ZJU-REAL/Easel / skills/builtin/paper-explainer
paper-explainer
Verified科研论文解读:解析 arXiv/PDF 的公式与图表,提炼问题、贡献、方法、关键图和结论,再产出 B站/视频号解读视频或知乎/公众号图文。 当用户说“论文解读、讲论文、论文转视频/图文、科研科普、arXiv、学术视频”时使用。 本 SKILL 从论文做内容;video-to-article 从视频做图文,doc-convert 只转换文档格式。
| File | Kind | Size |
|---|---|---|
| EASEL-META.md | markdown | 2.1 KB |
| SKILL.md | skill md | 9.8 KB |
| references/explain-methodology.md | markdown | 3.2 KB |
| references/paper-distill-schema.md | markdown | 2.7 KB |
| references/platform-adapt.md | markdown | 2.3 KB |
| references/slide-design.md | markdown | 11.5 KB |
| references/slide-plan.example.json | config | 2.9 KB |
| references/slide-plan.style-transfer.example.json | config | 1.8 KB |
| references/video-storyboard.md | markdown | 3.1 KB |
| scripts/paper_ingest.py | script | 19.1 KB |
| scripts/render_slides.py | script | 48.5 KB |
references/video-storyboard.md
View on GitHub# 论文视频分镜结构
> 把 asset-library.json 展开成视频分镜脚本 `script.md`。分镜/留存/口播节奏复用 **video-script** 的
> 方法(喂论文语境);本文件给论文视频**专属的段落结构**。
## 推荐结构(2–4 分钟中视频)
| 段落 | 时长占比 | 内容(取自 asset-library) | 画面 |
|------|---------|--------------------------|------|
| **钩子** | 0–15s | `hook` + `one_liner` | 冲击性画面/数字大字/概念图(ai-image-gen) |
| **问题** | 15s–25% | `problem` + `prior_gap` | 痛点场景图 / 对比示意 |
| **贡献预告** | | `contributions`(一句话预告"这篇怎么破") | 要点大字条 |
| **方法(主体)** | 25%–65% | `method.idea` + `analogy` + `how` | **核心方法图**(原图或 infographic 重绘)+ 类比动画/示意 |
| **结果(高潮)** | 65%–85% | `results`(关键数字)| **结果对比图**(chart-visualization 重绘,突出那一个结论) |
| **意义 + 局限** | 85%–100% | `takeaway` + `limitations` | 收束画面 |
| **互动钩子** | 结尾 | 抛问题引评论 | — |
## 口播原则
- **对话感**:像给朋友讲,不像念论文。短句、口语、有节奏。
- **一图一议**:切到某张图就只讲这张图要说的那一个点,讲完再切。
- **术语即时解释**:首次出现术语紧跟人话(用 asset-library `terms`)。
- **语速**:中文约 250 字/分钟;口播总字数 ≈ 时长(分钟)×250,用 `wordcount.py` 校验。
## 可选:双人问答口播(更抓耳)
借鉴 paper_to_podcast。设「主持人(好奇提问)+ 讲解者(解答)」两个角色:
- 主持人替观众问出疑问("等等,这跟以前的方法有啥不一样?"),讲解者回答。
- 一问一答天然制造节奏和悬念,比单人旁白更耐听。
- 配音时用 multi-voice-dubbing 给两角色分配不同音色,别用单声线 tts-voiceover 冒充双人。
## 分镜 → Slide → 成片
1. 每一页只对应一个中心结论:`claim`(屏幕观点)+ `narration`(口播)+ 一个视觉证据;不要把口播全文放上屏。
2. 按 `slide-design.md` 生成 `slide-plan.json`,只用其中定义的 cover/statement/evidence/process/metrics/comparison/takeaway 骨架。
3. 图:从项目根 `outputs/论文简称/assets/parsed/figures/` 选原图;方法图/结果图用 infographic/chart-visualization 重绘;原图太密就裁关键区域,不能缩成邮票。
4. 必须用 `render_slides.py validate → render → audit`,再肉眼查看 contact sheet;禁止每次在 outputs 临时发明一套 slide 脚本。
5. 单人口播用 tts-voiceover;双人问答用 multi-voice-dubbing。字幕与每页时长按 narration 分段对齐,再交 auto-short-video 合成。storyboard 顶层必须写 `"image_motion": "static"`;slide 不做 Ken Burns 缩放/平移,只在换页时使用克制转场。
6. 画幅按用户确认值;B站通常 16:9,视频号可 16:9 或 9:16,但不能静默推断。
## 封面
- 论文视频封面 = **一个钩子问题/惊人结论 + 3–6 字大字**,别用论文标题。
- 用 poster-hero 或 ai-image-gen 出封面。
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 |