When To Use

Use this skill when the user wants text-to-video or image-to-video generation through GoAI, especially for prompts like 生成视频, 做视频, 出视频, 文生视频, 图生视频, and 做个动画.

Pass the user's video 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.

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 做个, but do not rewrite the core prompt content.

Examples:

• User: 给我生成一段狮子奔跑的视频 -> --prompt "一段狮子奔跑的视频" or --prompt "给我生成一段狮子奔跑的视频"
• User: 做个海浪视频 -> --prompt "做个海浪视频" or --prompt "海浪视频"
• Never turn 给我生成一段狮子奔跑的视频 into a lion running video 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 video models by display.priority, filters them by the requested video_mode, and picks the highest-priority compatible model. When the user omits video parameters, the script derives default aspect ratio, duration, and resolution from the same capability response.