Summary
This wraps OpenAI's image generation API in a Python script with sensible defaults and Chinese language triggers. You get access to gpt-image-2 and the earlier models, with options for different aspect ratios, transparent backgrounds, and multi-image editing where you can feed in up to three reference images. The script handles both generation and editing modes, saves files locally, and supports custom API endpoints if you're running through Azure or a proxy. It's straightforward if you already have an OpenAI key and just want Claude to generate images without switching contexts. The bilingual triggers are a nice touch for international teams.
Install to Claude Code
npx -y skills add feiskyer/claude-code-settings --skill gpt-image-skill --agent claude-codeInstalls into .claude/skills of the current project.
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
An agent that runs the SEO playbooks that move rankings and ships PRs you control.
Get founding access →
Connect Claude to +800M contacts, +150M companies. Find & Enrich leads in chat.
Try For Free →Files
SKILL.md
Select a file.
Featured
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →An agent that runs the SEO playbooks that move rankings and ships PRs you control.
Get founding access →Connect Claude to +800M contacts, +150M companies. Find & Enrich leads in chat.
Try For Free →
