TypingMindTypingMindThe best frontend for AI
Dyz Med Evidence Audit logo

Dyz Med Evidence Audit

Community
duyunzhoudyz
dyz-med-evidence-audit

核对医学稿件中的关键论断是否被所引文献、指南、用户数据或明确标注的推断真正支持，输出逐条论断—证据 矩阵、来源定位和待处理问题。当用户要求检查引用是否对题、论断有没有依据、知识缺口是否夸大或结论是否 超出证据时使用；不代替完整同行评议、报告规范检查或参考文献排版。 Use to audit manuscript claims against cited literature and study evidence.

Overview

Publisherduyunzhoudyz
Repositorydyz-med-paper-skills
Skill namedyz-med-evidence-audit
Stars
102
Forks
1
Bundled files
6
Links
Skill sourceRepositoryHomepage
  • 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 Evidence Audit 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-evidence-audit
  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-evidence-audit .claude/skills/dyz-med-evidence-audit
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Dyz Med Evidence Audit 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 Evidence Audit 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 Evidence Audit 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.

医学论断—证据审计

核心原则

  1. 核对的是“来源是否支持这句话”，不是文献标题是否看起来相关。
  2. 把本研究数据、外部文献、指南、作者解释和推测分开。
  3. 题录身份、访问范围与论断支持分列记录；真实 DOI/PMID 或题录匹配不证明支持关系。摘要级核实不能冒充全文核实。
  4. 引用次数、期刊名和影响因子不是证据质量的替代指标。
  5. 不使用任意自引比例、引用量阈值或单一证据等级自动判定稿件对错。
  6. 默认只报告问题和建议；只有用户明确要求修订时才改稿。

所需输入

  • 要审计的稿件版本及段落定位；
  • 参考文献库、PMID、DOI、指南链接或本地全文；
  • 研究方案、结构化统计结果、表格和图；
  • 已有检索记录、关键文献地图和目标期刊（如有）。

工作流

1. 抽取需要核对的关键论断

重点覆盖：

  • 疾病负担、患病率和风险数字；
  • “首次”“尚无研究”“证据有限”等存在性断言；
  • 指南推荐、诊断阈值和治疗效果；
  • 文献比较、机制、因果和临床应用论断；
  • 结论与摘要中的核心判断。

纯粹复述本研究表格的描述性数字可直接做数据溯源，不必当作文献论断。

2. 建立来源与定位

每条论断保留稳定 ID、稿件位置、原句、来源类型和标识符，另行记录：

  • 题录身份核验：实际核对的字段、结果与依据；未完成或有冲突时明确说明；
  • 访问范围与核实层级：实际读到的全文、摘要、数据或未取得内容及原因；
  • 来源定位：页码、章节、表格、图、摘要段或本地数据文件路径，未取得时注明缺失，不编造；
  • 支持裁定：只采用下述六类，并记录理由与处理动作。

文献简报只能作为导航。正式矩阵、快速视图和 claim-locators.yaml 复用同一论断 ID 与来源定位； 快速视图不得把身份已核实或内容可访问显示成论断已获支持，也不得丢失定位或改变裁定。

可消费 dyz-med-cnki 的题录身份报告及独立R2检查记录：核对输入artifact_id/version/sha256、报告路径/哈希、 检查范围、日期、执行状态与mode，不强制导入兄弟脚本或使用passport。领域reference_identity的 matched/mismatch/unverified仅留在题录身份列；offline匹配只证明固定响应重放，在线成功也仅为 metadata_only，不证明全文或摘要已读，更不能自动写入下述六类支持裁定。缺少所需内容时按实际限制 裁定UNVERIFIABLE，不能只把题录unverified机械映射为支持关系结论。

真DOI加错题名的mismatch需记录核对字段、来源、日期与差异；404、429、超时、无结果或缺标识符不等于 文献虚构或论断UNSUPPORTED。原始文献库保持只读，修正建议另列；输入改变后旧检查不能继续证明当前版本。 需要外部查询时核对内容类别、用途、接收方/目的地、发送字段范围与当前可定位的人类授权；任何未知则 零发送。允许发公开DOI/PMID的许可不涵盖未发表稿件、全文、患者信息或作者身份外传。

3. 验证支持关系

  • 本研究数据：对照统计输出、表格、图和分析人群；
  • PMID/DOI：核对题名、研究设计、人群、比较、结局、效应方向和不确定性；
  • 指南：核对发布机构、版本、适用人群、推荐强度和原文范围；
  • 机制：区分直接实验支持、间接生物学合理性和纯推测；
  • 系统综述：核对检索、纳入研究、综合结果和证据确定性，而不只看结论句。

关键论断只有摘要不足以判断时，读取可合法访问的全文相关段落。不要为了核实而大段复制受版权保护的原文。

4. 何时补充检索

普通引用核对采用针对性检索即可。只有以下情形才需要更完整的检索记录：

  • “首次”“没有证据”等需要证明检索覆盖的论断；
  • 知识缺口可能被新研究关闭；
  • 稿件本身是系统综述/范围综述；
  • 发现相互矛盾或明显过时的证据。

记录数据库、日期、完整检索式、筛选范围和结果数；不要把一次简单搜索称为系统综述。

5. 给出裁定

正式矩阵与快速视图统一使用以下六类，不使用另一套支持状态：

裁定含义最小处理要求
SUPPORTED来源直接支持现有措辞可以无需纠正；仍须记录支持理由和来源定位
PARTIAL方向相关，但人群、结局、强度或范围不完全匹配缩小范围、降低措辞强度或补充来源，并指出未获支持的部分
MISSTATED来源真实，但稿件歪曲或夸大对照原文纠正表述、数字或因果强度；无法修复则删除
UNSUPPORTED已核对的材料不支持论断，或未提供支持来源补充支持来源、改为有依据的推测或删除；不得把访问失败当作不支持的证据
UNVERIFIABLE来源或判断所需内容未取得，无法核实支持关系补取合法来源或提交人工决定；记录缺失材料与当前限制
CONFLICTING可靠来源之间存在重要冲突呈现冲突双方及定位，限制结论强度并提交必要的专业判断

只有 SUPPORTED 可以填写“无需处理”。其他五类必须有与理由相符的具体修复建议或待人工决定项， 包括所需证据、待决定事项与剩余限制；不能以空白、“已知悉”或接受风险无动作关闭。作者接受建议或 接受限制不改变支持裁定；改写或补源后须对新句重新核实，不能自动升级为 SUPPORTED。 未知或旧状态不能默认通过，须按现有证据重新裁定；证据不足时保留 UNVERIFIABLE 及原因。

可重复的正文检查

需要核对实际 Markdown 与论断矩阵时，按正文绑定接口运行随包 audit_manuscript.py。 它检查文本变动、遗漏与孤儿引用，不代替六类支持关系判断；无需为普通对话审计强制建立项目。

输出

默认生成：

  • paper/evidence/claim-source-matrix.md
  • paper/evidence/claim-locators.yaml
  • paper/evidence/unsupported-claims.md
  • paper/evidence/search-record.md（仅在实际补充检索时）

矩阵至少包含：ID、稿件位置、论断、来源、题录身份核验、访问范围与核实层级、来源定位、六类支持裁定、理由和建议处理。 快速视图使用相同字段语义、ID、定位和处理要求，不另建事实来源。

验收标准

  • 每条关键论断有来源或明确的无来源状态；
  • 支持关系核对到人群、设计、结局和措辞强度；
  • 摘要级、全文级和数据级核实被清楚区分；
  • 矛盾证据没有被隐藏；
  • 不以引用量或作者身份替代方法学判断；
  • 所有建议都能定位到具体句子；
  • 六类裁定在正文、正式矩阵和快速视图中一致；五类非 SUPPORTED 均有具体动作或待人工决定项；
  • 题录真实、访问成功或作者接受限制均不被当作支持关系已经核实。

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 Evidence Audit AI skill do?

核对医学稿件中的关键论断是否被所引文献、指南、用户数据或明确标注的推断真正支持，输出逐条论断—证据 矩阵、来源定位和待处理问题。当用户要求检查引用是否对题、论断有没有依据、知识缺口是否夸大或结论是否 超出证据时使用；不代替完整同行评议、报告规范检查或参考文献排版。 Use to audit manuscript claims against cited literature and study evidence.

Why use Dyz Med Evidence Audit on TypingMind?

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

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

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 Evidence Audit?

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

Is the Dyz Med Evidence Audit 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.

Related AI Skills

View all
nexu-io logo

Html Ppt Zhangzara Monochrome

nexu-io
OrganizationPopular

A grant proposal on CRISPR base-editing for sickle-cell disease — the hypothesis, the approach, the milestones, and the risk. Built as a decision-grade academic research deck for grant review…

11.2K
96.7K
2 files
View
nexu-io logo

Html Ppt Zhangzara Scatterbrain

nexu-io
OrganizationPopular

A design-school graduation project: a civic wayfinding system for a transit hub — the brief, the process, and the outcome. Built as a decision-grade coursework defense deck for crit panel, faculty.

11.2K
96.7K
2 files
View
paperclipai logo

Create Agent Adapter

paperclipai
OrganizationPopular

Create or modify Paperclip agent adapters across server, UI, and CLI surfaces. Use when adding support for a new CLI agent, API agent, custom process, or adapter package.

16.2K
95.4K
Instructions
View
paperclipai logo

Create Paperclip Bundled Skill

paperclipai
OrganizationPopular

Turn an idea, tweet, or task into a skill in the Paperclip skills catalog (packages/skills-catalog). Use when asked to FIND or MAKE a skill and publish it as a bundled/optional catalog skill: research…

16.2K
95.4K
2 files
View

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇