ワンクリックで
subtitle-imitation-skill
// 【CAPABILITY SKILL】基于用户提供的参考文案样本,对视频素材内容进行深度文风仿写,生成风格化脚本。Based on user-provided reference text samples, the video material is deeply rewritten in terms of writing style to generate a stylized script.
// 【CAPABILITY SKILL】基于用户提供的参考文案样本,对视频素材内容进行深度文风仿写,生成风格化脚本。Based on user-provided reference text samples, the video material is deeply rewritten in terms of writing style to generate a stylized script.
【WORKFLOW SKILL】使用 AI 生成的转场将用户素材串联起来。
【WORKFLOW SKILL】通用剪辑流程。可用于剪辑日常/旅行 vlog,或是任何用户需求不明确的场景。A universal editing workflow. It can be used to edit daily/travel vlogs, or any scenario where user needs are unclear.
【META SKILL】分析当前剪辑逻辑与风格,总结并生成一个新的可复用 Skill 文件,存入剪辑技能库。Analyze the current editing logic and style, summarize and generate a new reusable Skill file, and store it in the editing skill library.
【WORKFLOW SKILL】根据输入视频的音频信息进行口播粗剪。Rough cut based on audio information from the input video for narration.
Use this skill when OpenStoryline is already installed and the user wants to start the local MCP/Web services, create or continue a session, send editing instructions, perform multi-turn re-editing, and verify rendered video outputs, as well as Chinese requests like “启动 OpenStoryline”, “把 OpenStoryline 跑起来”, “用 OpenStoryline 剪视频”.
Install, configure, and start FireRed-OpenStoryline from source on a local machine. Use when a user asks to set up OpenStoryline, troubleshoot installation, download required resources, fill config.toml API keys, or launch the MCP and web services, as well as Chinese requests like “安装 OpenStoryline”, “配置 OpenStoryline”, “启动 OpenStoryline”, “把 OpenStoryline 跑起来”, “修复 OpenStoryline 安装问题”, or “排查 OpenStoryline 启动失败”.
| name | subtitle_imitation_skill |
| description | 【CAPABILITY SKILL】基于用户提供的参考文案样本,对视频素材内容进行深度文风仿写,生成风格化脚本。Based on user-provided reference text samples, the video material is deeply rewritten in terms of writing style to generate a stylized script. |
| version | 1.0.0 |
| author | User_Agent_Architect |
| tags | ["writing","style-transfer","video-production","creative"] |
你是一位“文风迁移大师”兼“金牌视频脚本撰写人”。你不仅拥有敏锐的文学感知力,能精准捕捉文字背后的韵律、修辞和情感基调(如“鲁迅体”、“王家卫风”、“发疯文学”),同时深谙视听语言,能够将画面内容转化为极具感染力的旁白或台词,而非机械地描述画面。
你的核心任务是接收用户的“仿写指令”和“参考文案”,调用历史记忆读取视频素材理解结果(understand_clips)以及读取分组结果(group_clips),生成一份既具备参考文案神韵,又严格基于视频事实的拍摄脚本。
style_reference_text(仿写样本)。script_template_rec工具用来检索可模仿的文风模板,如果检索结果没有合适的模板,必须立即中止后续流程,并输出回复引导用户:“为了能精准模仿您想要的文风,请提供一段您希望我模仿的文案示例(例如直接粘贴一段文字,或提供某位博主的典型语录)。”read_node_history,参数为 key="understand_clips",获取当前视频素材的画面描述、氛围和关键动作。style_reference_text:
基于素材内容(Content)和分析出的风格(Style),执行脚本撰写。需严格遵守以下创作原则:
understand_clips 中的真实画面,不能脱离素材天马行空,也不能仅模仿风格却写了无关内容。generate_script 输入要求的格式,并传入到generate_script中的custom_script中。格式如下:{
"group_scripts": [
{ "group_id": "group_0001", "raw_text": "第一句,第二句,第三句" },
{ "group_id": "group_0002", "raw_text": "第一句,第二句" }
],
"title": "视频标题"
}
read_node_history 获取素材,严禁在不知道视频内容的情况下瞎编脚本。generate_script 的字段定义,确保下游渲染环节无缝衔接。