Dyz Med Flowchart logo

Dyz Med Flowchart

Community
duyunzhoudyz
dyz-med-flowchart

从可追溯的研究流程计数生成并核对随机试验、观察性研究、系统综述或范围综述流程图,交付结构化计数、 Mermaid/可渲染图稿、图注和流程叙述。当用户要求 CONSORT、STROBE、PRISMA 或 PRISMA-ScR 流程图时使用; 文献去重与筛选由 dyz-med-screening-pipeline 负责,其他统计图表由 dyz-med-figures-tables 负责。 Use for PRISMA, CONSORT and observational study flow diagrams from traceable counts.

Overview

Publisherduyunzhoudyz
Repositorydyz-med-paper-skills
Skill namedyz-med-flowchart
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 Flowchart 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-flowchart
  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-flowchart .claude/skills/dyz-med-flowchart
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Dyz Med Flowchart 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 Flowchart 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 Flowchart 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.

医学研究流程图生成与核对

核心原则

  1. 流程图只呈现已有、可追溯的事件与计数;不估算缺失数字,也不为了对账改数。
  2. 先确定研究设计和当前适用的报告规范,再选择节点;没有一张通用图适合所有研究。
  3. 每个数字保留来源文件、字段或记录集合,正文、表格和流程图使用同一来源。
  4. 系统综述的检索、去重、筛选和 PRISMA 计数由 dyz-med-screening-pipeline 生成;本技能只读计数并绘图。
  5. 失访比例不能单独决定缺失数据处理方法。只报告流程与差异,把影响分析交给 dyz-med-analyze 或 dyz-med-sensitivity。
  6. 无法渲染时交付 .mmd 或图形规格并标为 not_rendered,不要声称已生成图片。

选择规范

  • 随机试验:使用现行 CONSORT 2025 及与具体设计相符的扩展。
  • 队列、病例对照或横断面研究:按 STROBE 研究对象条目呈现必要流程;STROBE 不要求统一固定版式。
  • 系统综述/Meta:使用 PRISMA 2020 对应的流程图版本,区分数据库/注册平台与其他识别方法。
  • 范围综述:按 PRISMA-ScR 报告,并采用与检索来源匹配的 PRISMA 2020 流程结构。

记录规范名称、版本、扩展和核对日期。若用户要求旧版,保留为明确的历史需求,不称为现行规范。

工作流

1. 收集结构化流程事件

为每个节点记录:

text
node_id | label | count | parent | reason_breakdown
source_file | source_field/query | analysis_set | timepoint | notes

空节点分成:

  • not_applicable:设计上不适用;
  • not_recorded:应有但来源未记录;
  • zero:真实计数为 0。

不要把三者混写为空白。

2. 按设计建立节点

随机试验

按适用情况呈现:

  • 评估资格、排除总数及原因、随机分配;
  • 每组分配、实际接受和未接受干预及原因;
  • 每组失访、停止干预及原因和时间点;
  • 每个分析集纳入人数及排除原因。

不要默认“失访人数 = 未纳入分析人数”。ITT、治疗策略、改良 ITT、符合方案和安全性分析集可能使用不同分母, 必须在节点中写明分析集。

观察性研究

根据设计呈现来源人群、资格评估、排除、纳入、分组/匹配、随访和最终分析。病例对照、横断面、开放队列和 数据库研究的节点不同,不强套两臂试验结构。

系统综述或范围综述

只读 dyz-med-screening-pipeline 的单一 prisma-counts-<run>.json 工件,或用户已有的等价、可复算计数工件。 不创建第二套手工数字;旧 YAML 或无绑定汇总表保留为 unverified,不能仅凭文件名升级为已验证。

对新工具输出先核对独立 prisma-check-<run>.json:

  1. 通过 artifacts 的稳定 id=prisma-counts 找到用户实际路径;核对版本、实际字节 SHA256 和 check.report 哈希。
  2. 检查 scope.domain=prisma_counts,execution_status=completed、applicability=applicable,且 domain_result={namespace:prisma_counts,value:reconciled}。同时要求报告 status=reconciled、finalizable=true。
  3. 将 checks.inputs 与当前清单、规范化数据、实际计数脚本和所有声明依赖逐项核对;输入/版本/报告变化则旧检查 stale,缺绑定或缺文件则 unverified。单独的 completed、文件存在、0退出码或缓存 freshness 都不能代替核对。
  4. discrepancy/invalid/unverified 或存在未解决问题时,只能交付显著标记的审阅草图,注明哪些节点非最终计数; 不能将缺失关联导致的 observed_only 值当作最终0值。不在绘图阶段补决定、补映射或手工修数字。

从该工件的 counts[metric].count/member_ids/unit/filter 与 source_rows/associations 读取:

  • 各数据库、注册平台识别的记录,以及其他方法识别的记录或报告(按所选官方模板区分);
  • 筛选前删除的重复记录、自动化删除和其他删除;
  • 筛选记录与排除记录;
  • 寻求获取、未获取和实际评估的报告;
  • 按一个主要原因分类的全文排除报告;
  • 纳入报告数和纳入研究数。

严格区分 record、report 和 study;一项研究可能对应多份报告,记录和报告也可能多对多。 database_register/other_record/other_direct 分支不混算;other_direct 只有报告路径,没有标题摘要记录等式。 从记录到报告用关联边解释,不使用“筛选记录减排除记录=寻求报告”。not_retrieved 不属于全文排除; retrieved 但尚未评估的报告也不能冒充 reports_assessed。领域报告自带 equations 和 differences,绘图只消费不修复。 逐数据库/方法拆框须保留该工件 source_id 分组对应的成员集合,不制造第二份独立权威汇总。

3. 对账

只对适用于当前结构的关系做检查。例如:

  • 资格评估数与排除、随机/纳入节点之间能否解释;
  • 随机总数是否与各分配组总数一致;
  • 各组“接受 + 未接受”是否与分配数一致;
  • PRISMA 的筛选前删除、筛选、报告获取、全文排除和纳入节点是否可从行级记录重建;
  • 最终分析分母是否与 Table 1、模型输出和正文对应同一分析集。

输出 MATCH、MISMATCH、MISSING_SOURCE 或 NOT_APPLICABLE。发现差异时列出两边数值和来源,不自动修复。

4. 生成图稿

先使用流程图文字骨架确认标签,再生成 Mermaid 或项目既定图形格式。

  • 使用稳定的节点 ID,标签中保留阶段、n 和必要原因。
  • 对用户提供文本做 Mermaid 转义,避免破坏语法。
  • 控制每个框的文字量;长原因清单可移到图注或补充表。
  • 保存图源和渲染文件及权威计数工件的 ID/版本/哈希、metric 绑定,确保后续可编辑。系统综述不再另存可手改的 flow-counts 数值副本;节点清单仅保存 node_id、metric、标签和来源绑定。
  • 渲染后检查截断、箭头方向、字体、对齐、灰度可读性和页面尺寸。

5. 生成图注与流程叙述

图注说明研究设计、分析集、时间点、缩写和规范。流程叙述只使用已核对计数,并与图保持同一术语。不要在流程图 技能中推断缺失数据机制、自动建议多重插补或宣称高失访“使研究无效”。

输出

建议交付:

text
paper/data/figures/flow-counts.yaml
paper/data/figures/flow-diagram.mmd
paper/data/figures/flow-diagram.<svg|png|pdf>
paper/data/figures/flow-check.md
paper/sections/flow-narrative.md

以上 flow-counts.yaml 仅用于非系统综述的结构化计数。系统综述直接消费已绑定的 paper/evidence/prisma-counts-<run>.json 与独立检查回执,图源、图注和正文均引用这一版本,不复制维护第二份计数。 既有格式不强制改名,但须提供等价行级集合、单位与当前版本绑定;不能自动将历史手填汇总标为 reconciled。

标准库计数 CLI 由筛选技能提供,流程图不重新实现它。按已安装的 dyz-med-screening-pipeline 中的说明,将实际计数脚本以相同字节复制到论文项目内(例如 paper/tools/compute_prisma_counts.py),保留许可并在清单中绑定这份副本的路径、版本和哈希,再从论文项目根目录执行。不能直接把项目外的全局安装路径作为清单中的工具工件:

powershell
python -B paper/tools/compute_prisma_counts.py paper/evidence/prisma-inputs-v1.json --root . --output paper/evidence/prisma-counts-run-001.json --check-output paper/evidence/prisma-check-run-001.json --run-id prisma-run-001

它仅处理显式规范化 JSON,不下载或筛选文献;退出码0/1/2/3分别表示声明数据内闭合、错误或差异、参数错误、未核实。 无需安装 passport 才能使用独立回执;缺计数脚本或输入时报告缺项,不伪造运行结果。

完成标准

  • 规范、版本、扩展和研究设计已确认
  • 每个数字有来源,零值/不适用/未记录已区分
  • 适用的分母关系已对账
  • 分析集、时间点、record/report/study 用词正确
  • Mermaid 或其他图源可解析
  • 渲染文件已目视检查,或明确标为未渲染
  • 图注、正文和相关表格使用同一已核对计数

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 Flowchart AI skill do?

从可追溯的研究流程计数生成并核对随机试验、观察性研究、系统综述或范围综述流程图,交付结构化计数、 Mermaid/可渲染图稿、图注和流程叙述。当用户要求 CONSORT、STROBE、PRISMA 或 PRISMA-ScR 流程图时使用; 文献去重与筛选由 dyz-med-screening-pipeline 负责,其他统计图表由 dyz-med-figures-tables 负责。 Use for PRISMA, CONSORT and observational study flow diagrams from traceable counts.

Why use Dyz Med Flowchart on TypingMind?

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

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

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 Flowchart?

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

Is the Dyz Med Flowchart 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 👇