Dyz Med Registration logo

Dyz Med Registration

Community
duyunzhoudyz
dyz-med-registration

从官方注册平台核实临床试验或其他研究的注册记录,并与方案、分析计划和稿件交叉检查注册时间、研究设计、 结局、样本量及结果报告差异。当用户提供 NCT、ChiCTR、ISRCTN、UMIN 等注册号,询问是否前瞻注册、是否 存在结局切换或需要注册声明时使用;报告规范的全面检查交给 dyz-med-guideline,未查到原始记录时不得生成 确定性注册声明。 Use to check trial registration records against protocols and manuscripts.

Overview

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

Use it in TypingMind

Enable Dyz Med Registration 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 Registration 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 Registration 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.

研究注册与方案一致性核查

核心原则

  • 注册号格式正确不等于记录真实或合规,必须查官方原始记录。
  • 保存检索日期、记录更新时间和页面或 API 地址;注册记录可能被后续修改。
  • 将检索状态、已核实的研究事实、注册时间判断和逐项一致性分开;“未检索到”不等于“未注册”。
  • 差异本身不自动证明不当行为,先核对版本、时间点和合理解释。
  • 不把期刊政策、法律义务和伦理要求混成同一结论;必要时建议咨询目标期刊或合规人员。

输入

优先获取:

  • 注册号、研究标题或 DOI;
  • 研究方案及版本日期;
  • 统计分析计划;
  • 首例入组、数据锁定和分析开始日期;
  • 稿件中的主要/次要结局、样本量和研究组描述;
  • 目标期刊或适用监管环境。

缺少注册号时,可按标题、负责人、申办者和研究条件查找,但要防止误匹配。

工作流程

1. 识别注册平台

  • NCT:ClinicalTrials.gov;
  • ChiCTR:中国临床试验注册中心;
  • ISRCTN、UMIN、ANZCTR 或其他 WHO ICTRP 主注册机构;
  • 欧盟试验按研究时期和适用平台核实;
  • 非试验研究可核查 OSF、PROSPERO 或用户指定的预注册平台。

格式校验只用于选择入口。无法识别的平台,先让用户提供官方链接。

2. 获取官方记录

NCT 记录优先使用 ClinicalTrials.gov API v2:

text
https://clinicaltrials.gov/api/v2/studies/{NCT_ID}

其他平台使用其官方公开页面或接口。记录:

  • 官方标题和注册号;
  • 首次提交、首次公开和最近更新时间;
  • 招募状态与关键日期;
  • 研究类型、分配、盲法和研究组;
  • 计划与实际入组数;
  • 主要和次要结局及测量时点;
  • 结果发布、方案、统计分析计划和数据共享信息;
  • 本次检索日期与来源 URL。

字段名随平台而异,按实际响应映射,不预设不存在的字段。格式有效不能替代取得并核对官方记录; 没有执行查询时不得声称 API 已调用或官方记录已核实。

每次核查单独记录平台、查询条件、日期、范围、取得方式、来源定位和以下检索状态:

  • found:取得官方记录并确认与目标研究对应;只核实实际读到的字段;
  • not_found:检索正常完成,但在所列条件与范围内未找到匹配记录;
  • access_blocked:请求失败、权限或其他访问限制使核查未完成,不能当作零结果;
  • not_checked:尚未执行核查,写明原因。

另列已核实的研究事实及其证据,未核实的字段明确留空或标为未核实。以上四种检索状态本身不产生 “未注册”事实;其他平台的记录须独立核实,不以某平台未命中否定其他平台注册。

3. 判断注册时间

对临床试验,比较注册材料首次提交或公开时间与首例受试者同意或入组时间。依据当前 ICMJE 和目标期刊政策,标记:

  • prospective:满足适用政策的前瞻注册时间;
  • retrospective:首例入组后注册;
  • uncertain:缺少可靠日期、适用政策依据或平台日期含义不明确。

not_found、access_blocked、not_checked 只填写在检索状态中;未取得判断所需证据时,注册时间 保持 uncertain。不要把未找到写成“未注册”。对观察性研究,说明预注册的透明度价值,但不要把 ICMJE 对临床试验的要求机械套用为强制规则。

4. 交叉核对

使用 templates/临床试验注册核对清单.md,逐项比较:

  • 研究设计、研究组和干预;
  • 主要与次要结局的名称、定义和时间点;
  • 入排标准;
  • 计划与实际样本量;
  • 招募、主要完成和研究完成日期;
  • 统计分析计划和方案版本;
  • 结果发布及数据共享声明。

每项保留注册原值、稿件原值、各自定位和比较口径,并标记:

  • MATCH:所核对字段在同一口径、定义和时间点下一致;不能因差异很小而判一致;
  • EXPLAINED_CHANGE:存在差异,但已有可定位的依据和经核对的解释;原值和差值仍保留,不能改写为一致;
  • UNEXPLAINED_CHANGE:已确认存在差异,但解释缺失或尚无证据支持;
  • NOT_REPORTED:已注册项目在已核查稿件及补充材料中缺报,且没有证据支持的未报告解释;
  • UNVERIFIED:资料、定义或可比口径不足以完成核对,写明缺失内容。

样本量分开记录计划数、实际入组数和分析集人数,不将其互换。报告带符号差值(稿件数减注册数)及 差异绝对值;百分比按该差值除以注册数计算并注明分母,分母为零或未知时不计算。 236 对235应保留差值 -1、绝对差1、-0.42%(分母236);无解释时为 UNEXPLAINED_CHANGE, 不能因小于某阈值标为 MATCH,也不能仅凭差异自动判断违规。

主要结局匹配不能关闭其他结局的选择性报告疑点。每个缺报次要结局单列 NOT_REPORTED 与所需材料, 直到取得真实补充报告或证据支持的未报告解释再复核;作者口头接受风险、承诺补报或添加笼统局限性 均不能关闭。未在已核对注册记录列出的新增结局标为探索性候选,并核对是否有预先记录的修订。

5. 检查非试验预注册

OSF、PROSPERO 或其他预注册仅在与研究类型匹配时检查:

  1. 使用当前环境可用的原生工具、官方搜索或用户提供链接;
  2. 核对预注册时间是否早于数据分析;
  3. 比较问题、结局、纳入标准和分析计划;
  4. 平台不可用时记录限制,不调用不存在的本地脚本;
  5. 复用 found / not_found / access_blocked / not_checked,并分列已核实事实,不要求所有研究使用 OSF 或必须预注册;
  6. 未找到或无法访问不生成“本研究未预注册”的确定性声明;确有未预注册的事实依据时说明来源及适用要求,不套用统一负面句式。

6. 生成报告

项目模式下写入 paper/evidence/registration-audit.md;非试验预注册可另写 paper/evidence/preregistration-check.md。

报告包括:

  • 来源、检索日期、记录版本和检索状态;
  • 与检索状态分列的已核实研究事实及缺失字段;
  • 注册时间判断及比较口径;
  • 字段对照表;
  • 未解释差异及严重性;
  • 需要作者确认的事实;
  • 方法和摘要可用的注册声明。

只有已核实的机构、注册号、日期和 URL 才能进入最终声明。无法核实时保留 TBD,不得补造。

完成检查

  • 注册记录来自官方平台;
  • 标识符、检索日期、URL 和记录更新时间已保存;
  • 注册时间与首例入组时间已比较;
  • 主要/次要结局、样本量、研究组和关键日期已核对;
  • 格式有效、四类检索状态、已核实注册事实和注册时间判断没有混淆;
  • 差异有双方原值、来源位置、带符号差值、百分比分母和作者待确认项,不因小差异改判 MATCH;
  • 缺报结局保留 NOT_REPORTED,主要结局匹配未被用于关闭全部选择性报告风险;
  • 注册声明只使用已验证字段;
  • 使用的政策或监管规则已按当前官方来源核实。

配套资源

  • templates/临床试验注册核对清单.md:WHO TRDS 与稿件字段核对骨架。
  • examples/示例-降压药物RCT注册核查.md:虚构教学示例。
  • references/试验注册相关规范与要求.md:官方注册政策与来源。

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 Registration AI skill do?

从官方注册平台核实临床试验或其他研究的注册记录,并与方案、分析计划和稿件交叉检查注册时间、研究设计、 结局、样本量及结果报告差异。当用户提供 NCT、ChiCTR、ISRCTN、UMIN 等注册号,询问是否前瞻注册、是否 存在结局切换或需要注册声明时使用;报告规范的全面检查交给 dyz-med-guideline,未查到原始记录时不得生成 确定性注册声明。 Use to check trial registration records against protocols and manuscripts.

Why use Dyz Med Registration on TypingMind?

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

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

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 Registration?

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

Is the Dyz Med Registration 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 👇