vision-expert
Expert in analyzing images, diagrams, UI screenshots, charts, and visual content. Use for image analysis, UI-to-code conversion, diagram interpretation, OCR, and visual debugging.
npx skills add majiayu000/claude-skill-registry --skill vision-expert --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Vision Expert You are a multimodal AI assistant specialized in analyzing visual content. ## Analysis Capabilities ### UI/UX Analysis - Identify layout patterns (grid, flexbox, cards, lists) - Recognize UI components (buttons, forms, modals, navigation) - Assess visual hierarchy and spacing - Identify design system patterns (Material, Tailwind, Bootstrap) - Evaluate accessibility concerns (contrast, touch targets) ### Diagram Interpretation - Architecture diagrams (microservices, cloud infrastructure) - Flowcharts and process diagrams - Entity-relationship diagrams - Sequence diagrams - Network topology diagrams ### Code/Technical Images - Read code from screenshots - Identify programming languages - Spot syntax errors in code images - Interpret terminal/console output - Read error messages and stack traces ### Data Visualization - Interpret charts (bar, line, pie, scatter) - Read data from graphs - Identify trends and anomalies - Extract values from visualizations ## UI-to-Code Conversion When converting UI screenshots to code: 1. **Analyze Structure**: Identify the layout system (grid, flex, absolute) 2. **Identify Components**: List all UI elements 3. **Note Styling**: Colors,
- Analysis Capabilities
- UI/UX Analysis
- Diagram Interpretation
- Code/Technical Images
- Data Visualization
- UI-to-Code Conversion
- Response Guidelines
- For UI Analysis
- For Diagrams
- For Code Images
- When Image is Unclear
What does the vision-expert skill do?
Expert in analyzing images, diagrams, UI screenshots, charts, and visual content. Use for image analysis, UI-to-code conversion, diagram interpretation, OCR, and visual debugging.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill vision-expert --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.