Agent skill

Biomedical Paper

by LeoYeAI in LeoYeAI/openclaw-master-skills

AI-powered biomedical manuscript generation with docx output.

MITAuto-check passedDocuments & Office

Install Biomedical Paper

skills CLI
$ npx skills add LeoYeAI/openclaw-master-skills --skill biomedical-paper -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install LeoYeAI/openclaw-master-skills biomedical-paper --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/biomedical-paper-billing .claude/skills/biomedical-paper && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
biomedical-paper
GitHub stars
2.2k
Token cost
~3.3k tokens
SKILL.md length
402 words
Files
6 (incl. references, assets)
Skills in repo
1,235
Repo updated
First seen
Licence
MIT

At a glance

AI-powered biomedical manuscript generation with docx output.

  • Works in 8 steps: 接收与分析 → 生成正文 → 生成参考文献 → …
  • Provides Chinese draft/outline and requests full English research paper
  • SKILL.md covers 核心工作流(必读), 论文类型与模板, 引用预验证工作流(最关键环节) and 标准摘要格式(所有类型通用), plus 5 more sections
  • Runs Python scripts from its folder; reaches ghdx.healthdata.org

What it does

Biomedical Paper is an agent skill from LeoYeAI/openclaw-master-skills. AI-powered biomedical manuscript generation with docx output. Activates when user provides Chinese draft/outline and requests full English research paper. Includes: Abstract, Introduction, Methods, Results, Discussion, References. Specialized for: GBD epidemiology, cohort studies (CHARLS/NHANES), cross-sectional mediation analyses, pharmacovigilance (FAERS). Also supports: Chinese graduate/doctoral thesis (学位论文) formatting. Features: python-docx generation, Vancouver numbered references, journal-specific…

Its SKILL.md is about 3.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including reference files and assets (for example `_meta.json`, `assets/docx_builder.py` and `package.json`).

It sits in Documents & Office, covering Dispute resolution, Word documents and Essays and academic help. It works with python-docx and Microsoft Word. The repository describes itself as: 🧠 Curated collection of 1209+ best OpenClaw skills — weekly updated by MyClaw.ai. The licence is MIT.

When your agent uses it

  • Provides Chinese draft/outline and requests full English research paper
  • Tasks that involve Dispute resolution
  • Tasks that involve Word documents

Example prompts

  • “/biomedical-paper”

Requirements

  • Python 3

Workflow steps

8 steps, taken from the step headings in SKILL.md.

  1. 接收与分析
  2. 生成正文
  3. 生成参考文献
  4. 主要发现
  5. 机制解读
  6. 与其他研究比较
  7. 局限性(≥4条,学位论文要求≥5条)
  8. 结论

What it can do on your machine

Read from SKILL.md and the folder at commit e5199b5. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships script files (Python), which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • ghdx.healthdata.org

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Biomedical Paper loads about 3.3k tokens when it runs, and up to ~5.3k if it reads all its reference files. Until then it costs about 151 tokens; SKILL.md has 402 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~151
When it runs · the whole SKILL.md, loaded when a task matches
~3.3k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~5.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from LeoYeAI/openclaw-master-skills at commit e5199b5, republished under its MIT licence (© LeoYeAI). 402 words, ~3,275 tokens.

Download SKILL.mdSave it as .claude/skills/biomedical-paper/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.
name
biomedical-paper
description
AI-powered biomedical manuscript generation with docx output. Activates when user provides Chinese draft/outline and requests full English research paper. Includes: Abstract, Introduction, Methods, Results, Discussion, References. Specialized for: GBD epidemiology, cohort studies (CHARLS/NHANES), cross-sectional mediation analyses, pharmacovigilance (FAERS). Also supports: Chinese graduate/doctoral thesis (学位论文) formatting. Features: python-docx generation, Vancouver numbered references, journal-specific formatting. Confidence: High (validated workflow with 30+ successful papers)

Biomedical Paper Writing Skill

Produces publication-ready English biomedical manuscripts (or Chinese theses) from drafts using python-docx.


核心工作流(必读)

Phase 1: 接收与分析
  1. 用户提供中文草稿/大纲 → 确认论文类型(见下)
  2. 识别所有数据(统计值、样本量、引用编号)
  3. 立即执行引用预验证:将参考文献列表中的每一条与PubMed核对,标记无法验证的条目
  4. 如有引用缺失/无法验证 → 先补充验证,再生成正文
Phase 2: 生成正文
  1. 按论文类型套用标准结构模板(见本文档各类型模板)
  2. 所有统计数据(β/OR/RR/AAPC/95%CI/p值)必须原文照录,不得编造
  3. 引用编号全程追踪:记录"引用编号映射表"(见下方规范)
Phase 3: 生成参考文献
  1. 按 Vancouver 格式逐条生成引用(见"引用生成规范")
  2. 引用编号以正文中的实际使用为准,不沿用草稿中的旧编号
  3. 参考文献单独存 docx,并附加"引用编号映射表"说明文件

论文类型与模板

Type 1: GBD 流行病学(疾病负担趋势分析)
  • 模板文献: SIICI (Neuroblastoma Asia, GBD 2023)
  • 数据: GBD database (ghdx.healthdata.org)
  • 方法: Joinpoint Regression, EAPC/AAPC, ASIR/ASMR/DALYs
  • 关键词: Neuroblastoma; Neonate; Disease burden; Incidence; Mortality; DALYs; Asia
  • 表格: 4张(按地区/SDI/性别/年龄分层)
  • 图片: 5张(趋势线、choropleth地图)
  • 伦理: GBD IRB豁免(University of Washington)
  • 必须注明: ICD-10 和 ICD-9 代码
Type 2: 队列 / 登记数据库分析
  • 模板文献: CHARLS (Social participation & diabetes)
  • 数据: CHARLS, NHANES, MIMIC, SEER, FAERS 等
  • 方法: K-means聚类, logistic/linear回归, Cox比例风险, 亚组分析
  • 关键词: social participation; [disease]; incidence; [database]; K-means; mediation analysis
  • 表格: 4–13张(描述性统计、聚类轮廓、回归结果、亚组分析)
  • 图片: 5–17张(ROC曲线、K-M曲线、聚类轮廓、趋势图)
  • 伦理: 豁免IRB(去标识数据)
Type 3: 交叉横断面 / 中介分析
  • 模板文献: GBS (Phthalates, SII, cognitive function)
  • 数据: NHANES, 横断面调查
  • 方法: Linear/logistic回归 + 中介分析(bootstrap N=1000)
  • 关键词: phthalates; systemic inflammation; Systemic Immune-Inflammation Index; cognitive function; older adults; mediation
  • 表格: 4张(人口学特征、回归β+95%CI、中介分解)
  • 关键指标: SII = 血小板×中性粒细胞/淋巴细胞; SIRI = 中性粒细胞×单核细胞/淋巴细胞
Type 4: 学位论文(中文,硕士/博士)
  • 语种: 中文(正文)+ 英文摘要
  • 格式要求: 依各院校研究生院规范;正文宋体小四,英文Times New Roman 12pt
  • 章节结构: 前言 → 资料与方法 → 结果 → 讨论 → 结论 → 参考文献
  • 引用格式: 顺序编码制(与期刊Vancouver相同格式)
  • 字数要求: 硕士论文 ≥3万字,博士论文 ≥5万字(各校标准)
  • 核心规范: 不可有占位符(如"[此处补充数据]");表格内数据须与正文一致

引用预验证工作流(最关键环节)

操作步骤
Step 1: 提取用户提供的参考文献列表(全部条目)
Step 2: 对每一条执行 PubMed 搜索或 batch_web_search
        查询格式: "[第一作者] [期刊缩写] [发表年]" 或 "PMID: XXXXXXXX"
Step 3: 标记结果:
        ✅ VERIFIED (PMID匹配) → 可直接使用
        ⚠️  NEEDS_REVIEW → 作者/年份/期刊有偏差,需修正后使用
        ❌ NOT_FOUND → 无法验证,必须替换为可验证的真实文献
Step 4: 如有 NOT_FOUND 条目:
        → 搜索同一研究领域3年内(≤3年)的高质量真实文献替代
        → 记录替换原因(如:原引用#14 [虚构],替换为 Li M等 Syst Rev 2024;13:171)
Step 5: 生成最终"引用编号映射表"(见下)
引用编号映射表(每次必须生成)
markdown
## 引用编号映射表

| 旧编号 | 新编号 | 作者 | 期刊 | 年份 | PMID | 备注 |
|--------|--------|------|------|------|------|------|
| #1   | #1   | Lei J等 | Lancet Reg Health West Pac | 2024 | — | 替换(原文虚构) |
| #8   | #2   | Lei J等 | Lancet Reg Health West Pac | 2024 | — | 与#1合并/替换 |
| #14  | DEL  | —     | —    | —    | —    | 删除(虚构引用) |
| #15  | #14  | Li M等  | Syst Rev | 2024 | — | 重新编号 |
| ...  | ...  | ...   | ...  | ...  | ... | 递进 |

⚠️ 重要教训:PRISm大论文(2026-03-22)中,草稿含虚构引用(#14等),导致引用需全面重编。以后所有任务必须先验证再使用,任何无法PubMed查证的引用必须替换。


标准摘要格式(所有类型通用)

Objective: To [verb] whether/how [exposure/topic] [association] in [population] [using data from] [database].

Methods: [Study design], [N] participants/records from [database, year range]. [Key inclusion criteria]. [Statistical methods: clustering/regression/etc.]. [Mediation/stratification if applicable].

Results: [Main cluster/profile finding] (n=%, n=%). [Key association with OR/β, 95% CI, P-value]. [Subgroup findings]. [Mediation result] (ACME proportion %).

Conclusion: [Main finding]. [Mechanism/pathway implication]. [Policy/practice recommendation].
  • 字数: 250–350词
  • 摘要内不使用小标题(无"Background:", "Methods:"等)

标准前言格式(4段递进结构)

Paragraph 1 — 疾病/暴露负担:
[疾病/暴露]是一种[定义]。[全球/国家患病率,趋势]。[临床意义]。

Paragraph 2 — 流行病学背景:
流行病学研究表明[模式]。[主要危险因素]。[近期变化:COVID-19、老龄化等]。

Paragraph 3 — 研究缺口:
尽管[已有知识],但[缺口:缺乏比较/中介/预测研究]。[地区/数据库比较]有限。

Paragraph 4 — 研究目的:
利用[数据库],本研究旨在:(i) [目的1];(ii) [目的2];(iii) [目的3]。(如为学位论文,还需详述各章安排。)

标准方法格式

GBD 方法
所有数据均从公开可用的 GBD [年份] 数据库获取(http://ghdx.healthdata.org/gbd-results-tool)。
GBD研究整合了多个流行病学数据来源——包括人口登记、调查、已发表文献、
医院记录和死因数据——并采用标准化建模框架生成跨国跨时期的可比负担估算。
[疾病]采用 ICD-10 代码 [X] 和 ICD-9 代码 [Y] 进行识别。
[结局]提取自[国家],时间为[年份]:[列举结局],均以每10万人表示,
并按GBD全球标准人群进行年龄标准化。
本研究使用公开可用的去标识化汇总数据,已获得华盛顿大学机构伦理审查委员会豁免;
无需额外伦理审批。
队列 / 登记数据库方法
本研究为[回顾性/前瞻性] [队列/登记]研究,利用[数据库名称][年份范围]数据。
[纳入标准]: [N]名参与者/记录符合[临床/人口学标准]。
[排除标准]: [因X原因排除的记录数]。
[暴露/干预]: [按X标准定义]。
结局由[临床标准/ICD代码]定义。
统计分析:[回归类型],调整[协变量]。亚组分析按[因素]分层。
[中介/因果分析]采用[方法,bootstrap N次]。
所有分析使用[软件,版本号]完成。
交叉横断面中介方法
本研究为横断面研究,分析[数据库,年份范围]中[N]名[年龄范围]参与者的数据。
[暴露变量]的测量方式/定义:[详述]。
[中介变量]采用[公式/检测方法]评估。
[结局]采用[量表/测试]评估。
关联性采用[linear/logistic]回归分析,调整[协变量]。
中介分析采用[Hayes PROCESS宏/bootstrap方法],bootstrap样本数[N]。

标准结果格式

共纳入[N]名[参与者/记录]。[描述性发现]。

[主要发现]:[关联性,含β/OR/RR、95%CI、P值]。

[次要发现]:[亚组/分层结果]。

[中介发现]:[中介变量]显著中介了[关联性](ACME=[值],95%CI=[范围],P=[值];中介比例=[%])。

[表X–X]展示了[具体结果]。
统计报告规范(严格遵守)
  • 格式: OR=0.77 (95% CI: 0.65–0.91, P=0.002) 或 β=−0.13 (95% CI: −0.21 to −0.05, P=0.001)
  • P值保留3位小数(不是"P < 0.05",而是"P=0.043")
  • 样本量: n=1,234 (45.6%)
  • 禁止使用占位符如 [此处数据] 或 [待补充]

标准讨论格式(5个子节)

1. 主要发现
本研究利用[数据库]提供了[首个/最全面的][主题][分析]。
主要发现表明[主要关联性,含统计数据]。
2. 机制解读
该发现可能由[机制/通路]解释。
[引用文献]提供了支持证据。
3. 与其他研究比较
与[作者,年份]的研究结果一致,该研究报道了[发现]。
相比之下,[作者,年份]发现了[不同结果],这可能归因于[原因]。
4. 局限性(≥4条,学位论文要求≥5条)
本研究存在以下局限性。第一,[GBD: 模型不确定性] / [队列: 回忆/报告偏倚] / [横断面: 因果推断受限]。第二,[生态学研究设计]。第三,[数据代表性局限]。第四,[特定数据缺口]。第五(如适用):[研究设计假设]。
Show full SKILL.md (160 more words)Show less
5. 结论
综上所述,[主要发现]。[机制/通路意义]。本研究结果为[目标人群的针对性预防/临床建议/政策制定]提供了[循证依据]。

引用生成规范

格式要求(Vancouver,悬挂缩进)
编号. 作者A, 作者B, 作者C, 等. 标题. 期刊缩写. 年份;卷(期):页码. doi:XXXXX
  • 作者姓,名首字母(无点),最多作者显示至第3位后加", et al."
  • 期刊名用标准缩写(参考 PubMed Journal List)
  • 含 DOI 时必须附 DOI
  • 悬挂缩进: 0.35英寸
  • 字体: Times New Roman 10pt
  • 段后距: 6pt
python-docx 悬挂缩进实现
python
from docx import Document
from docx.shared import Pt, Inches
from docx.oxml.ns import qn

def add_reference(doc, number, text):
    p = doc.add_paragraph()
    p.paragraph_format.first_line_indent = Inches(-0.35)
    p.paragraph_format.left_indent = Inches(0.35)
    p.paragraph_format.space_after = Pt(6)
    run = p.add_run(f'{number}. {text}')
    run.font.name = 'Times New Roman'
    run._element.rPr.rFonts.set(qn('w:eastAsia'), 'Times New Roman')
    run.font.size = Pt(10)

docx XML 操作规范(进阶)

以下是文档内部操作的硬核规范,修改现有docx时必须遵守。

字体替换(完整遍历run)
python
from docx import Document
from docx.oxml.ns import qn
from docx.shared import Pt

doc = Document(path)

for p in doc.paragraphs:
    for run in p.runs:
        run.font.name = 'Times New Roman'
        run._element.rPr.rFonts.set(qn('w:eastAsia'), 'Times New Roman')
        run.font.size = Pt(11)

doc.save(path)
段落删除
python
body = doc.element.body
for p in doc.paragraphs:
    if 'PLACEHOLDER' in p.text or p.text.strip() == '':
        body.remove(p._element)
段落插入(指定位置)
python
from docx.oxml import OxmlElement
from docx.enum.text import WD_ALIGN_PARAGRAPH

def insert_paragraph_after(doc, ref_para, text, bold=False, font_size=11):
    """在 ref_para 之后插入新段落"""
    new_p = OxmlElement('w:p')
    # 设置格式...
    ref_idx = list(doc.element.body).index(ref_para._element)
    doc.element.body.insert(ref_idx + 1, new_p)
    return new_p
从后往前插入(避免索引偏移)
python
# 需要在多个位置插入时,先收集所有位置,从后往前排序
positions = [idx3, idx1, idx2]  # 要插入的索引
positions.sort(reverse=True)  # 从大到小
for idx in positions:
    body.insert(idx, new_element)
段落属性设置
python
from docx.oxml.ns import qn

p_elem = para._element
pPr = p_elem.get_or_add_pPr()
spacing = OxmlElement('w:spacing')
spacing.set(qn('w:line'), '360')    # 1.5行距 (360=单倍*240)
spacing.set(qn('w:lineRule'), 'auto')
spacing.set(qn('w:after'), '200')   # 段后间距
pPr.append(spacing)

学位论文专门规范(Type 4)

排版要求
项目要求
正文字体宋体小四(12pt)
英文/数字Times New Roman 12pt
行距1.5倍行距
页边距上下2.54cm,左右3cm
一级标题黑体三号,居中
二级标题黑体四号
引用文献顺序编码,同Vancouver格式
章节扩充工作流(扩充+30%等比例要求)
1. 统计原文段落数(Introduction原44段→目标59段,新增15段)
2. 识别可扩充方向:
   - 添加"近期限望变化/新指南"段落(如GOLD 2025更新)
   - 添加"研究方法路径图"说明
   - 添加"全球/区域对比"数据
   - 添加"机制假说"讨论段
3. 每扩充一段,同步更新引用列表(如有新增引用)
4. 生成扩充版后,重新运行引用编号映射
引用编号映射(学位论文特有问题)
  • 插入新引用 → 后续所有编号+1
  • 删除引用 → 后续所有编号-1
  • 必须同步更新:正文引用、全文交叉引用、参考文献列表
  • 生成文件命名:ch8_references_最终版.docx = 每次修订后的最终版本

质量检查清单(每次提交前必查)

引用验证(最高优先级)
  • 所有引用均可 PubMed 查证(含 PMID 或可验证期刊页码)
  • 虚构引用已全部替换为真实文献
  • 引用编号映射表已生成并保存
  • 正文引用编号与参考文献列表完全对应
数据真实性
  • 所有 AAPC/EAPC/β/OR/RR/95%CI/p 值原文照录
  • 无任何占位符([待补充]、[此处数据]等)
  • 表格数据与正文数据完全一致
格式
  • 摘要 ≤350 词,无小标题
  • 前言 4 段(或各校规定段数)
  • 讨论 ≥5 条局限性(学位论文)
  • 参考文献:Vancouver,悬挂缩进0.35",Times New Roman 10pt
  • 图表编号连续(Table 1, Table 2...; Figure 1, Figure 2...)
学位论文额外检查
  • 全文无中英混排标点错误
  • 目录结构符合学校研究生院规范
  • 字数满足学校要求(硕士≥3万字,博士≥5万字)
  • 中英文摘要完整(含研究目的、方法、主要结果、结论)

常见修订模式

用户反馈处理策略
"内容不够充实" / "+30%"识别可扩充方向,添加最新指南段落/对比数据/机制假说
"引用有误"先 PubMed 验证,再更新引用映射表,最后同步正文编号
"占位符未清理"搜索所有 [ 和 ] 模式,逐一补充或删除
"太生硬/不自然"添加衔接词("Interestingly," "Notably," "In contrast,")
"强调某一发现"扩充结果段,增加与亚组/分层数据对比
"添加亚组分析"新增亚组分析表格 + 描述段落 + 更新引用
"格式不一致"统一字体、行距、引用缩进,逐段检查 run.font.name

Python Docx 生成模板(完整版)

python
from docx import Document
from docx.shared import Pt, Inches, RGBColor
from docx.enum.text import WD_ALIGN_PARAGRAPH
from docx.oxml.ns import qn
from docx.oxml import OxmlElement

doc = Document()
style = doc.styles['Normal']
style.font.name = 'Times New Roman'
style.font.size = Pt(11)

# 设置默认中文字体
style._element.rPr.rFonts.set(qn('w:eastAsia'), '宋体')

# ── 标题 ──────────────────────────────────────
title_p = doc.add_paragraph()
title_p.alignment = WD_ALIGN_PARAGRAPH.CENTER
r = title_p.add_run('论文标题(主标题)')
r.bold = True; r.font.size = Pt(16)
r.font.name = 'Times New Roman'
r._element.rPr.rFonts.set(qn('w:eastAsia'), '黑体')

# ── 英文标题(期刊用)───
sub_p = doc.add_paragraph()
sub_p.alignment = WD_ALIGN_PARAGRAPH.CENTER
r = sub_p.add_run('Running Title: 英文简写标题(≤40字符)')
r.italic = True; r.font.size = Pt(10)
r.font.name = 'Times New Roman'

# ── 摘要 ──────────────────────────────────────
doc.add_heading('Abstract', level=2)
abstract_p = doc.add_paragraph()
abstract_p.paragraph_format.first_line_indent = Inches(0.3)
abstract_p.paragraph_format.space_after = Pt(6)
r = abstract_p.add_run('Objective: ... Methods: ... Results: ... Conclusion: ...')
r.font.name = 'Times New Roman'; r.font.size = Pt(11)

# 关键词
kw_p = doc.add_paragraph()
r = kw_p.add_run('Keywords: ')
r.bold = True; r.font.name = 'Times New Roman'
kw_p.add_run('keyword1; keyword2; keyword3; keyword4; keyword5.').font.name = 'Times New Roman'

# ── 中文摘要(学位论文)─────────────────────
doc.add_heading('摘要', level=2)
# ... 同理,中文宋体小四

# ── 正文章节 ──────────────────────────────────
for heading, level in [
    ('Introduction', 2),
    ('Methods', 2),
    ('Results', 2),
    ('Discussion', 2),
    ('Conclusion', 2),
    ('References', 2),
]:
    doc.add_heading(heading, level=level)

# ── 参考文献(悬挂缩进)─────────────────────
def add_ref(doc, num, text):
    p = doc.add_paragraph()
    p.paragraph_format.first_line_indent = Inches(-0.35)
    p.paragraph_format.left_indent = Inches(0.35)
    p.paragraph_format.space_after = Pt(6)
    r = p.add_run(f'{num}. {text}')
    r.font.name = 'Times New Roman'; r.font.size = Pt(10)
    r._element.rPr.rFonts.set(qn('w:eastAsia'), 'Times New Roman')

# 示例
add_ref(doc, 1, 'Lei J, Zhang X, Wang Q. et al. Title. Lancet Reg Health West Pac. 2024;45:101021. doi:10.1016/j.lanwpc.2024.101021')
add_ref(doc, 2, 'Li M, Chen H, Liu G. Title. Syst Rev. 2024;13:171. doi:10.1186/s13643-024-XXX')

doc.save('/workspace/output.docx')
print('✅ Saved: /workspace/output.docx')

输出文件命名规范

期刊论文: [主题]_v1.docx → [主题]_v2.docx → [主题]_最终版.docx
学位论文章节: ch[N]_章节名.docx → ch[N]_章节名_修订版.docx → ch[N]_章节名_最终版.docx
引用列表: ch[N]_references_fixed.docx(修正编号)→ ch[N]_references_updated.docx(+新文献)→ ch[N]_references_最终版.docx
引用映射: citation_mapping_[日期].md

关键规则(永久有效)

规则说明
引用必须先验证任何无法PubMed查证的引用,必须替换为真实文献,禁止保留虚构引用
编号映射全程追踪每次增删引用,同步更新正文编号和映射表
数据原文照录统计值不得四舍五入改变精度,不得凭空编造
无占位符原则正文和表格中不得有任何 [待补充] 类占位符
从后往前插入多点插入时按索引从大到小操作,避免索引偏移
每次修订存档xxx_v1.docx → xxx_v2.docx → xxx_最终版.docx,不覆盖历史版本

© LeoYeAI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 5 other files (references, assets) in skills/biomedical-paper-billing of LeoYeAI/openclaw-master-skills.

  • SKILL.md
  • _meta.json
  • assets/docx_builder.py
  • package.json
  • references/section-templates.md
  • references/style-guide.md

Open the folder on GitHubat commit e5199b5

Compare with similar skills

Biomedical Paper next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Biomedical Paper compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Biomedical Paper this skillLeoYeAI/openclaw-master-skills2.2k—~3.3kAutomated safety check: PassMIT
Academic Paper ComposerAAASS554/codex-academic-paper-skills5391 repos~3.2kAutomated safety check: PassMIT
Thesis DOCXcatlog22/maestro-flow5641 repos~2.5kAutomated safety check: PassMIT
Chinese Thesis WorkbenchZyhSechub/chinese-thesis-workbench-skill578—~2.9kAutomated safety check: PassMIT
Master Thesis Studiodarksider-9/master-thesis-studio-skill129—~3.1kAutomated safety check: PassMIT
PRISMA Systematic Review Writerkeemanxp/slr-prisma1021 repos~7.1kAutomated safety check: PassMIT

Similar skills

  • Academic Paper Composer

    AAASS554/codex-academic-paper-skills

    A skill your agent uses when the user needs to turn a real software engineering / computer science project and an existing thesis draft into a submission-ready undergraduate thesis manuscript.

    539 GitHub starsUsed in 1 repo~3.2k tokens
    Documents & OfficeAuto-check passed
  • Thesis DOCX

    catlog22/maestro-flow

    Create, revise, and format thesis or dissertation Word documents with strict academic formatting control.

    564 GitHub starsUsed in 1 repo~2.5k tokens
    Documents & OfficeAuto-check passed
  • Chinese Thesis Workbench

    ZyhSechub/chinese-thesis-workbench-skill

    Standardizes, drafts, revises, checks and packages Chinese undergraduate theses from school templates, source code and literature, with evidence traceability and DOCX output.

    578 GitHub stars~2.9k tokensUpdated 5 mo ago
    Documents & OfficeAuto-check passed
  • Master Thesis Studio

    darksider-9/master-thesis-studio-skill

    A skill your agent uses for Southeast University-style master's thesis projects from a Word template or existing draft, including optional reverse parsing of an existing DOCX, user intake, outline…

    129 GitHub stars~3.1k tokensUpdated 5 mo ago
    Documents & OfficeAuto-check passed
  • Guides you through writing a systematic literature review to the PRISMA 2020 checklist, producing a journal-format Word manuscript, a flow diagram and APA 7th references.

    102 GitHub starsUsed in 1 repo~7.1k tokens
    Research & ScienceAuto-check passed
  • Formal Modeling Paper Writer

    yushui2022/MathModel-Skill

    Plans, drafts, audits, formats and verifies a formal mathematical-modeling paper from an evidence chain, delivering audited Markdown and a Word file with native equations.

    454 GitHub stars~1.6k tokensUpdated 3 days ago
    Research & ScienceAuto-check passed

More from LeoYeAI/openclaw-master-skills

All 1,235 skills in this repo
  • DevOps Pipeline Management

    LeoYeAI/openclaw-master-skills

    Manages pipelines on a DevOps quality and efficiency platform through its OpenAPI: list workspaces and templates, create, update, run and cancel pipelines, and read run records.

    2.2k GitHub stars~4.2k tokensUpdated 2 mo ago
    Auto-check: notes
  • Feishu Document Collaboration

    LeoYeAI/openclaw-master-skills

    Patches OpenClaw's Feishu extension so an edited document triggers an isolated agent session that reads the doc and replies inline, turning it into a live chat space.

    2.2k GitHub stars~2k tokensUpdated 2 mo ago
    Auto-check passed
  • Files Memory System

    LeoYeAI/openclaw-master-skills

    Multi-context memory management system for OpenClaw agents with group-isolated storage, global shared memory, workspace organization, and group-specific skills isolation.

    2.2k GitHub stars~3.8k tokensUpdated 2 mo ago
    Auto-check passed
  • GEO-Claw AI Visibility Agent

    LeoYeAI/openclaw-master-skills

    Runs a brand's AI-search visibility work end to end: diagnosing how AI platforms represent it, repositioning it, producing AI-optimized content and monitoring ongoing mentions.

    2.2k GitHub stars~4.7k tokensUpdated 2 mo ago
    Auto-check passed
  • Google Workspace CLI

    LeoYeAI/openclaw-master-skills

    Installs and authenticates the gws CLI, then automates Gmail, Drive, Sheets, Calendar, Docs, Chat and Tasks with ready-made recipes, persona bundles and security audits.

    2.2k GitHub stars~2.6k tokensUpdated 2 mo ago
    Auto-check: notes
  • HealthFit Health Advisors

    LeoYeAI/openclaw-master-skills

    Runs four advisor roles, a fitness coach, nutritionist, data analyst and TCM practitioner, to build a health profile and track workouts, diet and wellness over time.

    2.2k GitHub stars~4.4k tokensUpdated 2 mo ago
    Auto-check passed

Questions about Biomedical Paper

What does Biomedical Paper do?

AI-powered biomedical manuscript generation with docx output. Biomedical Paper is an agent skill from LeoYeAI/openclaw-master-skills. AI-powered biomedical manuscript generation with docx output.

When should I use Biomedical Paper?

Biomedical Paper fits situations like: provides Chinese draft/outline and requests full English research paper; tasks that involve Dispute resolution; tasks that involve Word documents.

How do I install Biomedical Paper in Claude Code?

Run `npx skills add LeoYeAI/openclaw-master-skills --skill biomedical-paper -a claude-code`. Or copy the skill folder (skills/biomedical-paper-billing in LeoYeAI/openclaw-master-skills) into .claude/skills/biomedical-paper in your project. Claude Code loads it when a task matches its description.

How do I install Biomedical Paper in Codex?

Run `npx skills add LeoYeAI/openclaw-master-skills --skill biomedical-paper -a codex`. Or copy the skill folder (skills/biomedical-paper-billing in LeoYeAI/openclaw-master-skills) into .agents/skills/biomedical-paper in your project. Codex loads it when a task matches its description.

Can I use Biomedical Paper in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add LeoYeAI/openclaw-master-skills --skill biomedical-paper -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/biomedical-paper, .gemini/skills/biomedical-paper, .github/skills/biomedical-paper and .opencode/skills/biomedical-paper in your project.

What does Biomedical Paper need to run?

Going by SKILL.md and its folder, Biomedical Paper needs Python for the scripts in its folder. Our summary lists: Python 3.

Does Biomedical Paper access the network?

SKILL.md names 1 domain. In commands or code: ghdx.healthdata.org; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Biomedical Paper safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Biomedical Paper use?

Biomedical Paper is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Biomedical Paper use?

About 3.3k tokens (SKILL.md is roughly 13k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2k tokens, read only when the agent opens those files.

What are the alternatives to Biomedical Paper?

Skills that share tags, products or a category with Biomedical Paper: Academic Paper Composer (AAASS554/codex-academic-paper-skills, 539 stars), Thesis DOCX (catlog22/maestro-flow, 564 stars), Chinese Thesis Workbench (ZyhSechub/chinese-thesis-workbench-skill, 578 stars) and Master Thesis Studio (darksider-9/master-thesis-studio-skill, 129 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Biomedical Paper?

LeoYeAI (a GitHub user) maintains it in LeoYeAI/openclaw-master-skills, which has 2,161 GitHub stars. The repository holds 1,235 skills in this directory. The repository was last updated on July 20, 2026.

Source: LeoYeAI/openclaw-master-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.