Gpt Image 2 Style Library

This pulls from the awesome-gpt-image-2 style library to turn rough image ideas into structured prompts. You describe what you want,a product shot, infographic, poster, whatever,and it matches your intent against a repository of templates, style tags, and scene categories, then builds a complete prompt with composition, materials, constraints, and aspect ratio. The workflow is smart: if multiple templates fit, it shows you options instead of guessing. Output is bilingual and ready to copy. Helpful when you're working with GPT-Image2 and don't want to reinvent prompt structures from scratch or miss details like label readability and layout hierarchy. The reference file is generated from JSON, so it stays current with the upstream repo.

skills.sh installs: 4.2K
GitHub stars: 35.6K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add freestylefly/awesome-gpt-image-2 --skill gpt-image-2-style-library --agent claude-code

Installs into .claude/skills of the current project.

Files

GPT-Image2 Style Library

Use this skill to turn a user's image-generation intent into a production-ready GPT-Image2 prompt using the awesome-gpt-image-2 style library.

Example Output

City life system map example

Example request: 用 gpt-image-2-style-library 技能生成城市生命系统图谱

Reference

Read references/style-library.md before choosing a template or style.
The reference is generated from data/style-library.json in the repository.
Prefer the reference over memory when template names, categories, covers, or style tags matter.