Skip to main content
prompt GP ChatGPT

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

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 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.md

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.

view_image wangzan101 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. GP ChatGPT ★ 9,488repo stars image-generation claude-office-skills image-generation is a Claude Code skill that writes prompts for DALL-E, Midjourney, and Stable Diffusion. It helps shape image requests around a chosen style or format. CX Codex +1 5,800installs tao-generate-image-grounding NVIDIA Corporation tao-generate-image-grounding is a Claude Code skill that extracts referring phrases from image captions and assigns each phrase pixel bounding boxes for phrase-grounding data. CX Codex +1 1,600installs tao-train-image-classification NVIDIA Corporation tao-train-image-classification is a Claude Code skill that configures and runs PyTorch image classification in NVIDIA TAO. It supports training ResNet or EfficientNet backbones, distillation, and TensorRT export. CX Codex +1 1,600installs image-relighting eachlabs image-relighting — a skill for Claude Code, Cursor, Codex and Gemini CLI. Transforms photo lighting: studio setups, golden hour tones, neon glows, angled shadows — via each::sense API. CX Codex +1 245installs image-outpainting eachlabs image-outpainting paints new content beyond a photo's borders through each::sense: wider frames, other aspect ratios, room for banner text. CX Codex +1 232installs image-ocr benchflow-ai Use this skill to read text in images with Tesseract OCR through Python. It fits scans, screenshots, and batches of image files. CX Codex +1 1installs

From the same set132

The whole set →
screenshot The screenshot Claude Code prompt captures the current screen as an image. Save it to a new PNG path under /workspace, then call share_file to deliver it. GP ChatGPT ★ 9,488repo stars knowledge_read The knowledge_read prompt for Claude Code and ChatGPT reads information about apps and websites. It opens an attachment or looks up a resource that has not been opened yet. GP ChatGPT ★ 9,488repo stars phone_find The phone_find Claude Code prompt scrolls a mobile app and searches its accessibility tree for text, a resource ID, or a role. It stops if the app changes or the content no longer moves. GP ChatGPT ★ 9,488repo stars 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 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 view_image 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. 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

Project sponsors

Companies that keep this analytics open