Dyz Med Ideate logo

Dyz Med Ideate

Community
duyunzhoudyz
dyz-med-ideate

把尚未成形的临床观察、兴趣领域、导师方向或数据库线索,转化为结构化且可验证的医学研究问题,并完成 PICO、PECO、PICOS、FINER、机制层级和初步文献缺口判断。当用户说“不知道研究什么”“这个想法能否 做成课题”“想找一个可执行选题”时使用;已有明确问题和数据需要立项时转交 dyz-med-init,已有稿件时不要使用。 Use for clinical research ideation, PICO questions and feasibility exploration.

Overview

Publisherduyunzhoudyz
Repositorydyz-med-paper-skills
Skill namedyz-med-ideate
Stars
102
Forks
1
Bundled files
8
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.

  • 8 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 Ideate 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-ideate
  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-ideate .claude/skills/dyz-med-ideate
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Dyz Med Ideate 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 Ideate 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 Ideate 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.

医学研究选题与问题构建

目标与边界

把模糊想法推进到“可以检索、可以评估、可以讨论研究设计”的问题,不把热点清单当成选题结论。

  • 若用户已有明确问题和可用数据,只补齐必要缺口后建议进入 dyz-med-init。
  • 若用户已有稿件,转交相应写作或审稿技能。
  • 本技能服务于科研设计,不提供个体诊疗建议。
  • 不虚构文献、PMID、检索数量、数据可得性或发表概率。
  • 将文献事实、合理推断和待验证假设明确分开。

工作流程

1. 判断起点

先识别最接近的情形;信息不足时,一次只追问会改变选题方向的关键问题。

情形典型输入推进重点
临床观察“临床上常见某个现象”明确人群、暴露、比较和结局
宽泛兴趣“我对某疾病感兴趣”从疾病领域收窄到可回答的问题
现有数据“手上有一个数据库”先核对变量、样本量、时间结构与合规性
综述意向“想做 Meta 或综述”核对原始研究数量、异质性和近期综述
导师方向“导师让我做某方向”把方向翻译成可检索、可执行的问题
学业或晋升需求“需要完成一篇论文”在时间、资源、伦理和质量之间取可行解
趋势探索“最近什么方向值得做”区分热点、空白、竞争度与本地可行性

至少确认:

  • 目标人群或疾病范围;
  • 可获得的数据、样本或实验条件;
  • 时间、经费、伦理和团队能力限制;
  • 预期研究类型与用途;
  • 用户最在意的新颖性、可行性或临床价值。

2. 结构化研究问题

按问题类型选择框架,不强行套用 PICO。

  • 干预或治疗:PICO 或 PICOS。
  • 暴露与结局:PECO。
  • 诊断研究:PIRO。
  • 定性研究:PEO 或 SPIDER。
  • 预测模型:目标人群、预测时点、候选变量、结局、使用场景和外部验证。

形成一句主问题,并列出:

  • Population:人群、场景和关键纳排条件;
  • Intervention 或 Exposure:定义、剂量、窗口或测量方法;
  • Comparison:对照或参照;
  • Outcome:主结局、次要结局和测量时点;
  • Study design:能够回答该问题的设计。

发现一个要素不可测量时,先调整问题,不要继续包装。

3. FINER 可行性检查

逐项给出“通过、需补充、严重风险”及理由:

维度核心检查
Feasible样本、变量、技术、时间和经费是否足够
Interesting是否对研究者、同行或临床决策有意义
Novel是确认、反驳、扩展,还是新人群、新方法、新场景
Ethical伦理审批、知情同意、隐私和风险是否可接受
Relevant能否推进实践、政策、机制或后续研究

Feasible 或 Ethical 出现严重风险时,不把该方向列为首选;给出可逆的缩小方案或替代设计。

4. 机制层级升级

把问题标记为以下一层:

  • phenomenon:只描述现象;
  • association:检验变量之间的关联;
  • mechanism:检验中介、通路或因果链;
  • translational:连接临床决策、干预或产品路径。

若问题停留在现象或关联层,优先调用 dyz-med-mechanism 做问题升级。该技能不可用时,至少说明:

  • 可能的上游因素、中介、执行环节和表型;
  • 哪些环节已有证据,哪些只是待验证假设;
  • 为什么描述性或流行病学设计在当前阶段仍然合理。

不要为了显得“高级”而强行添加未经支持的机制。

5. 验证文献缺口

开始检索前,先读取 references/search-protocol.yaml。若领域匹配,再读取 references/search-templates/ 下的心血管、肿瘤或公共卫生模板;模板只是起点,必须按当前问题修改。

执行顺序:

  1. 从结构化问题生成主题词、自由词、同义词和缩写。
  2. 使用可用的 PubMed 检索与 MeSH 工具,至少执行一组可复现查询。
  3. 先找近两年的系统综述、指南和决定性研究,再扩大到近五年的关键研究。
  4. 记录检索日期、数据库、完整查询式、筛选条件、结果数和关键标识符。
  5. 对中国人群、国内诊疗路径或本土政策相关问题,再补充中文文献线索;明确网页线索与正式数据库记录的区别。
  6. 若可访问 ClinicalTrials.gov 或其他注册平台,检查正在进行的同题研究。
  7. 若已暴露 OSF 工具,可搜索预印本、注册报告与开放数据;若没有,标记“本轮未核查”,不要调用不存在的本地脚本。
  8. 对决定选题的 1 至 3 篇论文,在可获得全文时使用文档阅读工具核对方法、样本、结果和局限;摘要不能支持的细节不要补写。

若当前环境无法检索,只交付可执行的检索方案,并把缺口状态标记为“未验证”,不能声称缺口成立。

将结果归为:

  • CONFIRMED:现有证据未直接回答该具体问题;
  • PARTIALLY_FILLED:已有部分答案,需要收窄人群、暴露、结局或方法;
  • CLOSED:近期高质量证据已直接回答,应换方向;
  • UNVERIFIED:检索条件不足,暂不能判断。

只把有检索记录支持的状态写成前三类。

6. 形成候选方向

给出 1 个推荐方向和最多 2 个备选方向。每个方向必须包含:

  • 一句话研究问题;
  • 结构化框架;
  • 当前机制层级;
  • 文献缺口及证据状态;
  • 最小可行设计;
  • 数据、伦理、偏倚和竞争风险;
  • 为什么适合用户现有条件;
  • 下一步最小行动。

“发表潜力”只能基于问题质量、证据空白、方法适配度和期刊范围作分级判断,不承诺录用。

标准输出

markdown
## 选题判断

### 推荐方向
- 研究问题:
- 结构化框架:
- 当前层级:
- 缺口状态:
- 关键证据:
- 最小可行设计:
- FINER:
- 主要风险:
- 下一步:

### 备选方向
1.
2.

### 本轮检索记录
- 日期:
- 数据库:
- 查询式:
- 结果与关键标识符:
- 未覆盖来源:

### 决策建议
- 推荐:
- 不推荐:
- 需要用户确认:

完成检查

  • 至少形成 1 个具体、可检索、可执行的问题;
  • 结构化框架与研究类型匹配;
  • FINER 至少覆盖可行性、伦理和相关性;
  • 机制层级已标注,或已解释为何保持描述性设计;
  • 缺口状态有检索记录支撑,无法检索时标为 UNVERIFIED;
  • 所有文献标识符可追溯,不编造引用;
  • 数据可得性、伦理、关键偏倚和竞争风险已说明;
  • 给出 1 至 3 个明确的下一步动作。

配套资源

  • templates/选题结构化工作表.md:收集输入并形成候选问题。
  • examples/示例-社区获得性肺炎选题推导.md:虚构示例,只用于理解流程。
  • references/选题与研究问题相关标准.md:框架与方法学参考。
  • references/search-protocol.yaml:可复现检索与缺口验证规则。
  • references/search-templates/:三个领域的查询模板。

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 Ideate AI skill do?

把尚未成形的临床观察、兴趣领域、导师方向或数据库线索,转化为结构化且可验证的医学研究问题,并完成 PICO、PECO、PICOS、FINER、机制层级和初步文献缺口判断。当用户说“不知道研究什么”“这个想法能否 做成课题”“想找一个可执行选题”时使用;已有明确问题和数据需要立项时转交 dyz-med-init,已有稿件时不要使用。 Use for clinical research ideation, PICO questions and feasibility exploration.

Why use Dyz Med Ideate on TypingMind?

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

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

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 Ideate?

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

Is the Dyz Med Ideate 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 👇