TypingMindTypingMindThe best frontend for AI
Paper Onion logo

Paper Onion

Community
didixuxu
paper-onion

论文剥洋葱 — 逐层深入的论文阅读技能。将一篇学术论文拆解为四层渐进式阅读，最终生成一张手绘风格的思维导图笔记卡片（React artifact）。 当用户上传论文PDF、粘贴论文内容、给出论文链接，或说出以下任何意图时，使用此技能： - "帮我读这篇论文" / "分析这篇paper" - "论文笔记" / "论文总结" / "读论文" - "剥洋葱" / "逐层分析" - 上传了 .pdf 文件且内容看起来是学术论文 此技能与一次性输出报告的方式不同——它模拟真实的深度阅读过程，分四层逐步深入，每层都有明确的阅读任务和产出，最终浓缩为一张可保存的笔记卡。

Overview

Publisherdidixuxu
Repositorydidi-skills
Skill namepaper-onion
Stars
86
Forks
8
Bundled files
1
Links
Skill sourceRepository
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by didixuxu on GitHub. Read the source before you install it.

Installation

Install the Paper Onion AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/didixuxu/didi-skills/tree/main/paper-proofread
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/didixuxu/didi-skills.git /tmp/didi-skills
mkdir -p .claude/skills
cp -r /tmp/didi-skills/paper-proofread .claude/skills/paper-onion
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Paper Onion in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Paper Onion on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Paper Onion is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

论文剥洋葱 Paper Onion

核心理念

读论文不是信息倾倒，而是逐层内化的过程。这个技能模拟一个有经验的研究者如何真正读懂一篇论文：

  1. 先花30秒扫一遍，建立第一印象
  2. 再花5分钟理清故事线骨架
  3. 然后20分钟深入核心机制
  4. 最后10分钟内化为自己的理解，连接已有知识

每一层都不是简单的信息摘取，而是回答一个认知问题。

输入处理

接受以下输入类型：

  • PDF 文件路径（从 /mnt/user-data/uploads/ 读取）
  • 论文 URL（需要 fetch）
  • 直接粘贴的论文文本

如果是 PDF，先提取全文文本。如果提取困难，基于可获取的部分（标题、摘要、图表描述）尽力分析，并告知用户。

四层剥洋葱流程

对论文执行以下四层分析。每一层都有一个认知问题驱动，而非机械地填表。

第一层 · 30秒扫读 (👁)

认知问题：这篇论文在说什么？

只看标题、摘要、引言第一段和结论，提取：

  • one_sentence：一句话概括（不超过40字，用中文，必须让非专业人士也能听懂）
  • key_question：这篇论文试图回答的核心问题（用问句表达）
  • first_impression：3个第一印象要点（每个不超过15字）

风格要求：像你30秒扫完后跟朋友口头说"这论文讲的是……"那样自然。不要用学术腔。

第二层 · 骨架透视 (🦴)

认知问题：论文的逻辑骨架是什么？

快速通读全文，提取论文的"故事线"：

  • storyline：4步故事线，每步包含 label 和 text
    • 第1步标签用 "痛点"：前人方法的关键瓶颈是什么
    • 第2步标签用 "灵感"：作者的突破性洞察是什么
    • 第3步标签用 "方案"：具体怎么做的（一句话概括方法）
    • 第4步标签用 "证据"：关键实验数据（必须带具体数字）
  • key_figure：论文中最重要的一张图/表的描述（指明Figure几，说清楚它展示了什么）

风格要求：故事线要像一个"以前→发现→做了→证明了"的叙事，不是干巴巴的列表。

第三层 · 深度解剖 (🔬)

认知问题：核心机制到底怎么工作的？

仔细分析方法部分，提取：

  • mechanisms：3-5个核心机制，每个包含：
    • what：机制名称
    • why：为什么这样设计（不是"是什么"，而是"为什么"）
    • formula：关键公式或伪代码（用简洁的数学表示，如果没有公式就用一句话描述算法流程）
  • hidden_assumptions：2-3个论文没有明说但暗含的假设（这是最有价值的部分——作者不说但你应该知道的）

风格要求：每个 why 必须回答"如果不这样做会怎样"。隐形假设要尖锐但公正。

第四层 · 内化连接 (🧠)

认知问题：这对我意味着什么？

这是最重要的一层，也是大多数人跳过的一层：

  • napkin_formula：餐巾纸公式——用不超过10个字浓缩整篇论文的核心insight（像 "并行注意力 ＞ 顺序循环"、"扩散 = 逆向去噪" 这样极度压缩的表达）
  • core_insight：核心洞察——2-3句话，说清楚这篇论文改变了什么认知。不是摘要的重复，而是"读完后你理解了什么之前不理解的东西"
  • connections：3-5个知识连接，每个包含：
    • to：连接到的其他论文/概念/方法（写清名称和年份）
    • link：这个连接是什么关系（继承/对比/互补/启发/推广）用一句话说清
  • what_changed：读完这篇论文后"我的认知变化"——用第一人称写，像日记一样

风格要求：这一层最能体现深度理解。如果 connections 只能想到论文自己引用的那些reference，说明理解还不够深——要跨领域连接。

输出：React Artifact 笔记卡

完成四层分析后，生成一个 React artifact (.jsx)，呈现为手绘风格的笔记卡片。

关于视觉风格和实现细节，请阅读 references/notecard-template.md。

关键设计原则

  1. 一张卡片浓缩全部精华：不是四层的简单拼接，而是有主次的信息架构
  2. 手绘/纸质感：温暖的纸张底色(#fdf8ef)、手写字体(Caveat)、微微倾斜的元素、虚线边框
  3. 餐巾纸公式居中放大：这是整张卡的视觉焦点
  4. 故事线用箭头连接：痛点 → 灵感 → 方案 → 证据，一目了然
  5. 知识连接用彩色左边框：每个连接一种颜色，像思维导图的分支
  6. 隐形假设用警告色：提醒读者注意的地方

交互方式

这个技能的输出是一次性生成完整的笔记卡（不是交互式的多步操作）。但在生成过程中，按四层顺序组织思考，确保每一层都足够深入。

如果用户在看完笔记卡后追问某一层的细节，可以展开讨论，但不需要重新生成整张卡。

语言

  • 所有分析内容用中文输出
  • 论文标题、人名、术语保留英文原文
  • 公式用英文/数学符号
  • 风格：口语化、有温度、避免学术八股。想象你在咖啡馆给一个聪明的朋友讲这篇论文

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Paper Onion AI skill do?

论文剥洋葱 — 逐层深入的论文阅读技能。将一篇学术论文拆解为四层渐进式阅读，最终生成一张手绘风格的思维导图笔记卡片（React artifact）。 当用户上传论文PDF、粘贴论文内容、给出论文链接，或说出以下任何意图时，使用此技能： - "帮我读这篇论文" / "分析这篇paper" - "论文笔记" / "论文总结" / "读论文" - "剥洋葱" / "逐层分析" - 上传了 .pdf 文件且内容看起来是学术论文 此技能与一次性输出报告的方式不同——它模拟真实的深度阅读过程，分四层逐步深入，每层都有明确的阅读任务和产出，最终浓缩为一张可保存的笔记卡。

Why use Paper Onion on TypingMind?

Because you install it once and use it with any model. Paper Onion is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Paper Onion in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/didixuxu/didi-skills/tree/main/paper-proofread. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Paper Onion?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Paper Onion?

As many as you like. As long as a model supports skills, you can use Paper Onion with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Paper Onion AI skill free?

It is published on GitHub by didixuxu. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

Related AI Skills

View all
obra logo

Subagent Driven Development

obra
CommunityPopular

Use when executing implementation plans with independent tasks in the current session

25.8K
288.1K
6 files
View
affaan-m logo

Unified Memory

affaan-m
CommunityPopular

Share durable, inspectable context and handoffs between Claude, Codex, Hermes, Cursor, OpenCode, and other agents through the local ECC Memory Vault. Use when an agent must save work state, transfer…

40.4K
270.2K
1 files
View
NousResearch logo

Draw Your Font

NousResearch
OrganizationPopular

Turn a handwriting photo into an installable TTF font.

53.5K
250.4K
1 files
View
NousResearch logo

Adversarial Ux Test

NousResearch
OrganizationPopular

Roleplay a hostile user to find and triage UX pain points.

53.5K
250.4K
Instructions
View

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇