Stats
Actions
Tags
From team-shinchan
Analyzes images, PDFs, screenshots, and mockups visually. Provides UI component breakdown, text extraction, design pattern identification, and links findings to the codebase.
How this skill is triggered — by the user, by Claude, or both
Slash command
/team-shinchan:visionThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
```
If args is empty or only whitespace:
Ask user: "What image or PDF would you like me to analyze? (provide file path or describe)"
STOP and wait for user response
If args length > 2000 characters:
Truncate to 2000 characters
Warn user: "Request was truncated to 2000 characters"
Do not read further. Execute this Task NOW:
Task(
subagent_type="team-shinchan:ume",
model="sonnet",
prompt=`/team-shinchan:vision has been invoked.
## Visual Content Analysis Request
Analyze visual content including:
| Type | Capabilities |
|------|-------------|
| Screenshots | UI analysis, layout, components |
| Mockups | Design patterns, specifications |
| Diagrams | Architecture, flowcharts, ERDs |
| PDFs | Document extraction, summaries |
| Images | General visual content analysis |
## Analysis Requirements
- Describe visual elements in detail
- Identify UI components and patterns
- Extract text content where applicable
- Note design patterns used
- Connect with codebase (search for related files)
## Output Format
- Visual element breakdown
- Component identification
- Text extraction (if any)
- Related code references (if found)
- Actionable insights
User request: ${args || '(Please describe what to analyze)'}
`
)
STOP HERE. The above Task handles everything.
npx claudepluginhub seokan-jeong/team-shinchan --plugin team-shinchanGuides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.