科研插件
临床医学与公共卫生
Clinical Research & Public Health
面向临床与公卫研究:研究设计与方案、样本量、队列与 Meta 分析、报告规范核查、医学影像 AI 评估、流行病建模与卫生经济学评价、医学论文写作投稿。
官方收录发布者 Codar安全审核通过v0.1.158 个 Skill
README
临床医学与公共卫生(Clinical Research & Public Health)
面向临床与公卫研究:研究设计与方案、样本量、队列与 Meta 分析、报告规范核查、医学影像 AI 评估、流行病建模与卫生经济学评价、医学论文写作投稿。
来源与许可
本 Plugin 中的 Skill 精选自以下开源仓库,保留原许可;每个 SKILL.md 的 source 字段指向具体出处。
- Aperivue/medsci-skills — MIT,50 个 Skill
- Codar 自研 — MIT,3 个 Skill
- xjtulyc/awesome-rosetta-skills — MIT,5 个 Skill
示例提示词
请为一项回顾性队列研究设计统计分析计划,并按 STROBE 清单核查我的稿件。
包含的科研 Skills58 个
- 医学AI论文检索优化Optimizes a medical AI paper’s title, abstract and metadata for AI search engines. Use when a paper should be findable and citable by RAG tools and AI search.v0.1.0
- 临床数据统计分析与建模Generates reproducible Python or R code for clinical statistics and tables. Use when collected data needs Table 1, regression, survival or agreement analysis.v0.1.0
- 作者发表记录与策略分析Analyzes a PubMed author record to classify study types and authorship patterns. Use when planning a publication strategy from a researcher’s track record.v0.1.0
- 批量队列暴露结局分析Generates one cohort-analysis script per exposure-outcome pair from one template. Use when a validated method must run across many variable combinations at once.v0.1.0
- 样本量估算与检验效能Walks a decision tree to the right test and computes sample size with IRB text. Use when planning how many patients a study needs before data collection.v0.1.0
- 因果推断方法设计Runs DAG-based, instrumental-variable, difference-in-differences or RD analyses. Use when an association in observational data must support a causal claim.v0.1.0
- 报告规范逐条核查Audits a manuscript item by item against 49 reporting and risk-of-bias checklists. Use when checking a draft against STROBE, CONSORT, TRIPOD or similar guidelines.v0.1.0
- 临床数据清洗与画像Profiles a clinical dataset and generates cleaning code in staged, approved steps. Use when a CSV or Excel dataset needs missing-value and outlier checks before analysis.v0.1.0
- 跨国队列数据协调对比Harmonizes variables and runs parallel weighted analyses across national surveys like KNHANES and NHANES. Use when comparing one exposure-outcome link across countries.v0.1.0
- 变量定义与截断值溯源Maps exposure, outcome and covariate definitions to a cited guideline and DB columns. Use when variable cutoffs need a citable basis before the study protocol.v0.1.0
- 本地化临床数据脱敏Runs a local, network-free script that detects and removes identifiers from clinical data. Use when data may contain PHI and must be de-identified before LLM analysis.v0.1.0
- AI对标专家基准研究设计Plans the arms, rubrics, calibration probes and reviewer panel for an AI-vs-expert benchmark. Use before data collection when designing an AI-vs-human rating study.v0.1.0
- 放射影像AI研究设计审查Reviews a study’s analysis unit, cohort logic, leakage risk and reporting-guideline fit. Use when checking a clinical or medical-AI study design before drafting.v0.1.0
- 传染病仓室模型拟合Builds and fits SIR, SEIR and SEIHR compartmental models with Rt estimation. Use when an outbreak or epidemic’s spread needs mathematical modeling in Python.v0.1.0
- ICMJE利益冲突声明填写Clones a pre-filled synthetic ICMJE COI form, replacing only date, name and title. Use when each author on a submission needs a disclosure form filled quickly.v0.1.0
- 机构Word表单内容填充Fills an institutional Word form, such as an IRB protocol, without breaking its layout. Use when drafted content must be rendered into a CJK-aware .docx template.v0.1.0
- 队列数据库选题挖掘Profiles a longitudinal cohort database and ranks research-topic proposals with gap evidence. Use when looking for a question an available cohort or registry can answer.v0.1.0
- 投稿期刊匹配推荐Matches a manuscript abstract against curated journal profiles and ranks candidates. Use when choosing where to submit, or re-targeting after a rejection.v0.1.0
- DOI全文批量获取Batch-downloads open-access PDFs for a list of DOIs via Unpaywall, PMC and OpenAlex. Use when full texts are needed for a screening set such as a meta-analysis.v0.1.0
- 数据集编码本自动生成Profiles every variable in a tabular dataset into a structured, citable codebook. Use when a CSV, Excel or Stata dataset needs a data dictionary before analysis.v0.1.0
- 全球卫生数据获取分析Accesses and analyzes global health data from WHO GHO, IHME GBD and Our World in Data. Use when DALYs, age-standardized rates or choropleth maps are needed.v0.1.0
- 医学AI项目基金申请书撰写Structures a grant proposal’s significance, innovation, approach, aims and milestones. Use when drafting a research funding proposal, including a Korean grant plan.v0.1.0
- 卫生经济学评价建模Builds Markov cohort models with QALYs, PSA and cost-effectiveness planes. Use when a health intervention needs a formal cost-effectiveness evaluation.v0.1.0
- AI写作痕迹识别改写Scans a manuscript for AI writing patterns and rewrites flagged passages carefully. Use when a draft or response letter reads as obviously AI-written.v0.1.0
- 医学影像数据集画像与预处理Profiles a DICOM or NIfTI dataset’s spacing, intensity and label integrity before modeling. Use when preparing an imaging dataset and auditing it for leakage.v0.1.0
- 放射研究项目接手梳理Classifies a project’s type and state, lists missing inputs and scaffolds memory files. Use when starting or inheriting a messy radiology research project folder.v0.1.0
- 文献同步至Zotero与ObsidianSyncs a .bib reference list into Zotero and Obsidian literature notes with concept notes. Use when references from a search need to land in Zotero and Obsidian.v0.1.0
- 论文图表与可视化摘要制作Produces publication-ready ROC, forest, Kaplan-Meier and flow-diagram figures. Use when a paper needs statistical figures or a visual abstract, with AI-policy checks.v0.1.0
- 稿件项目进度管理Scaffolds a manuscript project’s folders and tracks writing progress across phases. Use when managing a project’s timeline, memory files and submission checklist.v0.1.0
- 参考文献渲染与格式化Renders a reference list via pandoc and a journal CSL and checks cross-references. Use when references must be written, rendered or converted for submission.v0.1.0
- 荟萃分析选题挖掘Starts from a publication profile or clinical question to find feasible meta-analysis topics. Use when scouting a meta-analysis topic before any protocol exists.v0.1.0
- 系统评价与荟萃分析全流程Runs a full systematic review pipeline from PROSPERO protocol through PRISMA reporting. Use when conducting a diagnostic-accuracy or intervention meta-analysis.v0.1.0
- 多模态大模型临床评测设计Audits how an LLM or multimodal LLM task is evaluated, covering reference standard and hallucination. Use when reviewing an evaluation harness for a clinical AI model.v0.1.0
- 医学影像模型验证评估Audits split leakage and computes held-out metrics and calibration for an imaging model. Use when validating or evaluating a trained medical-imaging model.v0.1.0
- 模型卡与数据集说明卡填写Fills a Model Card and dataset Datasheet from user-supplied facts with a completeness gate. Use when a trained imaging model needs documentation for a repo.v0.1.0
- PyTorch影像训练代码脚手架Emits a runnable PyTorch training repo with a patient-level seed-locked split. Use when a reproducible, leakage-safe starting repo is needed for an imaging task.v0.1.0
- 医学影像模型架构选型Picks a paper-grounded architecture family and vets a repo’s license and provenance. Use when choosing which model to use for a medical-imaging study.v0.1.0
- 医学科研任务智能路由Classifies a research request spanning several skills and routes it in order. Use when a research goal is described without naming a specific skill to invoke.v0.1.0
- 期刊同行评审意见撰写Drafts a structured external review in a journal’s format, scanning for prompt injection first. Use when reviewing someone else’s manuscript after an invitation.v0.1.0
- 医学论文英文润色Flags abbreviation, spelling and unit-spacing issues, then polishes style only. Use when a manuscript needs a mechanical copy-edit for English consistency.v0.1.0
- 学术报告讲稿与幻灯片制作Analyzes a paper and drafts speaker scripts, slide notes and a PPTX with Q&A prep. Use when preparing a talk such as a journal club or conference presentation.v0.1.0
- 质性访谈编码分析Codes interview or open-text data into themes using thematic or framework analysis. Use when analyzing qualitative clinical or public-health transcripts.v0.1.0
- 影像组学机器学习建模Enforces nested cross-validation and calibration for a radiomics or tabular ML model. Use when building or auditing a classical-learner clinical-ML prediction model.v0.1.0
- Markdown文档渲染为PDFRenders a Markdown document to PDF via pandoc and xelatex with CJK fonts. Use when a proposal or cover letter needs PDF layout without a bibliography.v0.1.0
- 跨数据库复现队列研究方法Extracts a published cohort study’s design and maps variables onto a new database. Use when applying an existing study’s methodology to a different database.v0.1.0
- 文献综述写作框架搭建Scaffolds a seven-part review-article skeleton with a scope statement and table stubs. Use when writing a narrative, scoping or systematic literature review.v0.1.0
- 审稿意见逐条回复修改Numbers and classifies every reviewer comment, then drafts a point-by-point response. Use when a manuscript comes back with reviewer or editor comments.v0.1.0
- PubMed多源文献检索Searches PubMed, Semantic Scholar and preprint servers, including only API-verified results. Use when finding papers or building a reference list.v0.1.0
- 投稿前自我审稿预评估Checks a manuscript before submission from a reviewer’s perspective, with leakage checks. Use when self-auditing one’s own manuscript ahead of submission.v0.1.0
- 科研环境依赖诊断Diagnoses Python, R, Node, Git, Zotero and configured MCP servers with a pass/fail table. Use when a skill fails for a missing tool or the environment needs checking.v0.1.0
- 空间流行病学聚集分析Computes Moran’s I, LISA clusters, mortality ratios and the Knox space-time test. Use when testing whether disease rates are spatially or spatio-temporally clustered.v0.1.0
- 量表信效度验证Runs reliability, factor-structure and invariance checks on a questionnaire or PRO. Use when a scale needs psychometric validation before or after it is used.v0.1.0
- 流行病学生存分析Runs Kaplan-Meier, Cox PH, AFT models and competing-risks analysis for time-to-event data. Use when a cohort or trial’s time-to-event outcome needs survival analysis.v0.1.0
- 期刊投稿包构建同步Detects drift between a canonical manuscript and its journal submission package. Use when building, auditing or freezing a journal submission package.v0.1.0
- 参考文献真实性核验Audits every citation against PubMed and CrossRef to flag fabricated or mismatched entries. Use when checking that a manuscript’s references are real before submission.v0.1.0
- 数据集版本哈希校验Builds a content-hash manifest of a dataset and verifies later copies for drift. Use when an analysis must prove it ran on the intended, unchanged data version.v0.1.0
- 医学论文IMRAD全流程撰写Runs an eight-phase pipeline from outline to submission-ready draft for IMRAD. Use when drafting a medical research manuscript or any individual IMRAD section.v0.1.0
- IRB伦理研究方案撰写Writes an IRB protocol’s background, design and statistical plan in full prose. Use when drafting a research protocol with institution-specific TODO sections.v0.1.0
常见问题
临床医学与公共卫生能做什么?
面向临床与公卫研究:研究设计与方案、样本量、队列与 Meta 分析、报告规范核查、医学影像 AI 评估、流行病建模与卫生经济学评价、医学论文写作投稿。
如何安装临床医学与公共卫生?
在科搭 Codar 左侧点击「插件」,在「插件」页签搜索「临床医学与公共卫生」并安装;也可以把本页的安装提示词发给 Claude Code 或 Codex。
临床医学与公共卫生需要哪些权限?
该科研插件没有声明额外权限;执行具体操作时仍由 Agent 按自身规则请求确认。
临床医学与公共卫生经过官方审核吗?
是。SpeedSkills 收录的每个版本都会记录内容摘要与权限声明,当前版本已通过安全审核。