TypingMindTypingMindThe best frontend for AI
Paper Buddy logo

Paper Buddy

Community
Z4science
paper-buddy

A curated prompt library ("论文搭子/paper-buddy") for the academic paper workflow — vetting research ideas, literature cards, Related Work tables, Introduction structuring, title/abstract writing, claim-vs-evidence checks, Chinese-English translation (LaTeX/Word), expanding/condensing, polishing, removing "AI flavor," method figures, plot/caption help, experiment analysis, consistency scans, derivation checks, harsh reviewer critique, model-choice advice, venue recommendation, cover/rebuttal letters (as .docx), defense prep, and a reviewer's toolkit for AI-text, data-fabrication, and prompt-injection signals in submitted PDFs. Use whenever the user works on a research paper — translating, polishing, checking an Introduction/abstract, building a Related Work table, naming a method, checking consistency, making a figure, writing an experiment analysis, reviewing someone else's submission, picking a venue, writing a cover/rebuttal letter, or prepping a defense — even without saying "paper-buddy."

Overview

PublisherZ4science
Repositorypaper-buddy
Skill namepaper-buddy
Stars
82
Forks
4
Bundled files
24
LicenseMIT
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.

  • 24 bundled files

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

  • Open source

    Published by Z4science on GitHub. Read the source before you install it.

Installation

Install the Paper Buddy 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/Z4science/paper-buddy/tree/main/skill/paper-buddy
  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/Z4science/paper-buddy.git /tmp/paper-buddy
mkdir -p .claude/skills
cp -r /tmp/paper-buddy/skill/paper-buddy .claude/skills/paper-buddy
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Paper Buddy 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 Buddy 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 Buddy 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.

论文搭子 · paper-buddy

一套覆盖"选题 → 文献 → 结构 → 写作 → 图表 → 严谨性自查 → 投稿 → 审稿回复 → 审稿人视角"全流程的 prompt 库。每个子任务都有一条现成的、结构化的 prompt（角色/任务/要求/输出格式/提交前自检/输入），直接套用该 prompt 结构来生成回复，而不是即兴发挥——这些 prompt 是反复打磨过的,结构本身就是价值所在。

怎么用

  1. 判断用户当前处于科研流程的哪个阶段(见下方索引表),读取对应的 references/*.md 文件。
  2. 在该文件里找到匹配的具体子任务 prompt。
  3. 把 prompt 里的"角色/任务/要求/输出格式/提交前自检"结构套用到当前对话,用用户提供的实际内容填入"输入"部分,按该结构组织回复。
  4. 不要跳过"提交前自检"里列的检查点——这些是这套库最有价值的部分,尤其是"不编造引用/数据""标注存疑点""诚实呈现不利结果"这几条,任何子任务都适用。
  5. 如果用户的请求跨越多个子任务(如"帮我把这段翻译成英文并润色"),可以链式套用多个 prompt,或提示用户这是两步操作。

索引:任务 → 参考文件

用户想做什么读取这个文件
判断一个研究 idea 值不值得做、提炼 contribution、给方法起名/acronym、整理文献速读卡片、写 Related Work 对比表references/ideation-and-literature.md
搭 Introduction 结构、写标题/摘要候选、检查全文 claim 与实验证据是否一致(故事线自洽性)、中↔英翻译(LaTeX/Word)、缩写/扩写文本references/structure-and-writing.md
英文论文润色、中文论文润色、逻辑/致命问题检查、去除英文或中文的"AI 味"(翻译腔、滥用词、机械过渡)references/polishing.md
生成论文方法框架图(配图 prompt)、推荐实验绘图方案、写图/表标题、写实验分析段落、符号术语一致性扫描、数字一致性自查、公式推导与量纲校验references/figures-and-rigor.md
让 Claude 扮演严苛审稿人审视全文、按任务类型选用哪个大模型、投稿 venue 推荐、写 cover letter、准备答辩 Q&Areferences/gatekeeping-and-submission.md
回复审稿人:要理论支撑 / 建议的实验能补 / 建议的实验补不了 / 把多条回复整合成完整 response letterreferences/rebuttal-templates.md
作为审稿人审视别人的投稿:识别疑似 AI 生成文本痕迹、数据造假/结果不自洽的可疑信号、稿件 PDF 里针对审稿 AI 的隐藏 prompt injection 指令references/reviewer-toolkit.md
针对具体学科(生信、CV、材料、物理、化学、人文社科)微调上述通用 promptreferences/domain-adaptation.md

产出文件,而不只是聊天里的文字

以下场景默认应该直接生成可下载的文件,而不是把内容原样贴在聊天里,用户拿到手就能用:

  • Cover letter / 审稿回复信(response letter):套用 gatekeeping-and-submission.md 或 rebuttal-templates.md 里的 prompt 生成内容后,用 docx 能力排版成正式的 .docx 文件(参考 /mnt/skills/public/docx/SKILL.md,该 skill 已在其他地方描述过如何用 docx(npm)库创建文档、如何转 PDF 检查排版)。答辩/审稿回复这类需要正式提交或发送的材料同理。
  • 中转英/英转中 Word 场景的翻译或润色:若用户明确说是要用于 Word 文档(而非贴进 LaTeX),同样可以直接产出 .docx,而不是只在聊天里给纯文本。
  • 纯粹用于聊天内讨论、迭代打磨阶段的内容(比如还在来回改的一段翻译、还没定稿的 abstract 候选)不必强行生成文件——判断依据同 file_creation_advice:是"定稿/要发送出去的东西"就产出文件,是"还在讨论"就留在聊天里。

贯穿全库的红线(所有子任务都要遵守)

  • 不编造:引用、DOI、数字、实验结果、审稿人原话——凡是用户没提供的,一律标"原文未提及"或"存疑",绝不脑补。
  • 诚实呈现不利结果:实验分析、审稿回复类任务中,反常或不利的数据必须如实呈现,不得淡化或藏进长句。
  • 修改阈值:润色/逻辑检查类任务中,若原文已经清晰规范,直接说"检测通过/无需修改",不要为了显得有用而强行改写通顺的句子。
  • LaTeX 完整性:涉及 LaTeX 片段的任务,必须保留所有命令、\cite/\ref/\label 键名、数学环境,并正确转义 % _ & 等特殊字符。
  • Word 场景不用 Markdown:凡是标注"Word 场景"的任务,输出必须是不含任何 Markdown 符号(不加粗、不加列表、不加标题符号)的纯文本(生成 .docx 时体现为对应的 Word 格式,而非 Markdown 语法残留)。
  • 审稿人工具箱只给信号,不下结论:reviewer-toolkit.md 里的所有输出都是"建议人工核实的线索",绝不能被当作"这篇论文造假/是 AI 代写"的定论,更不能在审稿意见里直接写成指控性表述。
  • 责任归属:这些 prompt 是协作工具,不是自动化投稿机——生成内容后提醒用户:AI 辅助情况需按投稿要求披露,引用/数据/结论需用户逐一核实,终稿责任在用户自己。

补充说明

  • 这套库覆盖面很广,但作者本人主攻机器学习/AI for Science,domain-adaptation.md 里其他学科(生信/材料/物理/化学/人文社科)的建议是经验性的、深度有限,使用时可以提醒用户这一点。
  • "模型选择"(在 gatekeeping-and-submission.md 里)是一套经验性的工作流偏好,不是定论,如果用户问起该用什么模型做什么任务,可以引用这套框架但同时提醒他们结合最新公开榜单和自己的实测。

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 Buddy AI skill do?

A curated prompt library ("论文搭子/paper-buddy") for the academic paper workflow — vetting research ideas, literature cards, Related Work tables, Introduction structuring, title/abstract writing, claim-vs-evidence checks, Chinese-English translation (LaTeX/Word), expanding/condensing, polishing, removing "AI flavor," method figures, plot/caption help, experiment analysis, consistency scans, derivation checks, harsh reviewer critique, model-choice advice, venue recommendation, cover/rebuttal letters (as .docx), defense prep, and a reviewer's toolkit for AI-text, data-fabrication, and prompt-inj...

Why use Paper Buddy on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Z4science/paper-buddy/tree/main/skill/paper-buddy. 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 Buddy?

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 Buddy?

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

Is the Paper Buddy AI skill free?

Yes. It is published on GitHub by Z4science under the MIT license. 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
openclaw logo

Tag Duplicate Prs Issues

openclaw
OrganizationPopular

Use gitcrawl to search duplicate OpenClaw PRs/issues, group related work in prtags, and sync duplicate state to GitHub.

82.2K
391K
1 files
View
openclaw logo

Update Team Server

openclaw
OrganizationPopular

Update the operator-configured Team server through its canonical owner; trust native validation and acceptance without duplicate checks or schedulers.

82.2K
391K
Instructions
View
openclaw logo

Cloud Image Bake

openclaw
OrganizationPopular

Bake, select, prove, and safely retire a Cloud Worker image with crabbox and config one-liners.

82.2K
391K
Instructions
View
openclaw logo

Acp Router

openclaw
OrganizationPopular

Route plain-language requests for Claude Code, Cursor, Copilot, OpenClaw ACP, OpenCode, Gemini CLI, Qwen, Kiro, Kimi, iFlow, Factory Droid, Kilocode, or explicit ACP harness work into either OpenClaw…

82.2K
391K
Instructions
View

Set up your own AI workspace now

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