visually and in the DOM
  • Ensure the hierarchy communicates through structure, not colour alone
  • Verify that removing all colour still leaves a readable, navigable page

Spacing system:

  • Use a consistent spacing scale (e.g., 4px base)
  • Ensure touch targets are at least 44x44px
  • Provide adequate spacing between interactive elements to prevent accidental activation

Step 3: Colour

Palette construction:

  • Define primary, secondary, neutral, and semantic colours (success, warning, error, info)
  • Every colour pairing must meet WCAG AA contrast ratios minimum (4.5:1 for text, 3:1 for large text and UI components)
  • Target WCAG AAA (7:1) where feasible

Colour independence:

  • Never convey information through colour alone
  • Always pair colour with text labels, icons, or patterns
  • Test with simulated colour blindness (protanopia, deuteranopia, tritanopia)

Dark mode / high contrast:

  • If applicable, design dark mode as a first-class experience, not an afterthought
  • Ensure all contrast ratios hold in both modes
  • Respect prefers-color-scheme and prefers-contrast media queries

Read the full file on GitHub · 118 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. 1mo ago First seen · 118 lines · 39 tokens per session scan A 0ccf865f5ec2

Subscribe to this mod's changes

ui-composition is a skill published in the GitHub repository Owl-Listener/designpowers (254 stars, last pushed 4mo ago), licensed MIT. It adds 39 tokens to every session and 1,048 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.

Related

Other skills, from other repositories

anti-slop-frontend

A mechanical, countable anti-slop checklist for AI-generated frontend. Catches the specific signatures an undirected model defaults to: AI-purple glows, Inter-everywhere, em-dashes, div-based fake screenshots, eyebrow-on-every-section, beige+brass "premium" palettes, generic Jane Doe / Acme data. Advisory layer that…

BlackBeltTechnology/pi-agent-dashboard · 147 tokens

accessibility-a11y

Semantic HTML, keyboard navigation, focus states, ARIA labels, skip links, and WCAG contrast requirements. Use when ensuring accessibility compliance, implementing keyboard navigation, or adding screen reader support.

BlackBeltTechnology/pi-agent-dashboard · 44 tokens

tailwind-shadcn

Tailwind CSS utility patterns with shadcn/ui component usage, theming via CSS variables, and responsive design. Use when styling components, installing shadcn components, implementing dark mode, or creating consistent design systems.

BlackBeltTechnology/pi-agent-dashboard · 50 tokens

frontend-mockup-loop

Plan, build, and iterate UX-friendly frontend mockups via a ground→contract→mockup→test→fix→learn loop, acting as an expert UX designer who grounds every decision in externally documented public design rules (Nielsen heuristics, Laws of UX, WCAG, GOV.UK/USWDS/Material). Uses the bundled servemockup, scoremockup, and…

BlackBeltTechnology/pi-agent-dashboard · 185 tokens

mcp-host-styling-integration

Integrates MCP App UI with host theming system. Applies host CSS variables, handles onhostcontextchanged, safe area insets, display mode detection, and fullscreen configuration.

a5c-ai/babysitter · 44 tokens

craft-studio

Router for the ArtCraft craft apps (PhotoCraft, VectorCraft, FilmCraft, LightCraft, PdfCraft, EffectCraft, DesignCraft, FigCraft, WordCraft, SoundCraft, DeckCraft, CADCraft, GridCraft) driven headless via pi-craft. Use to choose which app fits a job and run the discover-execute-save-verify loop - "which craft app…

BlackBeltTechnology/pi-agent-dashboard · 103 tokens