OpenParable
Skip to content
← Back to skills

UI Screenshot Composition

Design
ui-screenshot-composition

UI Screenshot Composition is an Agent Skill for design published in the TheGoat395/Codex-Skills repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Compose UI screenshots inside website layouts. Use for product sections, feature blocks, app showcases, case studies, dashboards, mockup stacks, detail crops, callout overlays, annotation systems, responsive screenshot art direction, and avoiding generic SaaS screenshot-card sections.

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/TheGoat395/Codex-Skills/blob/HEAD/skills/ui-screenshot-composition/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/ui-screenshot-composition, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

UI Screenshot Composition

Use this skill to turn UI screenshots into a designed evidence system, not a pile of framed rectangles.

Workflow

  1. Inspect the project, media assets, framework image/video APIs, responsive breakpoints, accessibility requirements, and verification commands.
  2. Read UI Screenshot Composition Guide for detailed direction before changing visuals or code.
  3. Define the media's job: proof, desire, navigation, instruction, atmosphere, conversion, or accessibility.
  4. Implement with stable dimensions, responsive crops, useful fallbacks, and real content hierarchy.
  5. Inspect rendered desktop and mobile states, then refine crop, contrast, loading, labels, captions, and polish.

Always Protect

  • Inspect before coding: framework, image/video components, asset folders, CMS or source content, styling system, responsive breakpoints, performance checks, accessibility checks, and available browser QA commands.
  • Treat images and video as content strategy, not decoration: every asset should reveal the real product, person, venue, object, interface, proof, or mood needed by the page.
  • Avoid generic stock-like visuals, dark blurred filler, random gradients, and media that crops away the subject users need to inspect.
  • Plan desktop, mobile, high-density, slow-network, reduced-motion, no-autoplay, failed-asset, and screen-reader states.
  • Reserve layout space with dimensions, aspect-ratio, CSS constraints, or framework image components to avoid layout shift.
  • Use meaningful alt text for informative images, empty alt for decorative images, captions/transcripts/tracks for media that needs them, and visible text for critical information.
  • Before delivery, inspect rendered desktop and mobile media crops, verify assets load without 404s, and run available lint/build/test/browser checks.