Paper Interpreter logo

Paper Interpreter

Community
chujianyun
paper-interpreter

论文解读助手。适用于用户发送 arXiv 论文链接,并希望下载论文、解读论文、生成读书笔记、做论文拆解或输出详细报告时使用。会在工作目录创建论文文件夹、下载 PDF 与 TeX Source(如有)、生成中文 Markdown 报告。默认先交付初稿,不自动复查;如果用户明确同意,再安排后续复查。不适用于只要简短推荐语的情况。

Overview

Publisherchujianyun
Repositoryskills
Skill namepaper-interpreter
Stars
743
Forks
103
Bundled files
2
Links
  • 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.

  • 2 bundled files

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

  • Open source

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

Installation

Install the Paper Interpreter 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/chujianyun/skills/tree/main/skills/paper-interpreter
  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/chujianyun/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/skills/paper-interpreter .claude/skills/paper-interpreter
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Paper Interpreter 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 Interpreter 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 Interpreter 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.

论文解读助手

适用场景

  • 用户发来 https://arxiv.org/... 链接,并明确要求"论文解读""论文拆解""详细总结""生成报告""下载论文"
  • 用户希望把论文资料落到本地目录,再生成一份结构完整、适合持续完善的中文报告
  • 用户接受以本地文件为主交付,而不是只在对话里看一段摘要

如果用户只要一段 200 字左右的推荐语,优先使用 paper-recommendation,不要使用本 skill。

设计模式

本 skill 主要采用:

  • Pipeline:严格按“下载资料 → 阅读材料 → 生成初稿 → 交付 → 如有需要再复查”的顺序执行
  • Generator:基于固定报告结构生成可长期迭代的文档
  • Inversion(轻度):开始前先确认范围,复查前再次征求用户同意

Gotchas

  • 不要把“论文推荐语”误判成“论文解读”,这两者要分流到不同 skill
  • 不要默认安排复查;是否复查必须先征求用户确认
  • 不要假装已经读完全文;如果只重点看了摘要、方法、实验,要明确说明
  • 不要编造论文中不存在的实验、公式、结论或数据
  • 不要只发路径不发文件;如果当前渠道支持发文件,应优先直接发送报告文件

工作流

0. 先确认执行范围(必须先做)

开始前先给用户一个简短确认,至少说清这 3 件事:

  • 会把论文下载到本地并生成报告
  • 初版默认先完成一版,不自动安排复查
  • 最终以文件为主交付,而不是直接在对话里长篇输出全文

如果用户已经明确接受“下载到本地 + 生成报告”的工作方式,可以直接继续,不必反复确认。

1. 确定保存目录

按以下优先级选择基础目录:

  1. 用户明确指定的目录
  2. 当前上下文中明显属于用户常用工作区的目录
  3. ~/Documents/working/papers

不要凭空发明新目录。无法确定时直接使用默认值。

2. 初始化论文工作区

先运行脚本,创建论文目录并下载资源:

bash
python3 skills/paper-interpreter/scripts/bootstrap_arxiv_paper.py '<arxiv_url>' '<base_dir>'

脚本会:

  • 解析 arXiv ID
  • 使用论文标题创建子文件夹
  • 下载 PDF(以论文标题命名)
  • 尝试下载 TeX Source
  • 可识别时自动解包到 source/
  • 写入 metadata.json
  • 如报告文件 {论文标题}_报告.md 不存在,则创建报告骨架

优先读取脚本输出中的 paper_dir、report_path、pdf_path、source_path。

3. 阅读材料并生成初版报告

生成报告前,按以下顺序获取信息:

  1. metadata.json
  2. arXiv 摘要页
  3. TeX Source(如果下载成功,优先用它确认公式、模块名、算法步骤)
  4. PDF 文件(以论文标题命名)

报告必须写入论文目录下的 {论文标题}_报告.md,并满足:

  • 中文输出
  • 结构完整,适合长期迭代
  • 不编造论文中不存在的实验、公式或结论
  • 对不确定内容明确写"论文未明确说明"或"需要进一步核对"
  • 在合适位置调用 mermaid skill 生成 Mermaid 图,至少 1 张,通常 2-3 张更合适
  • 如果需要产出多份报告,继续沿用标题做前缀,并通过后缀区分,例如 {论文标题}_报告_复查1.md、{论文标题}_报告_分享版.md

优先使用 report-outline.md 中的结构。

4. 初稿完成要求(必须执行)⚠️

生成初版报告后,必须立即把报告文件交付给用户:

  • 交付报告文件:{论文标题}_报告.md
  • 如果当前渠道支持文件发送,优先直接发送文件
  • 如果当前渠道不支持文件发送,至少明确给出可访问路径
  • 提醒用户这是初稿
  • 如果你判断值得继续复查,可以补一句“如有需要我可以再复查一轮”,但不要默认已安排

示例:

✅ 论文初稿已生成!

📄 报告文件:<报告文件路径或文件>
📝 当前版本:v1.0 初稿
如果你要,我可以再复查一轮,补实验细节和边界条件。

5. 报告写作要求

报告至少覆盖这些内容:

  • 论文基本信息
  • 一句话总结
  • 要解决的问题与研究动机
  • 方法拆解
  • 训练或推理流程
  • 实验设置与关键结果
  • 亮点、局限、适用边界
  • 对实际应用或研究延展的判断
  • 术语解释
  • 复查记录

调用 mermaid skill 时可优先考虑这些图:

  • 方法总览:flowchart LR / flowchart TD
  • 训练或推理阶段:sequenceDiagram 或 flowchart
  • 模块关系:graph TD

只保留真正能帮助理解的图;调用 mermaid skill 时不要为了凑数量而加图。

6. 如需复查,必须先征得用户确认

初版报告完成后,默认流程到此结束。

只有在用户明确同意“继续复查”之后,才可以进入后续完善流程。具体要求如下:

  • 先问用户要不要复查,不要自己默认安排
  • 用户同意后,才可安排 1 次或多次延迟复查
  • 如果当前环境支持定时任务、后台任务或提醒能力,可以在获得确认后再安排
  • 如果当前环境不支持真正的定时执行,要明确告诉用户限制,并在报告中写明建议复查方向

7. 复查任务的更新原则

复查时不要整篇推倒重写,遵循增量更新:

  • 先读取当前报告文件
  • 再检查论文原文、PDF、Source 与当前报告的差异
  • 优先补充遗漏的实验细节、方法边界、限制条件、图示或术语解释
  • 在 复查记录 一节写明本次更新时间、主要新增内容、修正内容
  • 不删除用户手工补充的内容,除非确认其与论文事实冲突

输出要求

初版报告完成后的必须操作⚠️

第一步:交付报告文件

  • 如果当前渠道支持文件发送,直接发送 {论文标题}_报告.md
  • 如果当前渠道不支持文件发送,提供清晰可访问的文件路径
  • 附带简短说明:
    • 初稿已完成
    • 当前版本信息
    • 如需复查可继续提出

第二步:汇报基本信息

  • 论文目录路径
  • PDF 文件是否下载成功(以论文标题命名)
  • TeX Source 是否下载成功
  • 报告文件路径(默认是 {论文标题}_报告.md)
  • 是否建议复查,以及如需复查必须先征求用户确认

注意:必须先发送文件,再汇报信息。不要反过来。

如果 TeX Source 不存在或下载失败,要明确说明"源文件不可得",但仍继续完成报告。

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 Interpreter AI skill do?

论文解读助手。适用于用户发送 arXiv 论文链接,并希望下载论文、解读论文、生成读书笔记、做论文拆解或输出详细报告时使用。会在工作目录创建论文文件夹、下载 PDF 与 TeX Source(如有)、生成中文 Markdown 报告。默认先交付初稿,不自动复查;如果用户明确同意,再安排后续复查。不适用于只要简短推荐语的情况。

Why use Paper Interpreter on TypingMind?

Because you install it once and use it with any model. Paper Interpreter 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 Interpreter in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/chujianyun/skills/tree/main/skills/paper-interpreter. 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 Interpreter?

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 Interpreter?

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

Is the Paper Interpreter AI skill free?

It is published on GitHub by chujianyun. 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.

View all

Set up your own AI workspace now

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