科研 Skill
IRB伦理研究方案撰写
write-protocol
Writes an IRB protocol’s background, design and statistical plan in full prose. Use when drafting a research protocol with institution-specific TODO sections.
SKILL.md
Write-Protocol Skill
Draft the scientific core of an IRB/ethics protocol and leave institution-specific sections as
[TODO] skeletons. Read both reference files before generating a protocol draft:
references/protocol_template.md-- the 10-section structure, per-section guidance, and the[TODO]blocks for Sections 5-9references/ethics_checklist.md-- jurisdiction-specific ethical requirements
Inputs
Collect the required inputs before generating; ask for any that are missing.
- Required: research question / hypothesis (specific, testable); study type (retrospective cohort, prospective cohort, cross-sectional, RCT, diagnostic accuracy, case-control, case series); target population (who, where, when); primary outcome; secondary outcomes (if any).
- Optional: key references (DOIs or search terms); institution name (header and ethics guidance); regulatory context -- Korea (PIPA), US (HIPAA/Common Rule), EU (GDPR), other.
Use prior skill outputs directly when they exist; when they do not, ask the user or call the skill:
- design-study: design recommendations, analysis unit, comparator design, validation strategy.
- calc-sample-size:
protocol/sample_size_justification.md(canonical IRB-ready prose) andprotocol/sample_size_calc.{R,py}(reproducible code). - search-lit: Background references with verified citations.
- define-variables:
variable_operationalization.md-- literature-grounded definitions, cutoffs, DB-variable mappings for the Methods section. Precondition: if the study is observational and no operationalization artifact exists, call/define-variablesbefore drafting Methods. Do not invent phenotype/cutoff definitions from the data dictionary inside this skill.
Protocol Structure -- 10 Sections
Core Sections (Fully Generated)
Section 1: Background and Rationale (400-600 words)
Full paragraphs, no bullet points, flowing from clinical context (disease burden, current
practice) through the knowledge gap and rationale (what this study adds) to the research question
or hypothesis. Call /search-lit if key references are not provided. Cite a reference only with a
/search-lit-confirmed DOI or PMID; otherwise mark it [UNVERIFIED - NEEDS MANUAL CHECK].
Section 2: Study Design and Eligibility Criteria (300-500 words)
Prose covering the study design with its justification (why this design answers this question),
the setting (single-center vs multi-center, institution description) and the study period,
followed by numbered inclusion and numbered exclusion criteria. If design-study output is
available, incorporate its analysis unit (patient vs lesion vs exam), comparator design,
validation strategy, and leakage risks with mitigations. Mark any clinical definition, diagnostic
criterion or guideline recommendation you cannot confirm [VERIFY] and ask the user.
Section 3: Sample Size Justification (150-300 words)
- If
protocol/sample_size_justification.mdexists (calc-sample-size output): embed it VERBATIM. Do not rephrase numbers. - If not available: prompt the user to run
/calc-sample-sizefirst; only fall back to a basic justification if the user explicitly declines. - Must include: test type, expected effect size (with literature source), alpha level, power, attrition adjustment.
- Final statement: "We plan to enroll N participants."
Section 4: Statistical Analysis Plan (300-500 words)
Full prose covering: descriptive statistics (continuous as mean (SD) or median (IQR); categorical as count (%)); the primary analysis (test, assumptions, handling of violations); pre-specified secondary analyses; pre-specified subgroup analyses with interaction tests; missing-data handling (complete case, multiple imputation, sensitivity analysis); software name and version (e.g., R 4.4.0, Python 3.12, SAS 9.4); two-sided alpha = 0.05 unless otherwise justified.
Skeleton Sections (TODO Markers)
Sections 5-9 are the [TODO] blocks from protocol_template.md, copied as they are; never fill
them with invented institutional content.
- Section 5: Study Title and Registration
- Section 6: Data Collection and Management
- Section 7: Ethical Considerations -- also add the template's jurisdiction guidance for the
regulatory context, and use
ethics_checklist.mdfor the full checklist. - Section 8: Timeline and Milestones
- Section 9: Budget
Section 10: References
A numbered list of the Section 1 citations, the Section 3 effect-size sources, and any references
in the calc-sample-size output. Every entry has a verified DOI or PMID or is marked
[UNVERIFIED - NEEDS MANUAL CHECK].
Output Format
Generate a single markdown file: protocol_draft.md
- All 10 sections with clear numbering (1. through 10.)
- Core sections (1-4) in full prose; the Section 2 eligibility criteria are the only lists
- Skeleton sections (5-9) with
[TODO]markers clearly visible - Word count targets noted in comments at the start of each core section
- Institution name in the header if provided
After generating, tell the user which sections are ready for review, which [TODO] items need
their input, and the next steps (e.g., "Fill in Section 5 title and registration, then adapt
Section 7 to your IRB form").
Quality Checks
Before delivering the protocol:
- Citation integrity: every reference has a DOI or PMID, or is marked
[UNVERIFIED - NEEDS MANUAL CHECK] - Internal consistency: sample size in Section 3 matches the analysis plan in Section 4
- Design alignment: study type in Section 2 matches the statistical approach in Section 4
- TODO completeness: all institution-specific items have
[TODO]markers - Word counts: core sections fall within target ranges
- No AI patterns: avoid phrases like "it is worth noting", "comprehensive", "plays a crucial role"
示例提示词
帮我起草一份新研究的IRB伦理审查方案初稿。
所属插件
安装该插件会一并获得同领域的 58 个 Skill / MCP。
同插件的其他科研 Skill
- 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.
- 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.
- 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.
- 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.
- 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.
- 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.
- 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.
- 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.
- 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.
- 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.
- 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.
- 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.
- 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.
- 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.
- 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.
- 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.
- 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.
- 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.
- 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.
- 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.
- 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.
- 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.
- 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.
- 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.
常见问题
IRB伦理研究方案撰写能做什么?
Writes an IRB protocol’s background, design and statistical plan in full prose. Use when drafting a research protocol with institution-specific TODO sections。
如何安装IRB伦理研究方案撰写?
在科搭 Codar 左侧点击「插件」,在「组件」页签搜索「IRB伦理研究方案撰写」并安装;在 Claude Code 或 Codex 中可以发送本页的安装提示词,或下载 Skill 包后解压到 ~/.claude/skills 或 ~/.codex/skills。
IRB伦理研究方案撰写需要哪些权限?
该科研 Skill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。
IRB伦理研究方案撰写经过官方审核吗?
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。