What are Claude Code Skills?

Claude Code Skills are reusable prompt templates stored as markdown files in your project's .claude/skills/ directory. They let you codify best practices and common workflows into slash commands that Claude follows consistently.

How do I create a Claude Code Skill?

Create a markdown file in .claude/skills/ with instructions for Claude. The filename becomes the command name — for example, .claude/skills/code-review.md can be invoked with /code-review during a Claude Code session.

Can I share skills with my team?

Yes. Skills stored in .claude/skills/ can be committed to version control so every team member has access to the same standardized workflows. You can also organize skills into subdirectories by category.

What is the difference between project and global skills?

Project skills (.claude/skills/) are specific to the current project and are committed to git. Global skills (~/.claude/skills/) are personal skills available across all your projects.

gemini-skills

New

7Community RegistryGeneralby Piotr MigdaÅ

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

Community PluginView Source

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

Install & Usage

Create the skills directory

mkdir -p .claude/skills

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

Invoke in Claude Code

/gemini-skills

View source on GitHub

Frequently Asked Questions

What is gemini-skills?