paper-deck
Skill0 starsChanged 3 months agoMITView on GitHub
综述 PPT 的生成规范：单篇论文 A/B 两页结构（页A 论据 + 页B 配图与解读）、逐字搬运不创作、 pptxgenjs 排版规范与已知坑、QA 检查表。适用于解读确认后进入写作阶段、或用户要求调整 PPT 版式时。触发词：生成 PPT、做幻灯片、A/B 结构、排版、deck。
1 other project uses a version of this.
Adopted by
Most recently taken up by
- zsyggg/paper-craft-skillstheir own version, first seen May 21, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- zsyggg/paper-craft-skills★ 1.2ksame 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-interpretSkill
- paper-surveySkill
The file
Files
Paper Deck · 综述 PPT 生成规范
单篇论文的 A/B 两页结构
页A —— 这篇在问什么 / 怎么做
- 立论前提（1–2 条）+ RQ 清单
- 研究设计要点（被试/条件/测量/分析，各 1 行）
- 页A 放 1 张框架图或方法图（可选）
页B —— 测出什么 / 怎么读 / 参考意义
- 关键结果（数值 + 口径 + 怎么读）
- 每个研究设计项下附「对应 RQx 的解释」原话段落
- 对课题参考（01 直接可用 / 02 需改造 / 03 风险约束）
- 页B 放 1 张结果图
整体结构（按需裁剪）：封面 / 研究背景 / 论文 1–N 各 A/B 两页 / 横向对比 / 结论与建议。
搬运铁律：零思考、逐字搬运
- 解读文件里怎么写，PPT 里就怎么放——不重新创作、不压缩改写。
- 文字放不下用
fit: "shrink"（normAutofit）让渲染引擎自动缩字号，不手动删字。
pptxgenjs 排版规范与已知坑
pres.layout = "LAYOUT_WIDE"（13.3" × 7.5"，16:9）- 颜色 hex 不带 # 号
slide.addText(text, options)— text 必须是独立第一个参数（字符串），不能塞在 options 里- 文本框有默认内边距，精确对齐时加
margin: 0 - 一次
new pptxgen()对应一个输出文件 - 所有可能溢出的文本框加
fit: "shrink"
视觉纪律
- 禁用渐变、阴影、圆角装饰；扁平干净
- 图片保持原始纵横比，不拉伸变形
- 关键论文配图优先用矢量示意或论文原图
QA 检查表（生成后必跑）
- 每页无文字溢出（shrink 生效检查）
- 图片不变形、位置不与文本框重叠
- 页A/页B 结构完整（每篇都有两页）
- 「对应 RQx 的解释」段落在每篇页B 都有
- 页码、标题与实际内容一致
交付
- 新版本存
build/<name>_v<N>.pptx，旧版本全保留，绝不直接覆盖 - 交付时附四段式摘要：结构拆解 / 逐页内容 / 文件改动 / QA 备注
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.