Mindket

DYZ MedPaper

Newversion 1 · updated
Star236

Overview

Gives Claude Code and Codex 32 skills for medical papers: topic choice, PubMed searches, drafting, translation, journal choice and reviewer replies. Built for Chinese doctors and medical graduate students.

DYZ MedPaper is an open-source project on GitHub in the Research category, listed by Mindket. It is free. This is version 1, last updated on . Install it from GitHub as its README says. Get Mindket’s setup notes on your Mindket account, as a zip.

At a glance

Runs in
  • Claude Code: install the skills and give tasks in Chinese
  • Codex: the same skills work here
  • Other agents that support Agent Skills: the README names them too
  • PubMed and Chinese sources such as CNKI, Wanfang and VIP: it designs the searches, and full text still needs your own access

Platform

Claude CodeCoding agent
CodexCoding agent

About

What it is

DYZ MedPaper is a set of 32 skills for Claude Code, Codex and other agents that support Agent Skills. It helps at each stage of a medical paper: choosing a topic, searching literature, drafting, rewriting, translating and answering reviewers. You give instructions in Chinese, and it can draft in Chinese, in English or in both.

Who it suits

It is built for Chinese doctors and medical graduate students who write papers while juggling clinical work. You can start from ward cases or a thesis project and move one step at a time.

IndustryWho uses itHow they use itExample
Clinical medicineDoctors with ward case dataNarrow a broad direction to a question they can search and discussCase data but no clear topic
Postgraduate studyMedical graduate studentsMove a thesis project from topic to a revised draftA supervisor asks for a major rewrite
Journal submissionAuthors preparing a submissionShortlist journals by topic, article type, budget and requirementsChoosing a journal for a finished paper
Peer reviewAuthors with reviewer commentsSplit each comment, plan the text edits and draft a replyA long list of reviewer comments

You can skip it if you do not write medical research papers.

Where to use it

  • Claude Code: install the skills and give tasks in Chinese
  • Codex: the same skills work here
  • Other agents that support Agent Skills: the README names them too
  • PubMed and Chinese sources such as CNKI, Wanfang and VIP: it designs the searches, and full text still needs your own access
Use caseWhoWhat they get back
Topic from case dataCliniciansCandidate topics, a feasibility call and the material still missing
Literature searchGraduate studentsA search plan, notes on key studies and questions worth chasing
Discussion rewriteAuthorsA new discussion draft, a map from results to evidence, reasons for each edit and open questions
Reviewer repliesAuthorsA point-by-point reply letter, the places to edit and a to-do list

How to use it

Start from the step that hurts most and tell the assistant in Chinese what you have and what you want. With only an idea, talk through topics first. With results, start writing. With a draft, edit it. With reviewer comments, work on the revision.

You do not need to learn the names of the 32 skills. You can also ask for one small job, such as translating a paragraph or improving an abstract.

Four skills with synthetic worked examples in the repository
ToolWhat it does
dyz-med-writing-planIts example plans a paper from the research question, through the main findings, to what each discussion paragraph says
dyz-med-manuscript-diagnoseIts example finds the problems behind a rejection, ranks them and plans the fixes
dyz-med-translateIts example sets a Chinese results paragraph beside its English version and notes what must stay and what needs separate handling
dyz-med-revisionIts example answers reviewer comments one by one and records the text changes and the unfinished work

Example

"Here are my results table, a few verified references and a draft discussion. Rewrite the discussion with the main finding first, then a comparison with earlier studies, then the clinical meaning and the limits. List anything without support separately." You get these parts back.

  • A discussion draft organised along the paper's main line
  • A note linking each key claim to its results or reference
  • The reason for each edit
  • Open questions, such as a missing reference or analysis that you must confirm

For newcomers and experts

If you are new, pick the step you are stuck on, such as choosing a topic or answering a reviewer, and describe your material and goal in Chinese. The repository's teaching examples are synthetic, so you can read how a task unfolds before you use your own data.

If you know the field, the useful part is continuity. A paper project can keep notes on how far the draft has come, which numbers are confirmed, what the supervisor asked and how many reviewer comments are open. The assistant reads them first when you return. For statistics, it discusses the plan and prepares code, and you confirm the plan before anything runs where the software and data exist.

  1. Topic from your case data
  2. Literature search
  3. First draft
  4. Supervisor edits
  5. Journal choice
  6. Reviewer replies

Good to know

  • Licensed under PolyForm NC 1.0.0, so read the license file before you reuse it
  • Status: public beta
  • Python 3.10 or newer is listed on the project page
  • The teaching examples are synthetic, not doctor feedback and not published papers
  • Where it cannot verify a requirement, it flags it so you and your supervisor can decide
  • Documentation exists in Chinese and English, and the install steps are in the quick-start section of the README

README and files

README
# DYZ MedPaper

Gives Claude Code and Codex 32 skills for medical papers: topic choice, PubMed searches, drafting, translation, journal choice and reviewer replies. Built for Chinese doctors and medical graduate students.

Made by duyunzhoudyz on GitHub. These notes are Mindket's, written from its README; the project's own files and license are in its repository.

## About

What it is: DYZ MedPaper is a set of 32 skills for Claude Code, Codex and other agents that support Agent Skills. It helps at each stage of a medical paper: choosing a topic, searching literature, drafting, rewriting, translating and answering reviewers. You give instructions in Chinese, and it can draft in Chinese, in English or in both.

Who it suits: It is built for Chinese doctors and medical graduate students who write papers while juggling clinical work. You can start from ward cases or a thesis project and move one step at a time.

```table
Industry | Who uses it | How they use it | Example
Clinical medicine | Doctors with ward case data | Narrow a broad direction to a question they can search and discuss | Case data but no clear topic
Postgraduate study | Medical graduate students | Move a thesis project from topic to a revised draft | A supervisor asks for a major rewrite
Journal submission | Authors preparing a submission | Shortlist journals by topic, article type, budget and requirements | Choosing a journal for a finished paper
Peer review | Authors with reviewer comments | Split each comment, plan the text edits and draft a reply | A long list of reviewer comments
```

You can skip it if you do not write medical research papers.

Where to use it:

- Claude Code: install the skills and give tasks in Chinese
- Codex: the same skills work here
- Other agents that support Agent Skills: the README names them too
- PubMed and Chinese sources such as CNKI, Wanfang and VIP: it designs the searches, and full text still needs your own access

```table
Use case | Who | What they get back
Topic from case data | Clinicians | Candidate topics, a feasibility call and the material still missing
Literature search | Graduate students | A search plan, notes on key studies and questions worth chasing
Discussion rewrite | Authors | A new discussion draft, a map from results to evidence, reasons for each edit and open questions
Reviewer replies | Authors | A point-by-point reply letter, the places to edit and a to-do list
```

How to use it: Start from the step that hurts most and tell the assistant in Chinese what you have and what you want. With only an idea, talk through topics first. With results, start writing. With a draft, edit it. With reviewer comments, work on the revision.

You do not need to learn the names of the 32 skills. You can also ask for one small job, such as translating a paragraph or improving an abstract.

```table
Title: Four skills with synthetic worked examples in the repository
Tool | What it does
dyz-med-writing-plan | Its example plans a paper from the research question, through the main findings, to what each discussion paragraph says
dyz-med-manuscript-diagnose | Its example finds the problems behind a rejection, ranks them and plans the fixes
dyz-med-translate | Its example sets a Chinese results paragraph beside its English version and notes what must stay and what needs separate handling
dyz-med-revision | Its example answers reviewer comments one by one and records the text changes and the unfinished work
```

Example: "Here are my results table, a few verified references and a draft discussion. Rewrite the discussion with the main finding first, then a comparison with earlier studies, then the clinical meaning and the limits. List anything without support separately." You get these parts back.

- A discussion draft organised along the paper's main line
- A note linking each key claim to its results or reference
- The reason for each edit
- Open questions, such as a missing reference or analysis that you must confirm

For newcomers and experts: If you are new, pick the step you are stuck on, such as choosing a topic or answering a reviewer, and describe your material and goal in Chinese. The repository's teaching examples are synthetic, so you can read how a task unfolds before you use your own data.

If you know the field, the useful part is continuity. A paper project can keep notes on how far the draft has come, which numbers are confirmed, what the supervisor asked and how many reviewer comments are open. The assistant reads them first when you return. For statistics, it discusses the plan and prepares code, and you confirm the plan before anything runs where the software and data exist.

```flow
Topic from your case data
Literature search
First draft
Supervisor edits
Journal choice
Reviewer replies
```

Good to know:

- Licensed under PolyForm NC 1.0.0, so read the license file before you reuse it
- Status: public beta
- Python 3.10 or newer is listed on the project page
- The teaching examples are synthetic, not doctor feedback and not published papers
- Where it cannot verify a requirement, it flags it so you and your supervisor can decide
- Documentation exists in Chinese and English, and the install steps are in the quick-start section of the README

## On GitHub, 6 November 2026

- Stars: 236
- Forks: 1
- Open issues and pull requests: 0
- Language: Python
- License: see the repository
- Topics: academic-writing, agent-skills, ai-agents, biostatistics, claude-code, clinical-research, codex, literature-review, manuscript, medical-research, medical-writing, meta-analysis

## Links

- Code: https://github.com/duyunzhoudyz/dyz-med-paper-skills
- Website: https://duyunzhoudyz.github.io/dyz-med-paper-skills/
- Releases: https://github.com/duyunzhoudyz/dyz-med-paper-skills/releases
- Issues: https://github.com/duyunzhoudyz/dyz-med-paper-skills/issues
- Star history: https://www.star-history.com/#duyunzhoudyz/dyz-med-paper-skills&Date

## Get the code

```
git clone https://github.com/duyunzhoudyz/dyz-med-paper-skills.git
```

Then follow the setup in its README. Nothing in this kit runs by itself.
Files
README.md  6 KB

1 file, 6 KB, downloaded as a zip.

What’s new

  • Version 1 · 2026-11-06

Compare with similar

Listed GitHub projects in the same category that share the most topics with this one.

ProductStarsActivityLanguageLicenseLast change
DYZ MedPaper This page236ActivePython—
ex-USSR Kinship ResearchShares codex · claude-code · agent-skills2,005ActivePythonMIT
Scientific Agent SkillsShares clinical-research · agent-skills56,365——MIT—
bioinformatics-agent-skillsShares claude-code · agent-skills75ActivePythonMIT
Numbers as Mindket last read them, from 2026-11-06 to 2026-11-07. Activity is read from each project’s last change on GitHub: Active within 30 days, Quiet within 180, Stale after that.

Reviews

No ratings yet

Write a review

No reviews yet.

More from Mindket

See all from Mindket

Bonsai-27B-GGUF

lmstudio-community · Kit

A GGUF conversion of the 27B Bonsai model for LM Studio, with a 3.80 GB Q1_0 language file and a 0.93 GB BF16 vision projector. Tested for text, vision and par…

New

Runs DeepSeek-V4.1-Flash-1017 as a 2.9 bits-per-weight EXL3 quantization, a 196 GiB copy for people serving large models on their own hardware. Perplexity stay…

New

MusicGen Small

facebook · Kit

Generates short music clips from a text description or an audio prompt, in the small checkpoint of facebook's MusicGen. It suits developers and music hobbyists…

New

Similar projects

See all in Research

Taste Skill

Leonxlnx · Skill

Leonxlnx’s Agent Skill that gives Claude Code and Codex an art direction, pictures from open collections and a real-browser check, so the websites and app scre…

New115k

Archify

tt-a1i · Skill

Generates interactive diagrams and explanatory pages from codebases or textual plans. It allows AI agents to visualize workflows, architecture, and complex log…

New94.8k

Scenario Agent Skills

scenario-labs · Skill

Collection of skills for AI agents to generate images, video, audio, and 3D assets for games and creative projects. Includes integrations for Blender, Unity, U…

New3546