Dyz Med Orchestrator logo

Dyz Med Orchestrator

Community
duyunzhoudyz
dyz-med-orchestrator

读取医学论文项目状态与现有工件,生成当前进度地图、关键风险和一个最合适的下一步建议。当用户问“现在 到哪一步”“下一步做什么”“从哪里开始”或需要澄清多种医学任务的选择时使用;状态查询只推荐下一步, 明确的自然语言任务直接匹配最窄职责 Skill,无需说出技能名;不自动串联后续阶段或宣告稿件可投稿。 Use to review medical research workflow progress and recommend the next task.

Overview

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

Use it in TypingMind

Enable Dyz Med Orchestrator 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 Orchestrator 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 Orchestrator 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.

医学论文进度地图与路由

定位

这是地图,不是自动流水线。它可以读取 paper/project-passport.yaml 和项目工件,解释当前状态并推荐下一步。 用户用自然语言提出的明确任务就是选择相应 Skill 的请求,无需手动说出技能名;仅问进度或下一步不构成执行授权。

意图选择与授权边界

  • 先匹配当前请求中职责最窄的 Skill,例如“只翻译这段摘要”直接选 dyz-med-translate,不先运行导航或摘要生成。
  • “写讨论”“精读这三篇论文”等清晰请求可直接选对应 Skill;不要为确认技能名增加一轮提问。
  • 只有请求确有歧义、且上下文不足以区分任务时才澄清,例如“帮我处理一下论文”需分清只读诊断、翻译或修订。
  • “现在到哪一步”“下一步做什么”只读取状态并推荐,不执行推荐项,不自动把阶段串成整篇写作流水线。
  • 选中 Skill 不等于其前置条件已满足。统计任务可先做只读检查和拟定计划,执行分析仍须核对针对当前计划的明确批准; 用户泛称“分析一下”或“继续”不能代替计划批准,也不能授权未列入计划的模型。
  • 导出只生成本地成品,投稿包准备只生成本地材料。上传、发送、外部数据仓库创建和正式提交须另行明确授权并最终确认。 用户提及“投稿”可触发材料准备或授权澄清,但不得据此点击提交。
  • 明确请求中所需的辅助工作仍受目标 Skill 自身边界约束;识别意图不授权所有后续阶段或自动循环修订。

宿主前提

本库的 SKILL.md 描述提供自然语言触发条件,32 份 agents/openai.yaml 显式声明 policy.allow_implicit_invocation: true,供支持该字段的宿主兼容使用。Codex 按描述支持隐式选择, 该策略默认允许;这不是运行时分类器,也不证明 Breezell 或其他宿主读取此字段。实际调用仍依赖技能安装、 索引、宿主能力和会话工具权限。当前结构校验与路由用例不等于部署完成或真实宿主意图调用已验证。

入口判断

先判断属于:

  • 新项目:有想法、方案或数据,但没有完整稿件;
  • 现有稿件:已有摘要、部分/完整草稿、拒稿信或审稿意见;
  • 状态查询:项目已在进行,只需要进度、风险和下一动作。

只有身份或经验会实质改变建议时才询问,不把用户画像当作固定前置步骤。

状态来源

按优先级读取:

  1. 实际存在且可验证的项目文件;
  2. paper/project-passport.yaml 中有来源的已确认状态;
  3. 当前对话中的用户确认;
  4. 未经核实的信息标为 unknown。

文件存在不等于内容完成;需结合验证报告、版本和开放问题判断。读取 passport 时按稳定 artifact ID 查实际路径,核对检查的完整输入集合、版本/字节哈希及报告;分列 execution_status、applicability、domain_result 与 freshness。旧记录没有绑定时保持 unverified,输入变化后相关旧检查为 stale,不将其旧PASS用于当前稿件;无关文件变动不使全部检查失效。人工批准还需目标版本、角色、时间及明确人类来源,字符串或布尔值不能替代。

如已安装 dyz-med-passport,可使用其只读验证脚本和工件合同;没有该技能时仍可读取明确输入并人工核对,不强制兄弟目录或数据库。脚本退出0仅说明声明的绑定有效,不证明科学通过、人类同意或材料可提交。不能仅凭状态查询补造记录、自动更新批准、重跑检查或执行推荐项。

路由地图

新项目常见入口

  • 研究问题不清:dyz-med-ideate
  • 机制假说:dyz-med-mechanism
  • 已有明确问题、设计和数据或结果,准备初始化论文写作项目:dyz-med-init
  • 注册核对:dyz-med-registration
  • 数据是否足够:dyz-med-data-adequacy
  • 系统综述筛选链:dyz-med-screening-pipeline
  • 从零检索中英文文献、建立候选池:dyz-med-cnki
  • 从已有候选池或明确论文清单筛选并全文精读:dyz-med-key-literature

分析与写作

  • 只读数据检查、拟定统计计划及获批后的分析:dyz-med-analyze
  • 稳健性:dyz-med-sensitivity
  • 临床意义解释:dyz-med-interpret
  • 图表与流程图:dyz-med-figures-tables、dyz-med-flowchart
  • 论证计划:dyz-med-writing-plan
  • 分节写作:dyz-med-introduction、dyz-med-methods、dyz-med-results、dyz-med-discussion、dyz-med-abstract
  • 一次性统稿:dyz-med-write(仅用户明确要求)

现有稿件与投稿

  • 先看现状:dyz-med-manuscript-diagnose
  • 论断证据:dyz-med-evidence-audit
  • 报告规范:dyz-med-guideline
  • 全面模拟审稿:dyz-med-review
  • 忠实中英互译:dyz-med-translate
  • 不改变科学事实的语言自然化:dyz-med-deai
  • 实质修订或逐条审稿回复:dyz-med-revision(仅讨论等单节请求优先对应分节 Skill)
  • 期刊匹配:dyz-med-journal-finder
  • 本地格式导出:dyz-med-export
  • 本地投稿材料包:dyz-med-submit(不自动上传、发送或提交)

工作流

以下用于状态查询与导航请求;明确的执行任务按前述意图规则直接匹配,不强制先产出进度地图。

1. 盘点阶段

检查研究问题、设计、伦理/注册、数据、分析、图表、五个正文部分、证据审计、报告规范、审稿、目标期刊、 导出和投稿包的实际状态。

2. 标记状态

使用:

  • complete:有当前工件,且所需验证在相应范围内执行完成、适用、结论满足该领域要求,输入绑定和报告仍为 current;
  • in_progress:已有部分工件;
  • not_started:尚未开始;
  • needs_confirmation:关键事实未确认,或必要检查/批准 stale、unverified(单列原因,不假装检查失败);
  • conflicting:来源冲突;
  • not_applicable:对当前稿件类型不适用。

3. 识别风险

优先呈现可能影响研究可信度或外部操作的风险:数据/数字冲突、设计和结论不匹配、伦理/注册未知、引用无法 核实、稿件版本混乱、目标期刊动态要求未核对。区分“必须先确认的源事实”与“可稍后优化的写作项”。

4. 推荐一个下一步

只推荐当前杠杆最高的一步,并说明:

  • 为什么现在做;
  • 需要什么输入;
  • 会产出什么;
  • 是否需要作者或临床/统计人员确认。

可列一个备选,但不一次性展开完整自动计划。

输出

默认交付:

  • 一张进度地图;
  • 当前阶段的一句话判断;
  • 关键风险与开放问题;
  • 推荐下一 Skill 和所需输入;
  • 如项目有 passport,给出需要修正的索引项;仅状态查询不写回,另获明确更新请求后才修改,保留扩展字段及历史。

状态查询到推荐为止,不自动执行所推荐的 Skill。用户随后提出明确任务时,可用自然语言直接选择对应 Skill, 但仍保留统计计划批准、文件写入位置确认和外部操作授权等前置条件。

验收标准

  • 状态与实际文件、报告和确认一致;
  • 不把文件存在误判为已完成;
  • 清晰任务按最窄职责匹配,无需用户说出技能名;
  • 状态查询只推荐,没有自动串联或绕过批准;
  • 只给一个首选下一步;
  • 不宣告“可投稿”或“已通过”超过现有证据。

配套资源

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 Orchestrator AI skill do?

读取医学论文项目状态与现有工件,生成当前进度地图、关键风险和一个最合适的下一步建议。当用户问“现在 到哪一步”“下一步做什么”“从哪里开始”或需要澄清多种医学任务的选择时使用;状态查询只推荐下一步, 明确的自然语言任务直接匹配最窄职责 Skill,无需说出技能名;不自动串联后续阶段或宣告稿件可投稿。 Use to review medical research workflow progress and recommend the next task.

Why use Dyz Med Orchestrator on TypingMind?

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

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

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 Orchestrator?

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

Is the Dyz Med Orchestrator 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 👇