BeClaude

gemini-skills

New
7Community RegistryGeneralby Piotr Migdał

Google Gemini 3 Pro skills for image generation (Nano Banana Pro) and AI consultation with web search and vision

First seen 5/22/2026
View Source

Summary

This skill integrates Google's Gemini 3 Pro models into Claude Code, enabling image generation with Nano Banana Pro and AI consultation with web search and vision capabilities.

  • It provides a second opinion from Gemini for complex tasks, including real-time data grounding and image analysis.

Overview

Claude Code skills for integrating Google's Gemini 3 Pro models into your workflow. For more context, see this blog post.

Skills Included

1. Nano Banana Pro (nano-banana-pro)

Generate images using Google's advanced Nano Banana Pro model (gemini-3-pro-image-preview).

Capabilities:

  • •Accurate infographics with real data (uses Google Search grounding)
  • •Text rendering in images
  • •Cartographic visualizations and maps
  • •Detailed instruction following
  • •Multiple aspect ratios: 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9
  • •Resolutions: 1K, 2K, 4K

2. Gemini Consultant (gemini-consultant)

Get a second opinion from Gemini 3 Pro (gemini-3-pro-preview) with Google Search grounding and vision.

Capabilities:

  • •Real-time web information via Google Search grounding
  • •Image analysis (single or multiple images)
  • •Configurable thinking depth (low for speed, high for complex reasoning)
  • •Context passing for detailed questions

Prerequisites

You need a Google AI API key with access to Gemini 3 Pro models.

bash
export GEMINI_API_KEY="your-api-key-here"

Get your API key from Google AI Studio.

Installation

bash
# In Claude Code, add the marketplace
/plugin marketplace add stared/gemini-claude-skills

# Install the plugin
/plugin install gemini-skills@gemini-claude-skills

Usage Examples

Once installed, Claude will automatically use these skills when appropriate. You can also explicitly request them:

Image Generation

"Generate an infographic showing the water cycle"

"Create a 16:9 landscape image of a futuristic city at 4K resolution"

AI Consultation

"Ask Gemini what the latest React 19 features are"

"Get a second opinion on this code architecture from Gemini"

"Have Gemini analyze this screenshot" (attach image)

Dependencies

The scripts use uv with inline script dependencies - no manual package installation required. Dependencies are declared in each script:

python
# /// script
# dependencies = ["google-genai"]
# ///

Author

Piotr Migdał (@pmigdal)

License

MIT

Links

Install & Usage

1
Create the skills directory
mkdir -p .claude/skills
2
Download the skill file
mkdir -p .claude/skills && curl -o .claude/skills/gemini-skills.md https://raw.githubusercontent.com/stared/gemini-claude-skills/main/SKILL.md
3
Invoke in Claude Code
/gemini-skills

Use Cases

Generate infographics with accurate real-time data using Google Search grounding.
Create maps or cartographic visualizations with precise text rendering.
Analyze multiple images and get detailed insights with vision capabilities.
Get a second opinion on complex code or logic problems using Gemini's reasoning.
Fetch and summarize real-time web information for research or debugging.
Generate high-resolution images in various aspect ratios for UI mockups or diagrams.

Usage Examples

1

/gemini-skills nano-banana-pro Create a 16:9 infographic showing global renewable energy trends in 2024, with accurate data and clear labels.

2

/gemini-skills gemini-consultant Analyze this image of a circuit board and identify any potential design flaws, with high thinking depth.

3

/gemini-skills gemini-consultant Search the web for the latest Python 3.13 features and compare them with what I have in my codebase.

View source on GitHub

Security Audits

LicenseUnknownSourceWarnRepositoryPass

Frequently Asked Questions

What is gemini-skills?

This skill integrates Google's Gemini 3 Pro models into Claude Code, enabling image generation with Nano Banana Pro and AI consultation with web search and vision capabilities. It provides a second opinion from Gemini for complex tasks, including real-time data grounding and image analysis.

How to install gemini-skills?

To install gemini-skills: create the skills directory (mkdir -p .claude/skills), then run: mkdir -p .claude/skills && curl -o .claude/skills/gemini-skills.md https://raw.githubusercontent.com/stared/gemini-claude-skills/main/SKILL.md. Finally, /gemini-skills in Claude Code.

What is gemini-skills best for?

gemini-skills is a skill categorized under General. Created by Piotr Migdał.

What can I use gemini-skills for?

gemini-skills is useful for: Generate infographics with accurate real-time data using Google Search grounding.; Create maps or cartographic visualizations with precise text rendering.; Analyze multiple images and get detailed insights with vision capabilities.; Get a second opinion on complex code or logic problems using Gemini's reasoning.; Fetch and summarize real-time web information for research or debugging.; Generate high-resolution images in various aspect ratios for UI mockups or diagrams..