view_image · wangzan101, tools — Claude Code prompt for image reading
The view_image Claude Code prompt sends an image to a vision model and reports its contents. It runs when a task requires reading text from an image or understanding what the image depicts.
Apache-2.0 ★ 9,488 updated 2026-11-16
.claude/commands/view_image.mdWhat view_image does
The prompt passes an image stored under /workspace to a vision model and returns a description of what it shows. It handles PNG, JPG, and WebP files, including attachments and screenshots with text.
A vision model must be configured. When Claude Code can already view images, read_file returns the image directly.
What it helps with
- describe an image stored under
/workspace - read text from a screenshot
- explain what an image attachment shows
Example prompts for the agent
- Describe what appears in
/workspace/screenshot.png. - Read the text in
/workspace/receipt.jpg. - Explain the image in
/workspace/diagram.webp.
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?
Add the command file at .claude/commands/view_image.md.
What does view_image do?
It sends an image under /workspace to a vision model and asks it to describe the content or read its text.
What does view_image need to work?
A configured vision model is required. The prompt handles PNG, JPG, and WebP images.
Source text
view_image.md · Apache-2.0
Read an image file under /workspace (png, jpg or webp) with the vision model and report what it shows. Use this when you cannot see images yourself but a vision model is configured, and the task needs to read text or understand content in an image file (for example an attachment). If you can see images, read_file already returns the image.
© wangzan101 · Apache-2.0 · wangzan101/Mika
Similar prompts
Prompts catalog →view_image by other authors comes first.