AI Image Tools (OpenAI + Gemini)

ai-image-tools

Generate and edit images using either OpenAI GPT Image 1.5 or Google's Nano Banana Pro (Gemini 3 Pro Image). Use when the user asks to generate/create/edit/modify images. Supports image-to-image editing for both providers and optional mask-based inpainting for OpenAI.

majiayu000/claude-skill-registry·0installs663starsDesign

SKILL.md

Full skill instructions

AI Image Tools (OpenAI + Gemini)

One unified skill for image generation + editing, supporting:

OpenAI: GPT Image 1.5 (generation + edits, optional mask inpainting)
Gemini: Nano Banana Pro (Gemini 3 Pro Image) (generation + image-to-image edits)

Usage

Run from your current working directory so outputs save where you're working.

Generate (text → image)

uv run scripts/generate_image.py --prompt "A moody cinematic portrait of a golden retriever" --filename "out.png"

Pick a provider explicitly:

# OpenAI (GPT Image 1.5)
uv run scripts/generate_image.py --provider openai --prompt "..." --filename "out.png"

# Gemini (Nano Banana Pro)
uv run scripts/generate_image.py --provider gemini --prompt "..." --filename "out.png"

Edit (image → image)

uv run scripts/generate_image.py --prompt "Make it look like a watercolor painting" --filename "out.png" --input-image "input.png"

Mask-based inpainting (OpenAI only):

uv run scripts/generate_image.py --provider openai --prompt "A red balloon" --filename "out.png" --input-image "input.png" --mask "mask.png"

Provider Selection

Default --provider auto:
- uses OpenAI if OPENAI_API_KEY (or --openai-api-key) is available
- otherwise uses Gemini if GEMINI_API_KEY (or --gemini-api-key) is available
Set --provider openai or --provider gemini to force one.

API Keys

OpenAI:
- env: OPENAI_API_KEY
- flag: --openai-api-key
Gemini:
- env: GEMINI_API_KEY
- flag: --gemini-api-key

Options (Provider-Specific)

OpenAI options

--quality low|medium|high (generation only; default medium)
--size 1024x1024|1024x1536|1536x1024|auto (default 1024x1024)
--background transparent|opaque|auto (generation only; default auto)
--mask path/to/mask.png (edits only)

Gemini options

--resolution 1K|2K|4K (default 1K)

Notes

Output is always saved as PNG at --filename.
Don’t read the output image back into the model unless explicitly requested.

Install skill

Copy and run in your terminal

npx -y skills add https://github.com/majiayu000/claude-skill-registry --skill ai-image-tools

View on GitHub

skills/data/ai-image-tools/SKILL.md

More Design skills

View all

Design

gpt-taste

gpt taste

92.7K 355.7K

View

Design

brandkit

Premium brand-kit image generation for high-end identity systems, logo concepts, and visual-world presentations.

92.7K 345.8K

View

Design

image-to-code

Premium website design-to-code skill that generates visual references first, then builds faithful frontend implementations.

92.7K 341.7K

View

Design

imagegen-frontend-web

Premium frontend image direction for landing pages and marketing sites, generating one distinct horizontal image per section.

92.7K 337.8K

View

Design

imagegen-frontend-mobile

Premium mobile app screen concepts and flows with clean hierarchy, strong imagery, and distinctive art direction.

92.7K 331.8K

View

Design

Emil Design Engineering

Emil Kowalski's philosophy on UI polish, component design, and the invisible details that make software feel good.

43.5K 323.4K

View

Design

impeccable

Frontend design and iteration for production-grade interfaces, from concept to ship.

76.8K 313.3K

View

Design

extract-design-system

Reverse-engineer design tokens from public websites into starter token files for your project.

232 129.9K

View

Design

Animate

Builds an animation from scratch by making the decisions in the order that determines whether it feels right.

43.5K 117.9K

View

Design

canvas-design

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.

179.7K 114.2K

View

Design

brand-guidelines

Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.

179.7K 100.1K

View

Design

theme-factory

Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.

179.7K 89.5K

View