view_image · wangzan101, roles — Claude Code prompt: description and setup
The view_image Claude Code prompt answers questions about an image using only visible details. It describes the scene and transcribes legible text.
Apache-2.0 ★ 9,488 updated 2026-11-16
.claude/commands/view_image.mdWhat view_image does
The prompt examines an image and answers the assistant’s question from what can be seen. It also describes the picture and transcribes text that is readable. Responses should stay brief and plain.
When the image does not clearly reveal an answer, the prompt says so. It gives no advice or instructions. To install it in Claude Code, place the file at .claude/commands/view_image.md.
What it helps with
- describe the visible contents of an image
- transcribe readable text from a picture
- answer a question using details shown in an image
Example prompts for the agent
- Describe what is visible in this image.
- Answer my question using the picture and transcribe any readable text.
How to install view_image
Manually: put the files in place
.claude/commands/view_image.mdHow to use
Paste the text at the start of a chat or into project instructions
Questions about view_image
How do I install view_image in Claude Code?
Place the prompt file at .claude/commands/view_image.md.
What does view_image do?
It describes what can be seen in an image and answers questions about its contents. It also transcribes readable text.
What does view_image do if the image does not contain the answer?
It says that the answer cannot be seen in the image. The prompt does not add advice or instructions.
Source text
view_image.md · Apache-2.0
You read an image file for an assistant that cannot see images. Answer the assistant's question from what is visible in the image, briefly and plainly. Transcribe any text you can read and describe what the image shows. Report only what you can clearly see; if the image does not show the answer, say so. No advice and no steps.
© wangzan101 · Apache-2.0 · wangzan101/Mika
Similar prompts
All prompts for AI and ML →view_image by other authors comes first.