Gemini Image

This wraps Gemini Pro's vision API for analyzing images from the command line. You can extract text from screenshots, debug error messages, compare UI states, or pull code snippets out of images. The prompting examples are genuinely useful, especially the structured templates for OCR, UI analysis, and turning screenshots into bug reports. It's basically OCR plus understanding, so you get both the text and context about what you're looking at. Works well for those moments when you need to grab text from an image or quickly analyze what's happening in a screenshot without manually typing everything out. Quality depends on your image clarity, and you'll want to verify extracted text since no OCR is perfect.

skills.sh installs: 1.2K
GitHub stars: 27
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add johnlindquist/claude --skill gemini-image --agent claude-code

Installs into .claude/skills of the current project.

Files

Gemini Image Analysis

Analyze images using Gemini Pro's vision capabilities.

Prerequisites

pip install google-generativeai
export GEMINI_API_KEY=your_api_key

CLI Reference

Basic Image Analysis

# Analyze an image
gemini -m pro -f /path/to/image.png "Describe this image in detail"

# With specific question
gemini -m pro -f screenshot.png "What error message is shown?"

# Multiple images
gemini -m pro -f image1.png -f image2.png "Compare these two images"

Analysis Operations

General Description

gemini -m pro -f image.png "Describe this image comprehensively:
1. Main subject/content
2. Colors and composition
3. Text visible (if any)
4. Context and purpose
5. Notable details"

Extract Text (OCR)

gemini -m pro -f screenshot.png "Extract all text from this image.
Format as plain text, preserving layout where possible.
Include any text in buttons, labels, or UI elements."

Code from Screenshot

gemini -m pro -f code-screenshot.png "Extract the code from this screenshot.
Provide as properly formatted code with correct indentation.
Note any parts that are unclear or partially visible."

SKILL.md on GitHub