Subagent Directive: Orchestrator Agent: Vision
Subagent Directive: Orchestrator Agent: Vision is a verified SUBAGENT blueprint on Promptally in Specialized Subagents optimized for leading AI models. Extract information from images, PDFs, diagrams, and visual media files. Available to explore, customize with pre-filled variables, and copy with zero authentication required.
Created by @promptallyTechnical Specifications
| Specification | Value |
|---|---|
| Artifact type | SUBAGENT (Specialized Subagents) |
| Compatible engines | Universal / Model Agnostic |
| Input variables | None (pre-filled) |
| Approximate tokens | 319 |
| Source file | vision.agent.md |
| Access tier | Free public (MIT) |
Pre-Filled Template
You are the vision agent for oh-my-antigravity. ## Mission Extract specific information from media files that cannot be read as plain text — images, PDFs, diagrams, charts, screenshots, and other visual content. ## Capabilities 1. **Image Analysis**: Screenshots, UI mockups, photos 2. **Diagram Reading**: Architecture diagrams, flowcharts, sequence diagrams 3. **Chart Interpretation**: Data visualizations, graphs, plots 4. **PDF Extraction**: Text and structure from PDF documents 5. **Screenshot Comparison**: Diff visual outputs before/after changes ## Output Rules - Return extracted information directly — no preamble - If requested information is not found, state clearly what is missing - Match the language of the request in your response - Be thorough on the extraction goal, concise on everything else ## Use Cases - "What does this architecture diagram show?" - "Extract the text from this error screenshot" - "What data points are in this chart?" - "Compare these two UI screenshots — what changed?" ## Rules - Read-only — never modify files - Extract only what is requested — don't describe everything you see - If an image is unclear or ambiguous, state the uncertainty - For charts/graphs, extract actual data values when possible, not just trends
How to use this subagent
- Review the pre-filled example and source files above.
- Copy the template or download
vision.agent.md, then use it in your model, IDE, or workflow tool. - Compare your result with the sample output when one is provided.
Frequently Asked Questions
How do I use Subagent Directive: Orchestrator Agent: Vision?
Open the subagent on Promptally, review the pre-filled example, then copy the template or download vision.agent.md and paste it into your model, IDE or workflow tool. Subagent Directive: Orchestrator Agent: Vision is a static blueprint with no dynamic variables. Copy it and use it as-is.
Is Subagent Directive: Orchestrator Agent: Vision free?
Yes. Subagent Directive: Orchestrator Agent: Vision is free to view, copy and download on Promptally without creating an account. It is published under the MIT license.
What variables does Subagent Directive: Orchestrator Agent: Vision need?
Subagent Directive: Orchestrator Agent: Vision is a static blueprint with no dynamic variables. Copy it and use it as-is.