zkywalkerzkywalkerCommunity·1 Agent Skills Included

nanobanana

Prompt optimization, image generation, editing, and reusable templates

Generates and edits images from plain-language requests in Chinese, English, or mixed language. Cleans up prompts, locks layout and edit boundaries, and routes tasks to GPT Image, Gemini, or host-native image tools. Archives final prompts and turns successful iterations into reusable templates, eliminating rework and guesswork.
npx skills add zkywalker/nanobanana --all -g -y

All Skills in This Repository (1)

Pure Emerald Level Indicators

Frequently Asked Questions

FAQPage Schema
How to install BananaHub?

Run `npx skills add zkywalker/nanobanana --all -g -y` in your terminal to install the skill globally, then run `/bananahub init` to configure your image provider.

What does BananaHub do?

It turns plain-language descriptions into optimized image prompts, then generates or edits images through providers like GPT Image or Gemini. It also archives prompts and reuses them as templates.

Which image models does BananaHub support?

It supports GPT Image via OpenAI or compatible gateways, Gemini / Nano Banana, Vertex AI, chat-compatible endpoints, and host-native image tools like Codex built-in generation.

Do I need an API key to use BananaHub?

Not always. If your agent host already has a built-in image tool, BananaHub can use it directly; otherwise you configure one provider API key during setup.

Can BananaHub edit existing images?

Yes. Use `/bananahub edit` with an input image to replace backgrounds, adjust elements, or apply mask-based edits depending on your provider.

Related Repositories in Design & Creative

View All in Design & Creative