ZJU-REAL/Easel / skills/builtin/real-lab-paper2video-v1
real-lab-paper2video-v1
Verified当用户需要论文视频、研究成果宣传片或修订成片时,制作或修订简洁优雅的论文讲解与宣传视频。将论文 PDF、arXiv 链接或素材包转为约三分钟的中文视频,使用完整论文原图、精准框选、内容动画、清晰轻快的配音配乐,并提供可编辑工程与成片检查;仅需图文时不使用本技能,通用论文解读用 paper-explainer。
| File | Kind | Size |
|---|---|---|
| EASEL-META.md | markdown | 2.7 KB |
| LICENSE | other | 11.1 KB |
| NOTICE | other | 613 B |
| SKILL.md | skill md | 6.1 KB |
| agents/openai.yaml | config | 277 B |
| assets/project-template/index.html | other | 3.7 KB |
| assets/project-template/motion-utils.js | script | 2.2 KB |
| assets/project-template/motion.js | script | 2.3 KB |
| assets/project-template/project.json | config | 165 B |
| assets/project-template/timeline.js | script | 340 B |
| references/paper-assets.md | markdown | 4.3 KB |
| references/production.md | markdown | 3.7 KB |
| references/quality.md | markdown | 2.5 KB |
| references/tooling.md | markdown | 5.0 KB |
| references/visual-system.md | markdown | 5.6 KB |
| requirements.txt | manifest | 49 B |
| scripts/easel_video.py | script | 3.9 KB |
| scripts/init_project.py | script | 1.1 KB |
| scripts/paper_assets.py | script | 2.3 KB |
| scripts/render.cjs | script | 4.9 KB |
| scripts/verify_video.py | script | 7.0 KB |
references/production.md
View on GitHub# 讲稿与声音制作
## 论文事实表
读取指定版本 PDF,记录标题、作者/机构、论文和代码链接、版本及 SHA256。复用同版本素材,或通过[内置资产模块](paper-assets.md)提取。
每条用于视频的结论记录以下字段:
| 字段 | 内容 |
|---|---|
| claim | 本页要讲清的结论 |
| source | 对应 PDF 页序、图表、段落或公式 |
| conditions | 模型规模、数据集、训练与推理设置 |
| values | 原始数值、单位、比较对象和提升口径 |
| limitation | 结论适用范围及论文披露的限制 |
将资产页码与实际 PDF 对照,明确采用零基页索引还是一基页序。实验数字按“模型 + 数据集/指标 + 方法 + 数值”组织;提升量标注为绝对分数或相对百分比。
## 讲稿和镜头表
面向有基本技术背景的观众,选择一条最值得记住的主线。三分钟视频可从以下时间分配开始,再依据实际口播调整:
| 段落 | 参考时长 | 讲解任务 |
|---|---:|---|
| 问题引入 | 15秒 | 用具体例子建立研究问题 |
| 核心想法 | 25秒 | 一句话说明思路及其作用 |
| 方法 | 70秒 | 先看 Pipeline 全景,再解释关键环节 |
| 实验证据 | 45秒 | 呈现主要对比和最有解释力的消融 |
| 适用范围 | 15秒 | 说明条件、代价和局限 |
| 收尾 | 10秒 | 重申贡献,给出论文/代码入口 |
按论文内容增减段落和页面。每页写出:结论、旁白、屏上文案、素材、强调目标、动画节拍。用一个主标题提出结论,侧栏按需要补充短要点,字幕呈现口播。将重复标题合并,文案精简到足以配合图像讲清当前信息。
策划阶段标注目标时长;取得音轨后,用实际对齐结果生成制作时间轴。已有指定配音时先匹配其内容和时长,再安排镜头。
## 旁白
使用清晰、自然、明亮的专业口吻。中文合成的一个可用起点是 `zh-CN-XiaoxiaoNeural`、语速 `+9%`、音高 `+2Hz`;按实际声音效果和用户偏好调整。
整段合成旁白,或按服务长度限制分为自然段,检查段落连接处的语气和停顿。为缩写、数字及公式确定读法;字幕使用论文中的规范术语。保留无损人声、讲稿及词边界/对齐数据。
以真实词边界或强制对齐结果安排字幕。长句按语义拆分,换页落在句间或明确的讲解转折。默认单行约40px字幕;双行版式相应扩大字幕区并重新安排图框。
## 配乐与混音
选择轻松愉快的无歌词器乐,节奏以100–115 BPM为起点。轻拨弦或键盘、温暖低音、轻打击适合论文讲解;108 BPM可作为默认尝试。
使用原创、用户提供或已有使用许可的曲目。音乐在开头淡入、跨页连续、片尾淡出;旁白出现时压低配乐,使术语、数字和句尾保持清楚。试听后调整人声与音乐的相对电平。
混音响度以−14至−16 LUFS为起点,true peak控制在−1 dBTP以内。保留独立人声、音乐与混音,便于后续替换。
## 修订与交付
以一份时间轴驱动画面、字幕和框选。修改讲稿后重新对齐声音;修改画面时沿用既有声音和时间轴。
为视频修订使用独立文件名,并记录源版本和最终文件哈希。重渲受影响镜头及相邻转场。使用分段缓存时,将代码、字体、图像、时间轴、尺寸、fps和渲染参数纳入缓存键,核对命中分段的帧数。
交付MP4、SRT、讲稿/镜头表、封面、工程ZIP和简短检查记录。工程收录当前源素材与来源、可编辑画面、时间轴、独立音轨、渲染及验证工具。使用包内相对路径;按素材许可保留署名或合法获取方式。
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| canvas-designanthropics/skillsCreate beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| docxanthropics/skillsUse this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| pdfanthropics/skillsUse this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| pptxanthropics/skillsUse this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. If a .pptx or .potx file needs to be opened, created, or touched, use this skill. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |