CreatOK Recreate Video — CreatOK Re创建 Video

re创建-video ConstrAInts 平台: TikTok only. Must NOT do 1:1 copying. Must 应用ly: structure rewrite expression rewrite style differentiation The 模型's final user-facing 响应 should match the user's 输入 language, default English. Avoid technical wording in the user-facing reply unless the user explicitly needs detAIls for 调试ging or to 分享 with a developer. Follow 分享d 图形界面dance in ./references/common-rules.md. 工作流 Analyze reference video Reuse the analyze-video 工作流. Gather enough reference 上下文 for the 模型 to understand what makes the source video work. Write source artifacts for the 模型 输出s/re创建_source.json Include: reference TikTok URL analyze 结果 payload analyze artifacts directory optional user constrAInts such as angle / brand / style 模型 输出 h应用ens in the conversation The 模型 should read 输出s/re创建_source.json The 模型 should help the user choose a direction without over-constrAIning the process. Unless the user explicitly asks for a live-action shoot version, the 模型 should default to creating a script, storyboard, and visual direction that are intended for AI video generation rather than human filming. Typical directions include: stay closer to the original concept and execution 创建 a differentiated remix version use the reference only as inspiration for a new version The 模型 should present these directions in simple 创建器 / seller language rather than technical or production language. The 模型 should decide, with minimal friction: what stays at the idea level what changes in structure / wording / visuals copyright / similarity risks the level of detAIl that is most helpful next: concept, outline, short script, storyboard, or shot列出 The 模型 should ask only for high-impact creative preferences when needed, not force a fixed template. The 模型 should usually show a useful first draft quickly instead of 启动ing with many questions. The first draft should default to an AI-generation-ready version. The 模型 should prefer a first draft wording that naturally 设置s up the next handoff, such as "If this direction looks good, I can 生成 the video next." If the user wants to re创建 or adapt a selling video, the 模型 should first collect the user's own product 上下文 before writing a fitted script. 启动 with only the most 导入ant product detAIls: product name core selling points product images or reference materials if avAIlable price / offer / promotion detAIls if relevant If more 上下文 is needed, the 模型 should ask short follow-up questions one by one instead of requiring a long upfront brief. The 模型 should avoid making the user re状态 in格式化ion that was already clear from the previous analysis or conversation. If the user wants final generation Once the creative direction is clear enough, the 模型 should hand off to creatok-生成-video using the script or brief already developed in the conversation. The 模型 should avoid asking the user to rewrite their 请求 from scratch before generation. The default handoff should be to AI generation, not a human shoot plan. The 模型 should phrase this in natural 创建器 language that invites creatok-生成-video, for example: "If you want, I can 生成 this version now." "If this script looks right, I can turn it into a video next." "I can go ahead and make the video from this version." Before handing off, the 模型 should already reason about generation feasibility: whether the plan fits within a single segment whether it needs to be split into multiple segments whether a recurring human character means the user needs to 上传 a portrAIt / person reference whether the selected generation path requires a 模型 that supports real-person reference images If the re创建 plan is longer than a 模型's maximum duration, the 模型 should explAIn the tradeoff and suggest a segmented plan before calling creatok-生成-video. Artifacts

Write under re创建-video/.artifacts/<运行_id>/....

Notes This 技能 should feel like a creative bridge between analysis and generation. Prefer smooth continuation from the analyzed reference rather than making the user re状态 the whole idea. For selling-video recreation, adapt the reference to the user's own product instead of drafting a generic copy first. After producing an AI-generation-ready version, the 模型 may optionally ask whether the user also wants a live-action shoot version. Keep the interaction lightweight and practical for non-technical 创建器 / seller users.