[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M72WMHQEPDPRR9TT30T7KHJ7":3,"skill-same:01M72WMHQEPDPRR9TT30T7KHJ7":64},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":31,"install":32,"resources":45},"01M72WMHQEPDPRR9TT30T7KHJ7","video-script-generator",null,"生成短视频脚本和分镜。输入产品\u002F主题描述、目标受众、时长，输出完整脚本+分镜结构（JSON\u002FYAML）。支持多种模板：痛点-解决、反转剧情、before-after。触发词：视频脚本、短视频文案、分镜、storyboard、video script。","agentscope-ai\u002FPawBench","agentscope-ai","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F211762292?v=4","01M6CRT6543BZGGVK3P85GC08Q","AgentScope-AI","01M72WJAXCYDAXK74090327ER7",127,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FPawBench\u002Fblob\u002Fmain\u002Fdata\u002Fpawbench-v1.0\u002Fassets\u002FT125_qwenpawbench_skillhub_0100\u002Fskills\u002Fvideo-script-generator\u002FSKILL.md",[],[],"2026-11-10 22:39:42",false,"---\nname: video-script-generator\ndescription: 生成短视频脚本和分镜。输入产品\u002F主题描述、目标受众、时长，输出完整脚本+分镜结构（JSON\u002FYAML）。支持多种模板：痛点-解决、反转剧情、before-after。触发词：视频脚本、短视频文案、分镜、storyboard、video script。\n---\n\n# 短视频脚本+分镜生成\n\n## 工作流程\n\n1. 收集输入信息\n2. 选择模板风格\n3. 生成脚本+分镜结构\n4. 输出结构化数据供下游消费\n\n## 输入参数\n\n| 参数 | 必填 | 说明 |\n|------|------|------|\n| topic | ✓ | 产品\u002F主题描述 |\n| audience | ✓ | 目标受众 |\n| duration | ✓ | 时长：15s \u002F 30s \u002F 60s \u002F 90s |\n| template | - | 模板：pain-solution \u002F before-after \u002F plot-twist |\n| platform | - | 平台：douyin \u002F xiaohongshu \u002F youtube-shorts |\n| tone | - | 语气：professional \u002F casual \u002F humorous \u002F dramatic |\n\n## 模板说明\n\n### pain-solution（默认）\n痛点引入 → 解决方案 → 效果展示 → CTA\n\n### before-after\n对比前的状态 → 转折点 → 对比后的状态 → CTA\n\n### plot-twist\n正常叙事 → 意外反转 → 揭示真相 → CTA\n\n详见 [templates\u002F](templates\u002F) 目录。\n\n## 输出格式\n\n```yaml\nmeta:\n  title: \"脚本标题\"\n  duration: 30s\n  platform: douyin\n  template: pain-solution\n\nscript:\n  hook: \"开场钩子文案\"\n  \n  scenes:\n    - id: 1\n      type: hook           # hook\u002Fpain\u002Fsolution\u002Fdemo\u002Fcta\n      duration: 3s\n      narration: \"旁白\u002F台词\"\n      shot_description: \"镜头描述：特写\u002F中景\u002F全景，动作，表情\"\n      visual_style: \"画面风格提示\"\n      demo_insert: false\n      \n    - id: 2\n      type: pain\n      duration: 5s\n      narration: \"...\"\n      shot_description: \"...\"\n      demo_insert: false\n      \n    - id: 3\n      type: solution\n      duration: 8s\n      narration: \"...\"\n      shot_description: \"产品界面展示\"\n      demo_insert: true\n      demo_action: \"点击生成按钮，展示结果\"\n      \n    - id: 4\n      type: cta\n      duration: 3s\n      narration: \"链接在评论区\"\n      shot_description: \"logo + 二维码\"\n      demo_insert: false\n\n  cta: \"链接在评论区 \u002F 点击头像私信\"\n  \nmusic_suggestion: \"轻快节奏 \u002F 紧张悬疑 \u002F 温馨治愈\"\n```\n\n## 场景类型\n\n| type | 用途 | 典型时长 |\n|------|------|----------|\n| hook | 开场吸引 | 2-3s |\n| pain | 痛点展示 | 3-5s |\n| solution | 解决方案 | 5-10s |\n| demo | 产品演示 | 5-15s |\n| result | 效果展示 | 3-5s |\n| twist | 反转 | 3-5s |\n| cta | 行动号召 | 2-3s |\n\n## 时长分配参考\n\n| 总时长 | 场景数 | 分配建议 |\n|--------|--------|----------|\n| 15s | 3-4 | hook(2) + core(10) + cta(3) |\n| 30s | 4-6 | hook(3) + pain(5) + solution(15) + cta(3) |\n| 60s | 6-8 | hook(3) + pain(8) + solution(35) + result(10) + cta(4) |\n\n## 使用示例\n\n用户：帮我写一个30秒的短视频脚本，推广我的AI写作工具，目标用户是自媒体博主\n\n执行：\n1. 确认参数：topic=AI写作工具, audience=自媒体博主, duration=30s\n2. 选择模板：pain-solution（默认）\n3. 生成脚本+分镜\n4. 输出 YAML 结构\n\n## 下游对接\n\n输出的结构化数据可直接用于：\n- `digital-avatar` skill：提取 narration 生成口播\n- `scene-video-generator` skill：按 shot_description 生成画面\n- `video-stitcher` skill：按 duration 拼接\n","# 短视频脚本+分镜生成\n\n## 工作流程\n\n1. 收集输入信息\n2. 选择模板风格\n3. 生成脚本+分镜结构\n4. 输出结构化数据供下游消费\n\n## 输入参数\n\n| 参数 | 必填 | 说明 |\n|------|------|------|\n| topic | ✓ | 产品\u002F主题描述 |\n| audience | ✓ | 目标受众 |\n| duration | ✓ | 时长：15s \u002F 30s \u002F 60s \u002F 90s |\n| template | - | 模板：pain-solution \u002F before-after \u002F plot-twist |\n| platform | - | 平台：douyin \u002F xiaohongshu \u002F youtube-shorts |\n| tone | - | 语气：professional \u002F casual \u002F humorous \u002F dramatic |\n\n## 模板说明\n\n### pain-solution（默认）\n痛点引入 → 解决方案 → 效果展示 → CTA\n\n### before-after\n对比前的状态 → 转折点 → 对比后的状态 → CTA\n\n### plot-twist\n正常叙事 → 意外反转 → 揭示真相 → CTA\n\n详见 [templates\u002F](templates\u002F) 目录。\n\n## 输出格式\n\n```yaml\nmeta:\n  title: \"脚本标题\"\n  duration: 30s\n  platform: douyin\n  template: pain-solution\n\nscript:\n  hook: \"开场钩子文案\"\n  \n  scenes:\n    - id: 1\n      type: hook           # hook\u002Fpain\u002Fsolution\u002Fdemo\u002Fcta\n      duration: 3s\n      narration: \"旁白\u002F台词\"\n      shot_description: \"镜头描述：特写\u002F中景\u002F全景，动作，表情\"\n      visual_style: \"画面风格提示\"\n      demo_insert: false\n      \n    - id: 2\n      type: pain\n      duration: 5s\n      narration: \"...\"\n      shot_description: \"...\"\n      demo_insert: false\n      \n    - id: 3\n      type: solution\n      duration: 8s\n      narration: \"...\"\n      shot_description: \"产品界面展示\"\n      demo_insert: true\n      demo_action: \"点击生成按钮，展示结果\"\n      \n    - id: 4\n      type: cta\n      duration: 3s\n      narration: \"链接在评论区\"\n      shot_description: \"logo + 二维码\"\n      demo_insert: false\n\n  cta: \"链接在评论区 \u002F 点击头像私信\"\n  \nmusic_suggestion: \"轻快节奏 \u002F 紧张悬疑 \u002F 温馨治愈\"\n```\n\n## 场景类型\n\n| type | 用途 | 典型时长 |\n|------|------|----------|\n| hook | 开场吸引 | 2-3s |\n| pain | 痛点展示 | 3-5s |\n| solution | 解决方案 | 5-10s |\n| demo | 产品演示 | 5-15s |\n| result | 效果展示 | 3-5s |\n| twist | 反转 | 3-5s |\n| cta | 行动号召 | 2-3s |\n\n## 时长分配参考\n\n| 总时长 | 场景数 | 分配建议 |\n|--------|--------|----------|\n| 15s | 3-4 | hook(2) + core(10) + cta(3) |\n| 30s | 4-6 | hook(3) + pain(5) + solution(15) + cta(3) |\n| 60s | 6-8 | hook(3) + pain(8) + solution(35) + result(10) + cta(4) |\n\n## 使用示例\n\n用户：帮我写一个30秒的短视频脚本，推广我的AI写作工具，目标用户是自媒体博主\n\n执行：\n1. 确认参数：topic=AI写作工具, audience=自媒体博主, duration=30s\n2. 选择模板：pain-solution（默认）\n3. 生成脚本+分镜\n4. 输出 YAML 结构\n\n## 下游对接\n\n输出的结构化数据可直接用于：\n- `digital-avatar` skill：提取 narration 生成口播\n- `scene-video-generator` skill：按 shot_description 生成画面\n- `video-stitcher` skill：按 duration 拼接\n",{"name":5,"description":7},"main","0f794a8bb6c27aa9ee4091b2691fa30e4ed9cc8f","data\u002Fpawbench-v1.0\u002Fassets\u002FT125_qwenpawbench_skillhub_0100\u002Fskills\u002Fvideo-script-generator",24,"https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FPawBench","https:\u002F\u002Fagentscope-ai.github.io\u002FPawBench\u002F","https:\u002F\u002Fgithub.com\u002Fagentscope-ai","2026-08-03 20:09:53",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add agentscope-ai\u002FPawBench --skill video-script-generator",{"tool":38,"command":39},"bunx","bunx skills add agentscope-ai\u002FPawBench --skill video-script-generator",{"tool":41,"command":42},"pnpm","pnpm dlx skills add agentscope-ai\u002FPawBench --skill video-script-generator","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FPawBench\u002Fblob\u002Fmain\u002Fdata\u002Fpawbench-v1.0\u002Fassets\u002FT125_qwenpawbench_skillhub_0100\u002Fskills\u002Fvideo-script-generator\u002FSKILL.md",true,[46,52,56,60],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"_meta.json","REFERENCE","参考文档",141,"https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FPawBench\u002Fblob\u002Fmain\u002Fdata\u002Fpawbench-v1.0\u002Fassets\u002FT125_qwenpawbench_skillhub_0100\u002Fskills\u002Fvideo-script-generator\u002F_meta.json",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"templates\u002Fbefore-after.md",1078,"https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FPawBench\u002Fblob\u002Fmain\u002Fdata\u002Fpawbench-v1.0\u002Fassets\u002FT125_qwenpawbench_skillhub_0100\u002Fskills\u002Fvideo-script-generator\u002Ftemplates\u002Fbefore-after.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"templates\u002Fpain-solution.md",1085,"https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FPawBench\u002Fblob\u002Fmain\u002Fdata\u002Fpawbench-v1.0\u002Fassets\u002FT125_qwenpawbench_skillhub_0100\u002Fskills\u002Fvideo-script-generator\u002Ftemplates\u002Fpain-solution.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"templates\u002Fplot-twist.md",1269,"https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FPawBench\u002Fblob\u002Fmain\u002Fdata\u002Fpawbench-v1.0\u002Fassets\u002FT125_qwenpawbench_skillhub_0100\u002Fskills\u002Fvideo-script-generator\u002Ftemplates\u002Fplot-twist.md",[65,71,78,85,92,99],{"skillNo":66,"name":67,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":19},"01M72WQCJKBJZB6SC8MMYK3C8R","data-reconciliation","https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FPawBench\u002Fblob\u002Fmain\u002Fdata\u002Fpawbench-v1.0\u002Fassets\u002FT140_skillsbench_xlsx-recover-data\u002Fskills\u002Fdata-reconciliation\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":19},"01M72WQ8R4DZKK1CT397C0ARQD","hierarchical-taxonomy-clustering","Build unified multi-level category taxonomy from hierarchical product category paths from any e-commerce companies using embedding-based recursive clustering with intelligent category naming via weighted word frequency analysis.","https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FPawBench\u002Fblob\u002Fmain\u002Fdata\u002Fpawbench-v1.0\u002Fassets\u002FT139_skillsbench_taxonomy-tree-merge\u002Fskills\u002Fhierarchical-taxonomy-clustering\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":19},"01M72WQ1989ZX613G3PY8Z492J","nlp-research-repo-package-installment","Align Python version and repo-declared dependencies (requirements.txt \u002F environment.yml) before installing packages for NLP research code reproduction.","https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FPawBench\u002Fblob\u002Fmain\u002Fdata\u002Fpawbench-v1.0\u002Fassets\u002FT138_skillsbench_simpo-code-reproduction\u002Fskills\u002Fnlp-research-repo-package-installment\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":19},"01M72WPZ828E746PAB3WCCQARW","state-space-linearization","Linearizing nonlinear dynamics around operating points for control design.","https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FPawBench\u002Fblob\u002Fmain\u002Fdata\u002Fpawbench-v1.0\u002Fassets\u002FT137_skillsbench_r2r-mpc-control\u002Fskills\u002Fstate-space-linearization\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":19},"01M72WPXFXKWDFVTGAYX0B1TSA","mpc-horizon-tuning","Selecting MPC prediction horizon and cost matrices for web handling.","https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FPawBench\u002Fblob\u002Fmain\u002Fdata\u002Fpawbench-v1.0\u002Fassets\u002FT137_skillsbench_r2r-mpc-control\u002Fskills\u002Fmpc-horizon-tuning\u002FSKILL.md",[],[],{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":19},"01M72WPW3863555HM0CACRCCFK","integral-action-design","Adding integral action to MPC for offset-free tension tracking.","https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FPawBench\u002Fblob\u002Fmain\u002Fdata\u002Fpawbench-v1.0\u002Fassets\u002FT137_skillsbench_r2r-mpc-control\u002Fskills\u002Fintegral-action-design\u002FSKILL.md",[],[]]