Skip to main content
prompt GP ChatGPT

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

Install into Claude Code · Manually: put the files in place All methods and platforms ↓
.claude/commands/view_image.md
Open on GitHub

What 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.md

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.

view_image wangzan101 The view_image Claude Code prompt answers questions about an image using only visible details. It describes the scene and transcribes legible text. GP ChatGPT ★ 9,488repo stars vercel-react-view-transitions vercel vercel-react-view-transitions — a skill that walks your agent through native view transitions in React: page changes, shared elements, enter and exit animations without third-party libraries. CX Codex +1 197,400installs view-pdf official anthropics view-pdf opens PDFs in an interactive viewer for shared markup, form filling, highlights, stamps, and visual signatures. Use it when text reading alone is not enough. CX Codex +1 6,500installs platform-list-view-generate forcedotcom platform-list-view-generate generates Salesforce List View XML metadata: filters, columns, visibility settings. Validates operator-field type compatibility and file structure before deployment. CX Codex +1 5,900installs view-transitions patterns.dev Teaches your agent the View Transitions API, so page and UI state changes animate without hand-written animation code. CX Codex +1 707installs scenario-side-view-game-kit scenario-labs scenario-side-view-game-kit generates 2D platformer pixel art, character sprite sheets, and layered level graphics with Scenario models and local scripts. CX Codex +1 691installs choosing-trend-or-slope-view PostHog choosing-trend-or-slope-view — a skill that settles what “change over time” means before a chart gets built: the full trend interval by interval, or only the gap between the two ends. CX Codex +1 204installs

From the same set132

The whole set →
run_command This Claude Code prompt runs shell commands in a Linux sandbox. Commands use /bin/sh -lc with /workspace as the working directory. GP ChatGPT ★ 9,488repo stars view_image The view_image Claude Code prompt answers questions about an image using only visible details. It describes the scene and transcribes legible text. GP ChatGPT ★ 9,488repo stars list_elements The list_elements Claude Code prompt turns the current screen into a text list instead of a screenshot. Each item gets a reference for later actions. GP ChatGPT ★ 9,488repo stars mika_open_file The mika_open_file Claude Code prompt opens workspace files in Mika’s built-in viewer. Show a report, screenshot, or downloaded document. GP ChatGPT ★ 9,488repo stars phone_event phone_event — a prompt for Claude Code listens for accessibility window events on a task's virtual display or package notifications. The listener stays active only during the call and ignores past events. GP ChatGPT ★ 9,488repo stars scroll This Claude Code prompt scrolls a page or panel in a chosen direction. Ask it to move up, down, left, or right. GP ChatGPT ★ 9,488repo stars phone_clear_text The phone_clear_text Claude Code prompt clears text from a phone screen’s focused field. It can also target a field by ref and snapshotId. GP ChatGPT ★ 9,488repo stars web_back The web_back Claude Code prompt returns the current browser tab to its previous page. If the address stays the same, the agent follows the page’s own back link. GP ChatGPT ★ 9,488repo stars

Project sponsors

Companies that keep this analytics open