video-prompting

SKILL.md

Turn a user’s intent into a strong, model-compliant video prompt by routing to the correct model guide and applying its formatting/tokens.

Model-specific guidance lives in references/models/. This file is the entry point: pick the model, ask the minimum clarifying questions, then draft the prompt in that model’s expected format.

To add a new model later: create references/models/ /prompting.md, then add it to this index.

起草和完善视频生成模型（文本到视频和图像到视频）的提示。当用户请求“视频提示”或特定于型号的提示（例如 Ovi、Sora、Veo 3、Wan 2.2 或 LTX-2）时使用，包括“文本到视频提示”、“图像到视频提示”或“为 [型号] 编写提示”等请求。 来源：square-zero-labs/video-prompting-skill。

查看原文