Dyz Med Sensitivity logo

Dyz Med Sensitivity

Community
duyunzhoudyz
dyz-med-sensitivity

围绕既有医学研究结果的具体不确定性,规划、执行或记录替代模型、缺失数据、偏倚假设、分析人群和研究纳入 变化,产出可追溯的稳健性比较与局限性说明。当用户问“结果稳不稳”“换假设会不会变”或明确要求敏感性分析 时使用;原始主分析交给 dyz-med-analyze,临床重要性解释交给 dyz-med-interpret。 Use for approved sensitivity analyses and robustness comparisons of existing findings.

Overview

Publisherduyunzhoudyz
Repositorydyz-med-paper-skills
Skill namedyz-med-sensitivity
Stars
102
Forks
1
Bundled files
4
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.

  • 4 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 Sensitivity 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-sensitivity
  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-sensitivity .claude/skills/dyz-med-sensitivity
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Dyz Med Sensitivity 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 Sensitivity 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 Sensitivity 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.

医学研究敏感性与稳健性分析

核心原则

  1. 从可能影响结论的具体假设或偏倚出发,不按研究类型机械执行一套固定分析。
  2. 保留预设主分析,不为恢复统计显著性而选择替代模型、删样本或调整阈值。
  3. 尽量在看主要结果前预设敏感性分析;事后新增的分析明确标为探索性。
  4. 比较估计值、区间、方向、临床解释和样本量,不以 P 值是否跨过 0.05 单独定义“稳健”。
  5. 每次分析保存实际输入、代码、参数、日志和输出;没有执行结果时只交付计划。
  6. 无通用 E-value、缺失率或异质性阈值可自动判定 PASS/FAIL。

所需输入

  • 主分析的研究问题、estimand、分析人群、模型和结果;
  • 数据版本、脚本、诊断和缺失数据信息;
  • 预设方案、注册或统计分析计划中的敏感性分析;
  • 需要检验的具体担忧及其可辩护的替代假设;
  • 临床重要阈值(若要判断结论是否发生临床层面的变化)。

无法取得可复现的主分析时,先列出缺项,不从稿件中的手工数值反推新分析。

工作流

1. 定义目标不确定性

对每项敏感性分析写清:

text
担忧 → 为什么可能影响主结果 → 要改变的一个假设/选择
保持不变的部分 → 比较指标 → 预期输出 → 是否预设

一次只改变可解释的因素;同时改变多项时不能判断是哪项驱动差异。

2. 按问题选择分析

担忧可考虑的分析
缺失结局或失访完整病例与主要方法对照、合理的多重插补、delta 调整、tipping-point、极端情景
模型设定预先合理的函数形式、链接函数、方差估计、聚类结构或影响点分析
协变量与混杂基于临床/因果依据的替代调整集、定量偏倚分析;不要用单因素 P 值逐步筛选
RCT 分析人群按 estimand 比较 ITT、治疗策略、符合方案或安全性人群;说明每种人群回答的问题
观察性研究未测量混杂E-value(适用时)或带可辩护参数的定量偏倚分析
Meta 分析leave-one-out、预设风险偏倚排除、替代异质性估计量、固定/随机效应对照、影响诊断
诊断准确性阈值变化、验证偏倚、疾病谱变化和参考标准假设

只有在研究数和方法条件足够时才评估小研究效应。按当前 Cochrane Handbook 的经验规则,漏斗图不对称检验 通常至少需要 10 项研究,还要考虑研究规模是否相近及效应量适用的检验。漏斗图不对称或 Egger 检验不能 单独证明发表偏倚,trim-and-fill 也不能作为自动“纠偏”后的主结果。

3. 审批并执行

  • 把敏感性分析计划和事后状态展示给用户。
  • 涉及新代码、重跑数据或改变分析人群时,先获得明确批准。
  • 复用主分析的已验证读取、清洗和结果导出路径;不要另建一套不一致的数据处理。
  • 除被检验因素外,尽量保持结局、时间点、效应尺度和人群定义不变。
  • 缺少软件或包时报告依赖,不自动安装。
  • 运行失败或假设不适用时保留失败记录,不用另一个“能跑通”的方法静默替换。

4. 谨慎使用 E-value

  • 先确认因果效应方向、无效值、区间和效应尺度。
  • 只对可按风险比尺度解释的结果直接使用标准公式;OR、HR、连续结局等按原方法要求转换并记录假设。
  • 优先使用经过验证的实现或原始方法说明,不手工套用不适用的近似。
  • 对保护性效应使用倒数,并采用离无效值最近的区间界计算区间 E-value。
  • 同时报告点估计和区间 E-value,并与本研究中已测混杂因素的合理强度比较。
  • 不用 1.3、1.5 或 2.0 等通用切点自动标记脆弱或稳健。

E-value 只量化一种未测量混杂情景,不能处理选择偏倚、测量误差、模型错误或所有未测混杂结构。

5. 比较并解释

使用敏感性分析记录表,对每次分析记录:

  • 与主分析相比改变了什么、为什么;
  • 样本量、事件数、估计值、区间和诊断;
  • 效应方向、大小和临床解释是否实质改变;
  • 结论是 robust、not_robust 还是 uncertain,以及判定依据;
  • 是否预设、是否发生执行偏离。

“稳健”只表示在已检验的合理假设范围内结论相近,不表示研究没有其他偏倚。

6. 交付

建议生成:

text
paper/analysis/sensitivity-plan.md
paper/analysis/sensitivity.<R|py>
paper/data/stats/sensitivity-results.<json|yaml>
paper/data/stats/sensitivity-report.md
paper/data/stats/sensitivity-run.log

若只收到汇总结果而没有数据/脚本,交付审阅表和待执行计划,不虚构复分析结果。把关键不稳健或仍不确定的部分 交给讨论/局限性写作;不要阻止用户继续工作,但要保留醒目标记。

完成标准

  • 每项分析对应一个明确不确定性
  • 主分析未被覆盖,预设与事后分析已区分
  • 输入、代码、参数和输出可追溯
  • 稳健性判断比较效应量、区间和临床解释
  • E-value 的尺度、方向、区间界和假设已核对
  • 没有把漏斗图不对称直接称为发表偏倚
  • 未执行的分析没有被写成结果

参考材料

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 Sensitivity AI skill do?

围绕既有医学研究结果的具体不确定性,规划、执行或记录替代模型、缺失数据、偏倚假设、分析人群和研究纳入 变化,产出可追溯的稳健性比较与局限性说明。当用户问“结果稳不稳”“换假设会不会变”或明确要求敏感性分析 时使用;原始主分析交给 dyz-med-analyze,临床重要性解释交给 dyz-med-interpret。 Use for approved sensitivity analyses and robustness comparisons of existing findings.

Why use Dyz Med Sensitivity on TypingMind?

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

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

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 Sensitivity?

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

Is the Dyz Med Sensitivity 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 👇