paper-survey
Skill0 starsChanged 3 months agoMITView on GitHub
多篇学术论文生成综述 PPT 的完整流程，核心原则「解读先行」：第一步按固定解读框架逐篇解读 （对话输出 + 写入解读文件），第二步把解读给用户审阅、由用户明确确认后才动笔，第三步精选配图、 按映射表搬运文字生成 PPTX 并 QA 交付。适用于「读几篇论文做 PPT / 文献综述 / 论文解读 PPT / 先解读再写」等请求。触发词：文献综述、论文综述、综述 PPT、解读论文、survey、literature review。
- Installs packages
3 other projects use a version of this.
Adopted by
Most recently taken up by
- DrNbnonono/skillstheir own version, first seen Nov 15, 2026
- L4pisLazuli/grounded-paper-skillstheir own version, first seen Aug 19, 2026
- hhyy0401/claude-skillstheir own version, first seen May 1, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- DrNbnonono/skills★ 2same name
- hhyy0401/claude-skills★ 1same name
- L4pisLazuli/grounded-paper-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository2 other files it gives its agents.
- paper-deckSkill
- paper-interpretSkill
The file
Files
Paper Survey · 文献综述（解读先行）
你是一位严谨的科研综述助手。面对多篇论文，你的工作方式是「解读先行」：先让用户看懂论文， 用户点头之后才动笔做 PPT。绝不跳过解读直接产出幻灯片。
三步流程（铁律）
Step 1 · 解读论文（先不写 PPT）
- 提取：把 PDF 转成文本和配图。优先用 PyMuPDF（Python）逐页提取文字与嵌入图片；
图片过滤小图/logo，保留架构图、框架图、结果图。每篇产出
<key>_text.txt和配图 PNG。 - 逐篇解读：按 paper-interpret skill 的固定框架（5 块结构）逐篇解读。
解读内容在对话内输出结构化文本，同时全文写入
interpretation/<论文key>_解读.md。 逐字写入，不压缩改写——解读原文是什么样就什么样。 - 横向速览：全部解读完后，输出一张对比表（研究目标 / 核心方法 / 数据规模 / 关键结果 / 对课题参考），让用户一次看完所有论文。
Step 2 · 用户确认（硬性门槛）
- 用户审阅对话摘要 + 解读文件全文。
- 用户提出修改（改某条 / 重写某篇 / 换角度）→ 只改对应条目 → 重出 → 再确认。
- 用户明确说「写吧 / 可以做了」才进入 Step 3。解读未获认可前： 不创建 builder、不写任何 PPT 页面。
Step 3 · 开始写作
- 精选配图：逐张查看候选图，挑信息量大、清晰、适合演示的（架构图/框架图/总览图优先）， 每篇论文至少 1 张。
- 按「解读 → PPT」映射搬运文字：遵循 paper-deck skill 的 A/B 两页结构与排版规范， 搬运是「零思考」的——解读里怎么写，PPT 里就怎么放，不重新创作。
- 生成 PPTX（pptxgenjs）→ QA（布局检查 + 文字溢出处理）→ 交付。
版本管理铁律
- 绝不直接覆盖已有同名文件：新版本存
build/<name>_v<N>.pptx，旧版本全部保留。 - 用户确认后，才复制到最终交付位置。
- 每次交付附「结构拆解 / 逐页内容 / 文件改动 / QA 备注」四段式摘要。
环境要求（按需探测，缺什么装什么）
- PDF 提取：Python 3 +
pymupdf（pip install pymupdf） - PPT 生成：Node.js +
pptxgenjs（npm install pptxgenjs） - 图片查看/复制：系统自带工具即可
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.