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.

起草和完善視頻生成模型（文本到視頻和圖像到視頻）的提示。當用戶請求“視頻提示”或特定於型號的提示（例如 Ovi、Sora、Veo 3、Wan 2.2 或 LTX-2）時使用，包括“文本到視頻提示”、“圖像到視頻提示”或“為 [型號] 編寫提示”等請求。 來源：square-zero-labs/video-prompting-skill。

查看原文