Dyz Med Results

Q: What does the Dyz Med Results AI skill do?

把已核实的统计输出、表格和图转写为医学论文结果部分，保持样本量、效应量、置信区间、P 值、模型及分析 层级可追溯。当用户需要撰写或修订结果正文、图表引用或数值一致性时使用；不运行新分析、不补造缺失数字， 也不承担讨论解释。 Use to write results sections while preserving verified effect estimates and numerical provenance.

Community

duyunzhoudyz

dyz-med-results

把已核实的统计输出、表格和图转写为医学论文结果部分，保持样本量、效应量、置信区间、P 值、模型及分析层级可追溯。当用户需要撰写或修订结果正文、图表引用或数值一致性时使用；不运行新分析、不补造缺失数字，也不承担讨论解释。 Use to write results sections while preserving verified effect estimates and numerical provenance.

Overview

Publisher	duyunzhoudyz
Repository	`dyz-med-paper-skills`
Skill name	`dyz-med-results`
Stars	102
Forks	1
Bundled files	6
Links	Skill source Repository Homepage

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.
6 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 Results AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/duyunzhoudyz/dyz-med-paper-skills/tree/main/dyz-med-results
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.

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-results .claude/skills/dyz-med-results

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Dyz Med Results 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 Results 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 Results 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.

医学论文结果部分撰写

写作前提

优先读取：

研究方案或统计分析计划中的主要、次要和探索性分析定义；
可追溯的统计输出或结构化结果；
方法部分中的分析人群、模型和协变量；
表格、图及其数据来源；
目标期刊与适用报告规范。

若只有截图、转述或无法追溯的数字，先标出可用性限制。缺少主要结局结果时，不生成看似完整的结果正文。

核心原则

每个数字逐项复制并核对，不重算统计结果或改原输出；展示舍入须逐值明确精度和规则，计数精确相等。
结果说明“观察到什么”，不解释原因、不比较文献、不写临床建议。
预设主要结局优先；预设次要、敏感性、亚组和事后探索性分析分层呈现。
统计显著不等于临床重要，无统计显著也不等于无效；优先报告效应量及不确定性。
基线 P 值不用于自动选择混杂因素；调整集以方法和实际模型为准。

工作流

1. 建立结果来源表

为每个拟写结果记录：分析名称、预设层级、分析人群、N、事件数、效应量、置信区间、P 值、模型、调整集、来源文件及位置。发现正文、表格与输出冲突时，停止该项写作并列出冲突。

用稳定工件ID analysis-results 映射实际 path/version/sha256，兼容既有 analysis-results.json、analysis-results.yaml、structured_results.yaml等名称，不改名、不凭文件名猜身份。接受有效可追溯的外部统计输出，不要求先运行 dyz-med-analyze。缺来源或未执行的结果保留为unverified。最小结果字段及有定位的报告清单见结构化对账输入合同。

对关键结果概括使用关键结论反查，把拟写句关联到上述来源表或已有论断证据矩阵中的同一条记录；按实际效应、区间、结局层级、设计及可信阈值复核，不只复制上游分类标签。缺少信息保留待核，不新增事实库或执行分析。

2. 确定呈现顺序

通常按参与者流程与描述性信息、主要结局、次要结局、安全性或不良事件、敏感性分析、亚组分析和探索性分析组织。顺序服从研究方案、研究类型和期刊要求。

3. 起草正文

报告各分析的实际分母、事件数或样本量；
给出适合该模型的效应量和置信区间，P 值作为补充；
区分未调整与调整结果，并准确写出模型或调整集；
亚组分析报告各组估计值与不确定性，并以交互检验评价组间差异；不要用“一组显著、另一组不显著” 推断交互；
计划外分析明确标为事后或探索性；
临床阈值只有在预先定义且来源明确时才可作为描述性参照，不在结果段落扩展解释。

4. 处理图表

正文概括主要发现，不逐格重复表格。核对每个图表编号、标题、分母和正文引用均存在且一致。图题、表题位置服从目标期刊要求，不假设所有期刊规则相同。

5. 解释防火墙

标出并移出原因推测、机制、与既往研究比较、价值判断和临床建议。不要静默删除作者内容；把拟移动文字放入 “讨论素材”或变更记录。

6. 可选只读数值对账

仅在用户请求核对时，使用自包含标准库对账脚本。输入为显式工件清单、规范化结果JSON与有定位的报告值JSON；不通用提取Word/PDF、不运行统计模型、不改稿或源结果。现有YAML可继续人工读取；需要机器核对时在获准输出区另建JSON派生工件，同时绑定原件并人工核实转换。

从已加载的本技能 SKILL.md 所在目录定位脚本，将 <本技能目录> 替换为该目录的绝对路径。在论文项目根目录运行；输入、输出及 --root 属于论文项目，技能目录仅提供脚本和模板：

powershell
python -B "<本技能目录>/scripts/check_result_consistency.py" paper/data/stats/result-artifacts.json --root . --report paper/reports/result-consistency-run-001.json --record paper/reports/result-consistency-run-001.check.json --check-id result-consistency-run-001

开发者单元测试在下载的源码仓库内运行：python -B -m unittest discover -s tests -p test_result_consistency.py -v。安装副本不包含仓库测试目录。

所有引用/输出路径相对于显式--root，禁止绝对路径、反斜杠、空段、.、..及链接逃逸；manifest参数自身相对于当前调用目录。输出必须为新文件，拒绝覆盖。输入运行前后按原字节核验。stdout为JSON摘要，领域报告含differences/unverified/matched_values/reported_items/coverage/inputs，其中报告项保留实际定位。独立.check.json含R2同形artifacts/checks记录及已落盘报告的SHA256；不自动写passport。

退出码：0=清单范围内consistent；1=discrepant（仍可并列未核实项）；3=无已检出差异但unverified； 2=参数、格式、路径、I/O或绑定错误（未生成可登记完成检查，检查stdout/stderr；后段写失败可能保留报告）。正常发现差异仍是execution_status=completed而非执行failed。空清单、缺来源、未执行、缺口径、未知字段或无法处理的值不能自动通过。整数严格相等；非整数默认精确比较，仅允许逐值显式十进制舍入，绝不以宽泛容差掩盖236与235。分别核对组别、单位、时间点及P/CI口径，不从P与CI推导相互矛盾，不自动换算HR/OR/RR。

consistent不是全文、模型适用性、来源真实性或医学结论认证；未列入清单的结果会单列为未覆盖。输入字节或版本改变后须新建检查，不能沿用旧结论。无passport也可独立使用这些记录；更新索引前由人审阅。

输出

默认写入 paper/sections/03-results.md，并附一份数值核对表或问题清单。只修改用户指定段落时，保留其余结果内容和编号。

验收标准

正文中的每个数字可追溯到指定输出；
主要、次要、亚组与探索性分析身份清楚；
结果与方法中的人群、模型和调整集一致；
没有新增数字、因果解释或文献比较；
图表编号、正文引用和分母一致；单位、参考组、时间点及展示精度已核对；
机器对账的覆盖范围、差异、未核实项及输入版本明确，不把工具退出0或completed当作科学通过。

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 Results AI skill do?

Why use Dyz Med Results on TypingMind?

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

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

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 Results?

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

Is the Dyz Med Results 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

Firecrawl Build

firecrawl

OrganizationPopular

Integrate Firecrawl into application code whenever a product, agent, or workflow needs web data inside the app — web search, live search results, page scraping, structured extraction, or browser…

Advisor Orchestrator Worker

Shubhamsaboo

CommunityPopular

Use when a task is too large for one model pass, needs parallel research or generation across many subtasks (like researching a dozen competitors at once), or the user asks to orchestrate multiple…

Openai Docs

Use for Codex models/pricing, scheduled tasks, skills, settings, setup, troubleshooting, customization, automations, and self-knowledge—including 'you,' 'your,' 'this app,' or 'this coding agent' when…

Caveman Explore

Read-only repository explorer for cold-start orientation, broad cross-file localization, or when a direct search failed. Skip it when the exact file or symbol is already named. Returns path:line…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

医学论文结果部分撰写

写作前提

核心原则

工作流

1. 建立结果来源表

2. 确定呈现顺序

3. 起草正文

4. 处理图表

5. 解释防火墙

6. 可选只读数值对账

输出

验收标准

配套资源

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now