把用户提供的小说原文 / 现成剧本，经**六个角色技能框架接力**转化为「分镜图提示词 + 视频脚本 + AI 视频提示词」。三个**稳定输出机制**：每个角色有独立技能框架（完整工作方法）；环节间有固定数据契约；质量门前置到每个角色并加终检。 使用提醒：无视频制作能力，本skill仅提供设计分镜和视频提示词服务，无视频生成能力，生成视频需自行调用其他视频模型能力生成视频，介意勿拍。
Turn one idea into a short-form video production plan with a script, shot timings, text storyboard, AI visual prompts, captions, titles, and A/B variants. No finished MP4 included.
Turn a script, idea, product photos or a start/end frame into one AI-generated 4, 6 or 8 s 720p MP4 with audio from Google Veo 3.1 Lite on OpenRouter. You approve a short shot plan first. Remix mode makes a new clip from your uploaded video's first frame. Video generation uses the publisher's hosted VIDEO_API_KEY.
把素材描述整理成無聲影片的紙上剪輯時間軸、字幕卡、素材缺口與補拍簡報。下載型文字規劃工具，不生成或輸出影片。 Turn footage descriptions into a paper-edit timeline, caption cards, asset gaps, and a pickup-shot brief for silent videos. A downloadable text-planning tool; it does not generate or export video.
Turn ideas, scripts, and product images into generation-ready short-form video clips (5–6s) with Seedance 2.0 Mini and Grok Cheap.