Dyz Med Init logo

Dyz Med Init

Community
duyunzhoudyz
dyz-med-init

为已有明确研究问题、研究设计和数据或结果的医学论文创建写作项目,识别研究类型、匹配当前报告规范、检查 可行性与关键风险,并生成最小 IMRaD 骨架。当用户说“研究已经做完,准备开始写论文”或要初始化新论文项目 时使用;尚未形成研究问题时先用 dyz-med-ideate,已有稿件需要评估时转 dyz-med-manuscript-diagnose。 Use to initialize a medical manuscript project from an established study.

Overview

Publisherduyunzhoudyz
Repositorydyz-med-paper-skills
Skill namedyz-med-init
Stars
102
Forks
1
Bundled files
9
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.

  • 9 bundled files

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

  • Open source

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

Installation

Install the Dyz Med Init 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/duyunzhoudyz/dyz-med-paper-skills/tree/main/dyz-med-init
  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/duyunzhoudyz/dyz-med-paper-skills.git /tmp/dyz-med-paper-skills
mkdir -p .claude/skills
cp -r /tmp/dyz-med-paper-skills/dyz-med-init .claude/skills/dyz-med-init
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Dyz Med Init 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 Dyz Med Init 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 Dyz Med Init 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.

医学论文项目初始化

目标与边界

把已成形的研究转成可审查、可继续推进的论文项目,不替用户补造研究设计、数据、伦理信息或研究结果。

  • 未确认的内容统一标为 TBD。
  • 报告规范用于提高透明度,不等同于研究质量认证。
  • 研究已完成时不做“观察后把握度”;改报告最小可检测效应、置信区间精度或可识别的效应范围。
  • 写入文件前确认项目根目录;已有文件不得静默覆盖。
  • 本技能初始化结构,不代替关键文献精读、正式统计分析或全文写作计划。

工作流程

1. 确认起点

至少确认:

  • 研究问题和主要目标;
  • 研究设计及研究阶段;
  • 人群、干预或暴露、比较和结局;
  • 数据、统计结果、方案、注册和伦理材料是否可用;
  • 目标期刊或文章类型;
  • 用户希望只得到初始化报告,还是同时创建本地项目结构。

若用户还在找方向,转 dyz-med-ideate。若已有完整或部分稿件,转 dyz-med-manuscript-diagnose。

2. 识别研究设计

选择最具体且有证据支持的类型,例如:

  • 随机或其他干预性试验;
  • 前瞻性或回顾性队列、病例对照、横断面;
  • 诊断准确性、预后或预测模型;
  • 病例报告或病例系列;
  • 系统综述、meta 分析、范围综述或叙述性综述;
  • 定性、卫生经济、质量改进或准实验研究;
  • 动物研究或临床试验方案。

同时选择适用的问题框架:PICO、PECO、PICOS、PIRO、PEO、SPIDER 或 PCC。无法判断时,列出两个候选设计及需要用户确认的差异,不擅自定型。

3. 核对研究问题是否仍有价值

若没有近期、可追溯的检索记录,调用 dyz-med-cnki:

  1. 查找近期系统综述、指南、关键研究和正在进行的注册项目;
  2. 记录数据库、日期、完整查询式、过滤条件、结果数和关键标识符;
  3. 将问题标为 confirmed、partially_filled、closed 或 unverified;
  4. 若问题已被直接回答,说明可更新、收窄或转向的路径。

无法检索时标为 unverified,不声称研究空白成立。

4. 匹配当前报告规范

先读取 references/报告规范版本清单.md,再通过 EQUATOR、规范官网或目标期刊作者指南确认当前版本和扩展。

研究类型默认路由
随机试验结果CONSORT 2025 及适用扩展
随机试验方案SPIRIT 2025 及适用扩展
观察性研究STROBE 及适用扩展
系统综述或 meta 分析PRISMA 2020;范围综述用 PRISMA-ScR
诊断准确性STARD 及适用扩展
病例报告CARE
预测模型TRIPOD+AI;LLM 研究按适用范围考虑 TRIPOD-LLM
动物研究ARRIVE 2.0
卫生经济评价CHEERS 2022
质量改进SQUIRE 2.0
定性研究COREQ 或 SRQR,按方法选择

templates/checklists/ 中的文件是本地版本快照,只在其版本与当前任务要求一致时使用。尤其不得把 CONSORT 2010 当成当前随机试验规范。

5. 做风险预扫描

至少检查:

  • 暴露、干预、比较和结局是否有可复现定义;
  • 时间顺序与研究设计是否支持拟写论断;
  • RCT 是否有前瞻性注册及可核对方案;
  • 主要结局是否存在切换风险;
  • 样本量、事件数、聚类、失访和缺失数据是否足以支持计划分析;
  • 多重比较、亚组和探索性分析是否预先区分;
  • 伦理审批、知情同意或豁免是否可核实;
  • 预测模型是否有足够事件、验证和过拟合控制;
  • 系统综述是否有协议、可复现检索和双人流程安排。

将问题分为:

  • must_resolve:继续写作会导致事实错误、数据矛盾或重大合规风险;
  • important_warning:可以继续生成骨架,但必须显式披露;
  • improvement:质量优化建议。

风险标签不是法律或期刊录用结论。

6. 评估可行性

使用 templates/研究设计确认清单.md 和 templates/feasibility-report.md,输出:

  • 当前已具备的材料;
  • 关键缺口及其影响;
  • 可行、部分可行或暂不可行;
  • 最小降级或重设计方案;
  • 需要临床、统计或伦理确认的问题。

涉及原始数据时,优先调用 dyz-med-data-adequacy。数据不足不必停止所有工作,但结论强度和分析范围必须降到当前可支持上限。

7. 核对叙述与真实数据

当用户同时提供大纲、摘要或旧结果与真实数据文件时:

  1. 明确唯一权威数据源及工作表;
  2. 从权威数据计算总样本量、分组数、主要结局和关键基线信息;
  3. 使用 templates/asset-reconciliation.yaml 记录声称值、实际值和状态;
  4. 将无法核实的值标为 unverified;
  5. 重大差异未由用户确认前,不把相关数字写进新稿。

不要调用不存在的验证脚本;按模板完成可追溯核对即可。

8. 生成初始化产物

仅需聊天交付时,返回:

  • 研究设计与问题框架;
  • 当前报告规范及版本;
  • 检索与新颖性状态;
  • 风险和可行性结论;
  • IMRaD 大纲;
  • 下一步路由。

用户要求创建本地项目时,先确认目标目录和名称。项目名必须拒绝路径分隔符、..、Windows 保留字符、空值和过长名称,并避免覆盖已有项目。创建最小结构:

text
paper/
├── sections/
├── data/
│   ├── figures/
│   ├── tables/
│   └── stats/
├── evidence/
├── references/
├── runtime/
├── submissions/
└── writing/
    └── section_plans/

创建 project.md 和带 TBD 的分节骨架;不要凭空创建注册号、伦理编号、结果或参考文献。

9. 路由下一步

  • 随机或干预性试验:dyz-med-registration;
  • 所有有数据项目:dyz-med-data-adequacy,再进入统计分析;
  • 新稿正式论证:dyz-med-key-literature,再进入 dyz-med-writing-plan;
  • 系统综述、meta 分析或范围综述:dyz-med-screening-pipeline;
  • 尚无目标期刊:dyz-med-journal-finder。

完成检查

  • 起点、设计类型和问题框架已确认;
  • 当前报告规范及适用扩展可追溯;
  • 新颖性状态有检索记录,或明确标为 unverified;
  • 风险和可行性缺口已分级;
  • 数据与叙述冲突没有被静默带入大纲;
  • 文件写入位置已确认且没有覆盖既有内容;
  • IMRaD 只包含已知事实和明确的 TBD;
  • 给出与研究类型匹配的下一步。

配套资源

  • templates/研究设计确认清单.md:初始化信息与风险核对。
  • templates/feasibility-report.md:可行性报告。
  • templates/asset-reconciliation.yaml:叙述与数据核对。
  • templates/checklists/:本地报告规范版本快照,使用前核对版本。
  • examples/示例-老年髋部骨折队列研究立项.md:虚构教学示例。
  • references/报告规范版本清单.md:当前规范路由与版本说明。

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 Dyz Med Init AI skill do?

为已有明确研究问题、研究设计和数据或结果的医学论文创建写作项目,识别研究类型、匹配当前报告规范、检查 可行性与关键风险,并生成最小 IMRaD 骨架。当用户说“研究已经做完,准备开始写论文”或要初始化新论文项目 时使用;尚未形成研究问题时先用 dyz-med-ideate,已有稿件需要评估时转 dyz-med-manuscript-diagnose。 Use to initialize a medical manuscript project from an established study.

Why use Dyz Med Init on TypingMind?

Because you install it once and use it with any model. Dyz Med Init 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 Dyz Med Init in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/duyunzhoudyz/dyz-med-paper-skills/tree/main/dyz-med-init. 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 Dyz Med Init?

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 Dyz Med Init?

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

Is the Dyz Med Init AI skill free?

It is published on GitHub by duyunzhoudyz. 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 👇