video-script
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
Chinese/dm:video-script
/dm:video-script
Purpose
用途
Write a production-ready video marketing script with hook variants, timestamps, visual direction notes, CTA placement, and platform-specific formatting. Produces a complete script package ready for production with visual and audio columns, accessibility notes, and thumbnail concepts.
撰写可直接用于制作的营销视频脚本,包含多种钩子变体、时间戳、视觉指导说明、CTA布局以及平台专属格式。产出完整的脚本包,包含视觉和音频列、无障碍说明以及缩略图构思,可直接投入制作。
Input Required
所需输入
The user must provide (or will be prompted for):
- Video type: The format of the video — ad spot, explainer, testimonial, product demo, social short, educational tutorial, brand story, or event recap
- Target platform: Where the video will be published — YouTube, TikTok, Instagram Reels, LinkedIn, YouTube Shorts, Facebook, or multi-platform
- Target length: Desired duration — 15s, 30s, 60s, 90s, 2-3 min, 5-10 min, or long-form 10+ min
- Key message or topic: The core idea, value proposition, or subject matter the video must communicate
- Call to action: What the viewer should do after watching — visit URL, subscribe, purchase, sign up, download, follow, etc.
- Target audience: Who the video is for — demographics, psychographics, awareness level, and platform behavior
- Brand tone: Desired tone and energy level — professional, casual, humorous, inspirational, educational, urgent, or conversational
- Available assets: What production resources are available — on-camera talent, b-roll footage, product samples, graphics/animation capability, studio vs. location, screen recordings
- Competitor video references: Optional — links or descriptions of competitor or aspirational videos to benchmark against
- Performance goals: What success looks like — views, watch-through rate, click-through rate, conversions, engagement, or brand lift
用户必须提供(或会被提示提供)以下信息:
- 视频类型:视频格式——广告片、解说视频、客户证言、产品演示、社交短视频、教学教程、品牌故事或活动回顾
- 目标平台:视频发布平台——YouTube、TikTok、Instagram Reels、LinkedIn、YouTube Shorts、Facebook或多平台
- 目标时长:期望时长——15秒、30秒、60秒、90秒、2-3分钟、5-10分钟或长视频(10分钟以上)
- 核心信息或主题:视频必须传达的核心观点、价值主张或主题内容
- 行动号召(CTA):观众观看后应采取的行动——访问网址、订阅、购买、注册、下载、关注等
- 目标受众:视频面向的人群——人口统计特征、心理特征、认知水平以及平台使用行为
- 品牌调性:期望的语气和活力水平——专业、随性、幽默、励志、教育性、紧迫感或对话式
- 可用资源:可用的制作资源——出镜人才、B-roll素材、产品样品、图形/动画制作能力、演播室或外景场地、屏幕录制素材
- 竞品视频参考(可选):竞品或标杆视频的链接或描述,用于参考对标
- 绩效目标:成功的衡量标准——播放量、完播率、点击率、转化率、互动量或品牌提升度
Process
流程
- Load brand context: Read for the active slug, then load
~/.claude-marketing/brands/_active-brand.json. Apply brand voice, compliance rules for target markets (~/.claude-marketing/brands/{slug}/profile.json), and industry context. Also check for guidelines atskills/context-engine/compliance-rules.md— if present, load restrictions and relevant category files. Check for custom templates at~/.claude-marketing/brands/{slug}/guidelines/_manifest.json. Check for agency SOPs at~/.claude-marketing/brands/{slug}/templates/. If no brand exists, ask: "Set up a brand first (/dm:brand-setup)?" — or proceed with defaults.~/.claude-marketing/sops/ - Determine platform specs and format constraints: Reference platform-specific requirements — aspect ratio (16:9, 9:16, 1:1), max duration, safe zones for text overlays, caption placement areas, and native content conventions. Apply platform algorithm preferences (e.g., TikTok favors native-feeling content, LinkedIn rewards professional storytelling, YouTube prioritizes watch time).
- Select script structure: Choose the optimal narrative framework based on video type and goals — AIDA (Attention-Interest-Desire-Action), PAS (Problem-Agitate-Solution), problem-solve-CTA, storytelling arc (setup-tension-resolution), listicle, before/after, or direct response. Justify the choice based on audience awareness level and platform norms.
- Write 3 hook variants: Craft three distinct opening hooks for the first 3 seconds — each using a different hook technique (bold claim, question, visual shock, pattern interrupt, relatable pain point, or curiosity gap). Provide rationale for why each hook works for the target audience and platform.
- Draft full script with timestamps: Write the complete script with second-by-second or scene-by-scene timestamps. Include speaker dialogue or voiceover lines, pause beats, transition cues, and pacing notes. Ensure the script hits the target duration within a 10% margin.
- Add visual direction notes: Create a visual column alongside the script specifying camera angles (wide, medium, close-up, overhead), b-roll suggestions, graphics and text overlay placements, transitions (cut, dissolve, swipe), product shots, and screen recordings where applicable.
- Place CTAs at optimal points: Position call-to-action moments at strategically timed intervals based on video length — verbal CTA, on-screen CTA overlay, end card CTA, and pinned comment CTA. For shorter videos, place a single CTA at the natural climax; for longer videos, use a soft mid-roll CTA and a strong end CTA.
- Add accessibility notes: Write a closed caption script ensuring all spoken content and meaningful sound effects are transcribed. Include audio description notes for key visual-only moments. Specify caption styling (font size, positioning, background contrast) per platform requirements.
- Create thumbnail and cover frame concept: Design a thumbnail concept for YouTube or a cover frame for Reels/TikTok — specify text overlay (7 words max), facial expression or product shot, color treatment, and contrast elements that drive click-through. Include 2 thumbnail variant ideas for A/B testing.
- Review against brand voice and platform best practices: Audit the complete script against brand voice settings, compliance requirements, and platform content policies. Flag any potential issues with claims, disclosures, music licensing, or platform-specific restrictions. Verify pacing matches platform consumption patterns.
- 加载品牌上下文:读取获取活跃品牌标识,然后加载
~/.claude-marketing/brands/_active-brand.json。应用品牌语调、目标市场的合规规则(~/.claude-marketing/brands/{slug}/profile.json)以及行业背景。同时检查指南:查看skills/context-engine/compliance-rules.md——若存在,加载限制条件和相关分类文件。检查~/.claude-marketing/brands/{slug}/guidelines/_manifest.json下的自定义模板。检查~/.claude-marketing/brands/{slug}/templates/下的代理操作流程。若未设置品牌,询问:"是否先设置品牌(/dm:brand-setup)?"——或使用默认设置继续。~/.claude-marketing/sops/ - 确定平台规格和格式限制:参考平台专属要求——宽高比(16:9、9:16、1:1)、最大时长、文本叠加安全区域、字幕放置区域以及原生内容规范。应用平台算法偏好(例如,TikTok偏好原生感内容,LinkedIn推崇专业叙事,YouTube优先考虑观看时长)。
- 选择脚本结构:根据视频类型和目标选择最优叙事框架——AIDA(注意力-兴趣-欲望-行动)、PAS(问题-激化-解决方案)、问题-解决-CTA、故事弧(铺垫-冲突-解决)、清单式、前后对比或直接响应式。根据受众认知水平和平台规范说明选择理由。
- 撰写3种钩子变体:为开头3秒创作3种不同的开场钩子——每种使用不同的钩子技巧(大胆断言、提问、视觉冲击、模式打断、共鸣痛点或好奇心缺口)。说明每种钩子对目标受众和平台有效的原因。
- 撰写带时间戳的完整脚本:撰写完整脚本,包含逐秒或逐场景的时间戳。包含演讲者台词或旁白、停顿节拍、转场提示和节奏说明。确保脚本时长在目标时长的10%误差范围内。
- 添加视觉指导说明:在脚本旁创建视觉列,指定拍摄角度(全景、中景、特写、俯拍)、B-roll建议、图形和文本叠加位置、转场方式(切镜、溶解、滑动)、产品镜头以及适用的屏幕录制素材。
- 优化CTA布局:根据视频时长在战略时机设置行动号召时刻——口头CTA、屏幕CTA叠加、片尾卡片CTA以及置顶评论CTA。短视频在自然高潮处放置单个CTA;长视频则使用软性中插CTA和强力片尾CTA。
- 添加无障碍说明:撰写隐藏字幕脚本,确保所有语音内容和有意义的音效都被转录。为关键纯视觉场景添加音频描述说明。根据平台要求指定字幕样式(字体大小、位置、背景对比度)。
- 创建缩略图和封面帧构思:为YouTube设计缩略图构思,或为Reels/TikTok设计封面帧——指定文本叠加(最多7字)、面部表情或产品镜头、色彩处理以及提升点击率的对比元素。提供2种缩略图变体用于A/B测试。
- 对照品牌语调和平台最佳实践审核:对照品牌语调设置、合规要求和平台内容政策审核完整脚本。标记任何潜在问题,如宣传声明、披露要求、音乐授权或平台专属限制。验证节奏是否符合平台内容消费模式。
Output
输出
A structured video script package containing:
- 3 hook variants with rationale explaining the technique used and expected audience response for each
- Full script with timestamps — second-by-second or scene-by-scene timing from open to end card
- Visual direction column specifying what the viewer sees at each timestamp — camera angles, b-roll, graphics, text overlays, transitions, and product shots
- Audio direction column covering voiceover delivery notes, background music cues (genre, energy, licensing notes), sound effects, and silence beats
- On-screen text callouts with exact copy, timing, positioning, font size guidance, and animation style
- CTA placement map with timing rationale — why each CTA appears where it does based on viewer retention curves
- Platform-specific formatting notes — aspect ratio, duration compliance, safe zones, caption areas, and algorithm optimization tips
- Accessibility package — closed caption script, audio description notes, and caption styling specifications
- Thumbnail/cover frame concept — 2 variant ideas with text overlay, imagery, color treatment, and click-through optimization rationale
- Production notes — talent requirements, location suggestions, props and wardrobe, equipment recommendations, and lighting direction
- Estimated production complexity rating (low/medium/high) with justification based on required assets, talent, locations, and post-production
- Alternative cut guidance — how to create a shorter or longer version from the same shoot, specifying which sections to cut or expand
结构化的视频脚本包包含:
- 3种钩子变体,附带每种所用技巧的说明以及预期受众反应
- 带时间戳的完整脚本——从开场到片尾卡片的逐秒或逐场景计时
- 视觉指导列,指定每个时间戳观众看到的内容——拍摄角度、B-roll、图形、文本叠加、转场和产品镜头
- 音频指导列,涵盖旁白交付说明、背景音乐提示(流派、活力、授权说明)、音效和停顿节拍
- 屏幕文本标注,包含确切文案、计时、位置、字体大小指导和动画风格
- CTA布局图,附带计时理由——基于观众留存曲线说明每个CTA放置位置的原因
- 平台专属格式说明——宽高比、时长合规性、安全区域、字幕区域和算法优化技巧
- 无障碍包——隐藏字幕脚本、音频描述说明和字幕样式规范
- 缩略图/封面帧构思——2种变体方案,包含文本叠加、图像、色彩处理和点击率优化理由
- 制作说明——人才要求、场地建议、道具和服装、设备推荐以及灯光指导
- 预估制作复杂度评级(低/中/高),基于所需资源、人才、场地和后期制作说明理由
- 替代剪辑指导——如何从同一拍摄素材制作更短或更长版本,指定需删减或扩展的部分
Agents Used
使用的Agent
- content-creator — Script writing, hook development, narrative structure, visual and audio direction, CTA placement, accessibility scripting, thumbnail concept, brand voice alignment, and platform-specific formatting
- content-creator——脚本撰写、钩子开发、叙事结构、视觉和音频指导、CTA布局、无障碍脚本编写、缩略图构思、品牌语调对齐以及平台专属格式设置