Multimodal Task Prompt
Works identically on GPT-4o vision and Gemini multimodal. The structured format ensures both models extract the same categories of information rather than giving vague descriptions.
I'm sharing {{media_type}} with you. Analyze it and provide: 1. **Description**: What you see/hear in detail (be specific about elements, layout, colors, text) 2. **Key information extraction**: Pull out all data points, names, numbers, dates, or actionable items 3. **Quality assessment**: Rate the {{media_type}} quality on a 1-10 scale with justification 4. **Suggestions**: {{num_suggestions}} specific, actionable improvements 5. **Accessibility**: Note any accessibility concerns (alt text needed, contrast issues, readability) Format the extracted information as a structured table where applicable.
Variables to customize
Why this prompt works
Works identically on GPT-4o vision and Gemini multimodal. The structured format ensures both models extract the same categories of information rather than giving vague descriptions.
What you get when you save this prompt
Your workspace unlocks powerful tools to iterate and improve.
AI Optimization
One-click improvement with structure analysis and pattern suggestions.
Version History
Track every edit. Compare versions side-by-side with word-level diffs.
Folders & Tags
Organize your library with nested folders, tags, and drag-and-drop.
$ npm i -g @promptingbox/mcpUse Everywhere
Access prompts from Claude, Cursor, ChatGPT & more via MCP integration.
Your prompts, organized
Save, version, and access your best prompts across ChatGPT, Claude, Cursor, and more.