claude-meta/home-claude/skills/gemini-image/SKILL.md

name	description
gemini-image	Use when user asks to generate, create, edit, or produce images.

Gemini Image Generation

Uses Gemini Python API via scripts in this skill's scripts/ directory.

Setup (once)

pip install -r ~/.claude/skills/gemini-image/requirements.txt

Requires GEMINI_API_KEY environment variable.

Generate image from text

python ~/.claude/skills/gemini-image/scripts/generate_image.py "<prompt>" <output.jpg>

Options: --model gemini-3-pro-image-preview (higher quality), --aspect 16:9, --size 2K

Edit existing image

python ~/.claude/skills/gemini-image/scripts/edit_image.py <input.jpg> "<instruction>" <output.jpg>

Important

• Output format is JPEG by default — always use .jpg extension
• Models: gemini-2.5-flash-image (default, fast), gemini-3-pro-image-preview (higher quality)
• Aspect ratios: 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9
• Sizes: 1K (default), 2K, 4K (4K only with pro model)
• Ask user for output path if not specified