When To Use

Use this skill when the user wants image generation, image editing, or reference-image-based image creation through GoAI, especially for prompts like 生成图片, 画图, 出图, 做图, 修图, and 改图.

Pass the user's image prompt through as-is unless the user explicitly asks for prompt optimization, prompt polishing, rewriting, translation, or additional creative detail. Do not silently embellish short prompts such as 画一个老虎.

Do not translate the user's prompt to another language. If the user writes in Chinese, pass Chinese to --prompt. If the user writes in English, pass English to --prompt. You may strip only lightweight request wrappers such as 帮我, 给我, 请, 生成, or 画一张, but do not rewrite the core prompt content.

Examples:

• User: 给我生成一只狮子 -> --prompt "一只狮子" or --prompt "给我生成一只狮子"
• User: 画一个老虎 -> --prompt "画一个老虎" or --prompt "一个老虎"
• Never turn 给我生成一只狮子 into a lion unless the user explicitly asks for English translation.

Default Behavior

This package currently targets the production environment at https://mustgoai.com. Override GOAI_BASE_URL only when you intentionally need a different endpoint.

This skill now uses a single cross-platform Python entrypoint through uv. If the user does not specify a model, the script queries /api/v1/models/capabilities, sorts enabled image models by display.priority, and picks the highest-priority model.