Menu

Not in the top 1,000 by GitHub stars

duyunzhoudyz/dyz-med-paper-skills

医学论文写作与科研助手：面向中国医生和医学研究生的 32 个 Agent Skills，适用于 Claude Code、Codex，覆盖选题、PubMed 文献检索、中英写作、选刊投稿与审稿修回。Medical writing & research skills.

ResearchWriting

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

dyz-med-abstract/SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → 7e195770241d

No earlier version was observed for comparison.

Compare on GitHub

dyz-med-analyze/SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → 7e195770241d

No earlier version was observed for comparison.

Compare on GitHub

dyz-med-cnki/SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Local scripts

First observation → 7e195770241d

No earlier version was observed for comparison.

Compare on GitHub

dyz-med-data-adequacy/SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → 7e195770241d

No earlier version was observed for comparison.

Compare on GitHub

dyz-med-deai/SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Local scripts

First observation → 7e195770241d

No earlier version was observed for comparison.

Compare on GitHub

dyz-med-discussion/SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → 7e195770241d

No earlier version was observed for comparison.

Compare on GitHub

dyz-med-evidence-audit/SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Local scripts

First observation → 7e195770241d

No earlier version was observed for comparison.

Compare on GitHub

dyz-med-export/SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Local scripts

First observation → 7e195770241d

No earlier version was observed for comparison.

Compare on GitHub

dyz-med-figures-tables/SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → 7e195770241d

No earlier version was observed for comparison.

Compare on GitHub

dyz-med-flowchart/SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → 7e195770241d

No earlier version was observed for comparison.

Compare on GitHub

dyz-med-guideline/SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → 7e195770241d

No earlier version was observed for comparison.

Compare on GitHub

dyz-med-ideate/SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → 7e195770241d

No earlier version was observed for comparison.

Compare on GitHub

dyz-med-init/SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → 7e195770241d

No earlier version was observed for comparison.

Compare on GitHub

dyz-med-interpret/SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → 7e195770241d

No earlier version was observed for comparison.

Compare on GitHub

dyz-med-introduction/SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → 7e195770241d

No earlier version was observed for comparison.

Compare on GitHub

dyz-med-journal-finder/SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → 7e195770241d

No earlier version was observed for comparison.

Compare on GitHub

dyz-med-key-literature/SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → 7e195770241d

No earlier version was observed for comparison.

Compare on GitHub

dyz-med-manuscript-diagnose/SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → 7e195770241d

No earlier version was observed for comparison.

Compare on GitHub

dyz-med-mechanism/SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → 7e195770241d

No earlier version was observed for comparison.

Compare on GitHub

dyz-med-methods/SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → 7e195770241d

No earlier version was observed for comparison.

Compare on GitHub

dyz-med-orchestrator/SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → 7e195770241d

No earlier version was observed for comparison.

Compare on GitHub

dyz-med-passport/SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Local scripts

First observation → 7e195770241d

No earlier version was observed for comparison.

Compare on GitHub

dyz-med-registration/SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → 7e195770241d

No earlier version was observed for comparison.

Compare on GitHub

dyz-med-results/SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Local scripts

First observation → 7e195770241d

No earlier version was observed for comparison.

Compare on GitHub

dyz-med-review/SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → 7e195770241d

No earlier version was observed for comparison.

Compare on GitHub

dyz-med-revision/SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → 7e195770241d

No earlier version was observed for comparison.

Compare on GitHub

dyz-med-screening-pipeline/SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Local scripts

First observation → 7e195770241d

No earlier version was observed for comparison.

Compare on GitHub

dyz-med-sensitivity/SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → 7e195770241d

No earlier version was observed for comparison.

Compare on GitHub

dyz-med-submit/SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → 7e195770241d

No earlier version was observed for comparison.

Compare on GitHub

dyz-med-translate/SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Local scripts

First observation → 7e195770241d

No earlier version was observed for comparison.

Compare on GitHub

dyz-med-write/SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → 7e195770241d

No earlier version was observed for comparison.

Compare on GitHub

dyz-med-writing-plan/SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → 7e195770241d

No earlier version was observed for comparison.

Compare on GitHub

View on GitHubAdd to my skills

Verified commit 7e195770241d327715c075fe4d81e33b4748cfff

312GitHub stars
294stars in 7 days
32skills in this repository
7commits in 30 days

Heat

8.0
  • Star growth, last 7 daysNot available
  • Star growth, last 24 hoursNot available
  • Rank movement, last 7 daysNot available
  • Commits, last 30 daysNot available
  • Accounts asking about it through MCP, last 7 daysNot available
  • Hot votes this weekNot available

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

Nov 1, 2026Nov 8, 2026312

30-day change not yet available: not enough history.

Individual skills in this repository

How it works

dyz-med-abstract

When your agent uses it

从已完成正文和已核实结果生成或修订医学论文标题、结构化摘要与关键词，并按目标期刊当前作者须知核对 分节、字数和必报信息。当用户要求写摘要、压缩摘要、起学术标题或制作中英双语摘要时使用；不从缺失正文 中编造结果，也不把内置期刊配置当作实时官方要求。 Use for medical manuscript titles, structured abstracts and bilingual abstracts.

What it loads into context

Frontmatter

119 tokens

Always available to the agent

SKILL.md

1,295 tokens

When the skill is activated

Reference documents

5,667 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

  1. 入口边界
  2. 所需输入
  3. 核心原则
  4. 工作流
  5. 输出
  6. 验收标准
  7. 写作方法参考
  8. 配套资源

Files

  • SKILL.mdcore4,867 bytes
  • agents/openai.yamlasset309 bytes
  • data/term-store.yamlasset2,938 bytes
  • examples/worked-example-zhonghua-trimming.mddoc7,231 bytes
  • references/abstract-reporting-references.mddoc4,371 bytes
  • references/writing-craft.mddoc3,112 bytes
  • templates/abstract-structure-skeleton.mddoc4,891 bytes
  • templates/journals/icmje-default.jsonasset1,064 bytes
  • templates/journals/jama.jsonasset1,283 bytes
  • templates/journals/lancet.jsonasset1,036 bytes
  • templates/journals/nejm.jsonasset920 bytes
  • templates/journals/zhonghua-default.jsonasset2,087 bytes

No excerpt is shown for this license. Read the source on GitHub.

View the complete source on GitHub

Skills included

  • dyz-med-abstract
  • dyz-med-analyze
  • dyz-med-cnki
  • dyz-med-data-adequacy
  • dyz-med-deai
  • dyz-med-discussion
  • dyz-med-evidence-audit
  • dyz-med-export
  • dyz-med-figures-tables
  • dyz-med-flowchart
  • dyz-med-guideline
  • dyz-med-ideate
  • dyz-med-init
  • dyz-med-interpret
  • dyz-med-introduction
  • dyz-med-journal-finder
  • dyz-med-key-literature
  • dyz-med-manuscript-diagnose
  • dyz-med-mechanism
  • dyz-med-methods
  • dyz-med-orchestrator
  • dyz-med-passport
  • dyz-med-registration
  • dyz-med-results
  • dyz-med-review
  • dyz-med-revision
  • dyz-med-screening-pipeline
  • dyz-med-sensitivity
  • dyz-med-submit
  • dyz-med-translate
  • dyz-med-write
  • dyz-med-writing-plan

Repository facts

License
No license detected
Created
Nov 1, 2026
Last pushed
Nov 1, 2026
Forks
1
Open issues
0
Project activity
Active

Before you install

Local scripts

Automated signals, not a guarantee

Checked Nov 6, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 6 notes
  • dyz-med-export/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • dyz-med-flowchart/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • dyz-med-passport/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • dyz-med-results/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • dyz-med-review/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • dyz-med-screening-pipeline/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
Show all 92 signals by file

dyz-med-analyze/references/methodology-references.md

  • Network accessline 12
    - **CONSORT 2025**——现行随机试验报告规范，已取代 CONSORT 2010；统计方法、分析人群、结局估计和   不确定性报告应按当前清单核对：   https://www.bmj.com/content/389/bmj-2024-081123
  • Network accessline 13
    不确定性报告应按当前清单核对：   https://www.bmj.com/content/389/bmj-2024-081123 - **STROBE**——观察性研究报告规范，第12项（统计方法，含混杂控制、缺失数据处理、亚组/交互分析说明）
  • Network accessline 14
    https://www.bmj.com/content/389/bmj-2024-081123
  • Network accessline 16
    与本技能的"混杂因素处理"、"计划外分析声明区"直接呼应。 - **TRIPOD+AI**——预测模型开发与验证研究的现行报告框架；适用时从 EQUATOR 页面进入当前材料：   https://www.equator-network.org/reporting-guidelines/tripod-statement/
  • Network accessline 18
    https://www.equator-network.org/reporting-guidelines/tripod-statement/

dyz-med-cnki/references/literature-cli.md

  • Network accessline 23
    授权文件含 query_sha256（query.txt 原始字节）、purpose=public_literature_search、destination=https://eutils.ncbi.nlm.nih.gov/entrez/eutils/、confirmed_at，以及 source.kind=human、actor_id、statement、reference。由助手根据真实会话授权记录填写，不要求用户手写，不补造确认。记录仅供追溯，不认证身份。已有明确授权可
  • Network accessline 33
    接口依据：[NCBI E-utilities](https://www.ncbi.nlm.nih.gov/books/NBK25501/)。本工具不宣称完成中文数据库检索、全文阅读、撤稿核查或系统综述纳入。

dyz-med-cnki/scripts/import_references.py

  • Executable scriptline 1
    #!/usr/bin/env python3

dyz-med-cnki/scripts/search_pubmed.py

  • Executable scriptline 1
    #!/usr/bin/env python3
  • Network accessline 14
    BASE = 'https://eutils.ncbi.nlm.nih.gov/entrez/eutils/'

dyz-med-cnki/scripts/verify_references.py

  • Executable scriptline 1
    Executable file
  • Network accessline 21
    HOSTS = {"crossref": "https://api.crossref.org",
  • Network accessline 22
    "pubmed": "https://eutils.ncbi.nlm.nih.gov"}

dyz-med-cnki/templates/search-record-skeleton.md

  • Network accessline 53
    极少数不在首版允许字符集内的合法DOI也交人工核实，不据格式判虚构。PMID为1至10位正整数字符串。 - 同时提供PMID/DOI时仅请求PubMed，取得元数据后在本地核对两个字段；仅DOI时请求Crossref。   没有可用标识符不做题名猜搜；固定目的地为`https://api.crossref.org`与`https://eutils.ncbi.nlm.nih.gov`。
  • Network accessline 54
    - 同时提供PMID/DOI时仅请求PubMed，取得元数据后在本地核对两个字段；仅DOI时请求Crossref。   没有可用标识符不做题名猜搜；固定目的地为`https://api.crossref.org`与`https://eutils.ncbi.nlm.nih.gov`。 - 至少核对请求标识符和title；可选字段仅在提供时核对。题名/期刊/作者使用Unicode NFKC、大小写、
  • Network accessline 55
    没有可用标识符不做题名猜搜；固定目的地为`https://api.crossref.org`与`https://eutils.ncbi.nlm.nih.gov`。
  • Network accessline 92
    "purpose":"reference_identity_verification",   "content_category":"public_bibliographic_identifiers",   "destinations":["https://api.crossref.org","https://eutils.ncbi.nlm.nih.gov"],
  • Network accessline 93
    "content_category":"public_bibliographic_identifiers",   "destinations":["https://api.crossref.org","https://eutils.ncbi.nlm.nih.gov"],   "fields":["doi","pmid"],
  • Network accessline 94
    "destinations":["https://api.crossref.org","https://eutils.ncbi.nlm.nih.gov"],

dyz-med-data-adequacy/references/规范与文献清单.md

  • Network accessline 5
    - **TRIPOD+AI**：回归或机器学习预测模型的报告规范。用于检查数据来源、样本量、缺失、模型开发、验证和性能报告。     https://www.equator-network.org/reporting-guidelines/tripod-statement/
  • Network accessline 6
    https://www.equator-network.org/reporting-guidelines/tripod-statement/

dyz-med-deai/scripts/compare_protected.py

  • Executable scriptline 1
    #!/usr/bin/env python3

dyz-med-evidence-audit/scripts/audit_manuscript.py

  • Executable scriptline 1
    #!/usr/bin/env python3

dyz-med-export/scripts/export_docx.py

  • Executable scriptline 1
    #!/usr/bin/env python3
  • Network accessline 14
    W = 'http://schemas.openxmlformats.org/wordprocessingml/2006/main'
  • Network accessline 15
    R = 'http://schemas.openxmlformats.org/officeDocument/2006/relationships'
  • Network accessline 67
    if cy > 7315200:         cx, cy = round(cx * 7315200 / cy), 7315200     return f'''<w:p><w:r><w:drawing><wp:inline xmlns:wp="http://schemas.openxmlformats.org/drawingml/2006/wordprocessingDrawing">
  • Network accessline 68
    cx, cy = round(cx * 7315200 / cy), 7315200     return f'''<w:p><w:r><w:drawing><wp:inline xmlns:wp="http://schemas.openxmlformats.org/drawingml/2006/wordprocessingDrawing"> <wp:extent cx="{cx}" cy="{cy}"/><wp:docPr id="{index}" name="Figure
  • Network accessline 69
    return f'''<w:p><w:r><w:drawing><wp:inline xmlns:wp="http://schemas.openxmlformats.org/drawingml/2006/wordprocessingDrawing">
  • Network accessline 70
    <wp:extent cx="{cx}" cy="{cy}"/><wp:docPr id="{index}" name="Figure {index}" descr="{escape(caption, {chr(34): '&quot;'})}"/> <a:graphic xmlns:a="http://schemas.openxmlformats.org/drawingml/2006/main"><a:graphicData uri="http://schemas.open
  • Network accessline 71
    <a:graphic xmlns:a="http://schemas.openxmlformats.org/drawingml/2006/main"><a:graphicData uri="http://schemas.openxmlformats.org/drawingml/2006/picture">
  • Network accessline 72
    <pic:pic xmlns:pic="http://schemas.openxmlformats.org/drawingml/2006/picture"><pic:nvPicPr><pic:cNvPr id="{index}" name="figure.png"/><pic:cNvPicPr/></pic:nvPicPr>
  • Network accessline 184
    styles += f'<w:style w:type="paragraph" w:styleId="{name}"><w:name w:val="{name}"/><w:pPr><w:spacing w:after="120" w:line="300" w:lineRule="auto"/>' + ('<w:keepNext/>' if name in {'Title','Heading1','Heading2','Heading3'} else '') + f'</w:p
  • Network accessline 185
    styles += '</w:styles>'     rels = '<Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships"><Relationship Id="rStyles" Type="' + R + '/styles" Target="styles.xml"/>'     for i in range(1, len(media) + 1):
  • Network accessline 186
    rels = '<Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships"><Relationship Id="rStyles" Type="' + R + '/styles" Target="styles.xml"/>'
  • Network accessline 188
    rels += f'<Relationship Id="rImg{i}" Type="{R}/image" Target="media/figure{i}.png"/>'     rels += '</Relationships>'     types = '<Types xmlns="http://schemas.openxmlformats.org/package/2006/content-types"><Default Extension="rels" ContentT
  • Network accessline 189
    rels += '</Relationships>'     types = '<Types xmlns="http://schemas.openxmlformats.org/package/2006/content-types"><Default Extension="rels" ContentType="application/vnd.openxmlformats-package.relationships+xml"/><Default Extension="xml" C
  • Network accessline 190
    types = '<Types xmlns="http://schemas.openxmlformats.org/package/2006/content-types"><Default Extension="rels" ContentType="application/vnd.openxmlformats-package.relationships+xml"/><Default Extension="xml" ContentType="application/xml"/><
  • Network accessline 193
    with ZipFile(dest, 'x', ZIP_DEFLATED) as archive:         archive.writestr('[Content_Types].xml', types)         archive.writestr('_rels/.rels', '<Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships"><Relations
  • Network accessline 194
    archive.writestr('[Content_Types].xml', types)         archive.writestr('_rels/.rels', '<Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships"><Relationship Id="rDoc" Type="' + R + '/officeDocument" Target="word
  • Network accessline 195
    archive.writestr('_rels/.rels', '<Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships"><Relationship Id="rDoc" Type="' + R + '/officeDocument" Target="word/document.xml"/></Relationships>')

dyz-med-figures-tables/references/methodology-references.md

  • Network accessline 7
    - **CONSORT 2025**——现行随机试验报告规范，已取代 CONSORT 2010：   https://www.bmj.com/content/389/bmj-2024-081123
  • Network accessline 8
    https://www.bmj.com/content/389/bmj-2024-081123
  • Network accessline 23
    - **STARD 2015**——诊断准确性研究报告规范，涉及2×2表、ROC曲线报告要求。 - **TRIPOD+AI**——预测模型研究的现行报告框架；从 EQUATOR 页面进入当前清单与解释材料：   https://www.equator-network.org/reporting-guidelines/tripod-statement/
  • Network accessline 25
    https://www.equator-network.org/reporting-guidelines/tripod-statement/

dyz-med-flowchart/references/规范与文献清单.md

  • Network accessline 5
    - **CONSORT 2025 声明**——现行随机试验报告规范，已取代 CONSORT 2010；按具体试验设计同时核对适用扩展：   https://www.bmj.com/content/389/bmj-2024-081123
  • Network accessline 6
    https://www.bmj.com/content/389/bmj-2024-081123
  • Network accessline 12
    meta分析的报告规范，其标志性的四阶段流程图（识别/筛选/资格评估/纳入）是本技能PRISMA分支直接   实现的结构。根据检索是否包含其他方法选择官方流程图版本：   https://www.prisma-statement.org/prisma-2020-flow-diagram
  • Network accessline 14
    https://www.prisma-statement.org/prisma-2020-flow-diagram

dyz-med-guideline/references/references.md

  • Network accessline 9
    - **CONSORT 2025**：随机试验结果报告，已取代 CONSORT 2010。     https://www.bmj.com/content/389/bmj-2024-081123
  • Network accessline 10
    https://www.bmj.com/content/389/bmj-2024-081123
  • Network accessline 12
    - **SPIRIT 2025**：随机试验方案，更新 SPIRIT 2013。     https://www.bmj.com/content/389/bmj-2024-081477
  • Network accessline 13
    https://www.bmj.com/content/389/bmj-2024-081477
  • Network accessline 18
    - **CARE**：病例报告。 - **TRIPOD+AI**：回归或机器学习预测模型；LLM 研究按适用范围检查 TRIPOD-LLM。     https://www.equator-network.org/reporting-guidelines/tripod-statement/
  • Network accessline 19
    - **TRIPOD+AI**：回归或机器学习预测模型；LLM 研究按适用范围检查 TRIPOD-LLM。     https://www.equator-network.org/reporting-guidelines/tripod-statement/ - **ARRIVE 2.0**：动物研究。
  • Network accessline 20
    https://www.equator-network.org/reporting-guidelines/tripod-statement/
  • Network accessline 27
    EQUATOR 指南库：https://www.equator-network.org/reporting-guidelines/

dyz-med-guideline/references/versioned-guidelines.md

  • Network accessline 5
    | 研究类型 | 起始规范 | 官方来源 | 扩展检查 | |---|---|---|---| | 随机试验结果 | CONSORT 2025 | [BMJ statement](https://www.bmj.com/content/389/bmj-2024-081123) | 集群、非劣效、实用性、AI等按实际设计选择 |
  • Network accessline 6
    |---|---|---|---| | 随机试验结果 | CONSORT 2025 | [BMJ statement](https://www.bmj.com/content/389/bmj-2024-081123) | 集群、非劣效、实用性、AI等按实际设计选择 | | 随机试验方案 | SPIRIT 2025 | [BMJ statement](https://www.bmj.com/content/389/bmj-2024-081477) | 方案与试验技术类型 |
  • Network accessline 7
    | 随机试验结果 | CONSORT 2025 | [BMJ statement](https://www.bmj.com/content/389/bmj-2024-081123) | 集群、非劣效、实用性、AI等按实际设计选择 |
  • Network accessline 8
    | 随机试验方案 | SPIRIT 2025 | [BMJ statement](https://www.bmj.com/content/389/bmj-2024-081477) | 方案与试验技术类型 |
  • Network accessline 9
    | 观察性研究 | STROBE | [官方清单](https://www.strobe-statement.org/checklists/) | RECORD等，按数据来源 |
  • Network accessline 10
    | 系统综述 | PRISMA 2020 | [官方清单](https://www.prisma-statement.org/prisma-2020-checklist) | PRISMA-S、ScR、P等按任务 |
  • Network accessline 11
    | 预测模型 | TRIPOD+AI | [官方站点](https://www.tripod-statement.org/) | LLM等实际适用范围 |
  • Network accessline 12
    | 病例报告 | CARE | [官方清单](https://www.care-statement.org/checklist) | 病例特点及期刊要求 |

dyz-med-init/references/报告规范版本清单.md

  • Network accessline 35
    - CONSORT 2025：https://www.bmj.com/content/389/bmj-2024-081123
  • Network accessline 36
    - SPIRIT 2025：https://www.bmj.com/content/389/bmj-2024-081477
  • Network accessline 37
    - EQUATOR 指南库：https://www.equator-network.org/reporting-guidelines/
  • Network accessline 38
    - TRIPOD+AI：https://www.equator-network.org/reporting-guidelines/tripod-statement/

dyz-med-interpret/references/methodology-references.md

  • Network accessline 8
    报告规范基础。 - **CONSORT 2025**——现行随机试验报告规范，要求透明报告结局估计及其不确定性：   https://www.bmj.com/content/389/bmj-2024-081123
  • Network accessline 9
    - **CONSORT 2025**——现行随机试验报告规范，要求透明报告结局估计及其不确定性：   https://www.bmj.com/content/389/bmj-2024-081123 - **STROBE** 第16项——观察性研究同样需要透明报告效应量估计及精确度。
  • Network accessline 10
    https://www.bmj.com/content/389/bmj-2024-081123

dyz-med-orchestrator/references/科研项目管理与可追溯性实践说明.md

  • Network accessline 40
    [Codex 官方 Skills 文档](https://developers.openai.com/codex/skills.md)说明可根据描述隐式选择技能，

dyz-med-passport/scripts/validate_passport.py

  • Executable scriptline 1
    #!/usr/bin/env python3

dyz-med-registration/SKILL.md

  • Network accessline 51
    https://clinicaltrials.gov/api/v2/studies/{NCT_ID}

dyz-med-registration/references/试验注册相关规范与要求.md

  • Network accessline 7
    - **WHO Trial Registration Data Set 1.3.1**：当前页面列出 24 个最小注册数据项。     https://www.who.int/tools/clinical-trials-registry-platform/network/who-data-set
  • Network accessline 8
    https://www.who.int/tools/clinical-trials-registry-platform/network/who-data-set
  • Network accessline 10
    - **ICMJE 临床试验注册政策**：建议临床试验在首位参与者同意入组时或之前，在可接受的公共注册库完成注册；对非试验研究鼓励注册，但不机械套用为同等强制要求。     https://www.icmje.org/recommendations/browse/publishing-and-editorial-issues/clinical-trial-registration.html
  • Network accessline 11
    https://www.icmje.org/recommendations/browse/publishing-and-editorial-issues/clinical-trial-registration.html
  • Network accessline 13
    - **ClinicalTrials.gov API v2**：单项研究记录使用 `/api/v2/studies/{nctId}`；字段结构和 API 版本应以当前官方文档为准。     https://clinicaltrials.gov/data-api/about-api/api-migration
  • Network accessline 14
    https://clinicaltrials.gov/data-api/about-api/api-migration
  • Network accessline 16
    - **CONSORT 2025**：当前随机试验结果报告规范，已取代 CONSORT 2010；注册、方案和开放科学信息按当前条目及目标期刊要求报告。     https://www.bmj.com/content/389/bmj-2024-081123
  • Network accessline 17
    https://www.bmj.com/content/389/bmj-2024-081123
  • Network accessline 19
    - **WHO ICTRP Search Portal**：用于发现 WHO 数据提供方中的注册记录；ChiCTR 是可检索的中国来源之一。     https://www.who.int/tools/clinical-trials-registry-platform/the-ictrp-search-portal
  • Network accessline 20
    https://www.who.int/tools/clinical-trials-registry-platform/the-ictrp-search-portal

dyz-med-results/scripts/check_result_consistency.py

  • Executable scriptline 1
    Executable file

dyz-med-screening-pipeline/references/规范与文献清单.md

  • Network accessline 5
    - **PRISMA 2020 声明**（Page MJ, McKenzie JE, Bossuyt PM, et al. *BMJ* 2021;372:n71）——本技能的   记录、报告和研究计数依据。按检索来源选择官方流程图版本：   https://www.prisma-statement.org/prisma-2020-flow-diagram
  • Network accessline 7
    https://www.prisma-statement.org/prisma-2020-flow-diagram

dyz-med-screening-pipeline/scripts/compute_prisma_counts.py

  • Executable scriptline 1
    #!/usr/bin/env python3

dyz-med-sensitivity/references/methodology-references.md

  • Network accessline 14
    - **Cochrane Handbook for Systematic Reviews of Interventions，Chapter 13**——漏斗图不对称是小研究   效应信号之一，不等于发表偏倚；不对称检验通常至少需要 10 项研究，并应按效应量选择方法：   https://training.cochrane.org/handbook/current/chapter-13
  • Network accessline 16
    https://training.cochrane.org/handbook/current/chapter-13

dyz-med-translate/scripts/compare_protected.py

  • Executable scriptline 1
    #!/usr/bin/env python3

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Some files could not be read; the facts below still hold.

Declared and executed: 4 facts
Signal confidence: 92 facts

and 42 more

Works with

Agent compatibility, from the files in this repository
AgentStatusEvidenceInstall to
Claude CodeCompatibleStandard SKILL.md dyz-med-abstract/SKILL.md.claude/skills/<skill-name>/
CodexCompatibleStandard SKILL.md dyz-med-abstract/SKILL.md.agents/skills/<skill-name>/
CursorCompatibleStandard SKILL.md dyz-med-abstract/SKILL.md.cursor/skills/<skill-name>/
Gemini CLICompatibleStandard SKILL.md dyz-med-abstract/SKILL.md.gemini/skills/<skill-name>/
GitHub CopilotCompatibleStandard SKILL.md dyz-med-abstract/SKILL.md.github/skills/<skill-name>/
OpenCodeCompatibleStandard SKILL.md dyz-med-abstract/SKILL.md.opencode/skills/<skill-name>/
  • Native The repository ships a manifest, folder or frontmatter field for this agent.
  • Compatible A standard SKILL.md that this agent can read.
  • Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.

You might also use

Aperivue/medsci-skills

Agent Skills for medical research — literature search, reporting-guideline & citation checks, statistics, publication figures, submission. Works with Claude Code, Codex, Cursor & …

373GitHub stars

KalarisLabs/research-agent-skills

Turn any AI agent into a research co-scientist: 280+ open-source agent skills for literature reviews, hypotheses, experimental design, data analysis, paper writing, citation verif…

109GitHub stars

gxCaesar/open-research-skills

从选题到可复现发布：十个可独立安装的科研 agent skill —— 顶会/期刊论文、科研绘图、基金 proposal 撰写、方法迭代到 SOTA、冷审与代码数据发布。Ten installable agent skills for research…

63GitHub stars

PangenomeAI/academic-skills-food-nutrition

Open, MIT-licensed food, nutrition & agricultural science research skills for Claude Code, Codex, MiniMax Agent, OpenClaw & Grok Build — multi-agent literature/systematic review, …

41GitHub stars

tigerless-labs/design-harness

Feed your agent papers and half-formed ideas — it links them into a system design you can defend. Markdown keeps the record; a visual canvas makes it readable. An Agent Skill for …

234GitHub stars

FOURTEEN1416/academic-agent-toolkit

250+ academic Agent skills + orchestration engine: math modeling · paper writing · LaTeX · scientific figures · literature review · IP drafting. Host-agnostic (any Agent), quality…

13GitHub stars