Gemini Image

🌐Community
by johnlindquist · vlatest · Repository

Generate images from text prompts using Google's Gemini model, offering creative visuals based on your descriptions.

Install on your platform

We auto-selected Claude Code based on this skill’s supported platforms.

1

Run in terminal (recommended)

terminal
claude mcp add gemini-image npx -- -y @trustedskills/gemini-image
2

Or manually add to ~/.claude/settings.json

~/.claude/settings.json
{
  "mcpServers": {
    "gemini-image": {
      "command": "npx",
      "args": [
        "-y",
        "@trustedskills/gemini-image"
      ]
    }
  }
}

Requires Claude Code (claude CLI). Run claude --version to verify your install.

About This Skill

What it does

This skill enables AI agents to analyze images using Google's Gemini Pro vision model. It supports various image formats (PNG, JPEG, GIF, WebP) and provides built-in analysis templates for tasks like text extraction (OCR), code recovery from screenshots, UI/UX feedback, error diagnosis, and data extraction from charts. The skill can handle both single and multiple images in a request to facilitate comparisons.

When to use it

  • Extracting text from screenshots or documents using OCR.
  • Recovering code snippets from visual representations of code.
  • Analyzing user interfaces (UI) for usability issues or identifying elements.
  • Diagnosing errors presented visually, such as in error messages displayed on a screen.
  • Comparing multiple images to identify differences or similarities.

Key capabilities

  • Supports PNG, JPEG, GIF, and WebP image formats.
  • Provides analysis templates for text extraction (OCR), code recovery, UI/UX feedback, error diagnosis, and data extraction from charts.
  • Handles single and multiple image comparisons.
  • Utilizes Google Gemini Pro's vision capabilities.

Example prompts

  • "Describe this image comprehensively: [path to image.png]"
  • "Extract all text from this screenshot: [path to screenshot.png]"
  • "Analyze this UI: [path to ui-screenshot.png]"

Tips & gotchas

  • Requires the google-generativeai Python library and a valid GEMINI_API_KEY environment variable set up before use.
  • The skill is designed for image analysis, not general image generation.
  • When recovering code from screenshots, be aware that partially visible or unclear sections may require manual correction.

Tags

🛡️

TrustedSkills Verification

Unlike other registries that point to live repositories, TrustedSkills pins every skill to a verified commit hash. This protects you from malicious updates — what you install today is exactly what was reviewed and verified.

Security Audits

Gen Agent Trust HubPass
SocketPass
SnykPass

Details

Version
vlatest
License
Author
johnlindquist
Installs
164

🌐 Community

Passed automated security scans.