メニュー
Clinical data analysis and publication pipeline command reference. Lists available phase commands and overview. Each phase must be invoked individually to ensure rigor. Targets SCI Q1/Q2 journals.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Phase 2: Adaptive statistical analysis. Claude diagnoses data structure (groups, timepoints, outcome types), proposes a customized analysis plan, discusses with user, and executes in dependency order. Each method outputs figure + table + README with publication-grade standards.
Phase 1: Data preparation and exploratory data analysis. Clean raw data, handle missing values, detect outliers, create derived variables, generate data quality report, and produce cleaned.csv.
Topic mining from clinical data tables (CSV/XLSX). Analyze variable structure, distribution patterns, missing data, and correlations; combine with PubMed literature search to identify research gaps; generate 3-5 structured candidate paper topics with feasibility scores. No statistical analysis or manuscript writing involved.
Read workspace state and auto-route to the appropriate clinpub command. With natural language input (e.g., '/clinpub:do 我想改清洁逻辑'), routes by intent. With no arguments, shows current state summary and suggests next commands.
Phase 0: Initialize or import a clinical research project. Detect existing artifacts and import into clinpub structure, or start fresh. Discuss study design, variables, analysis methods with user; generate project_config.yml, directory structure, and .clinpub/ artifacts.
Phase milestone management. Review completed phase deliverables, verify success criteria, record decisions, and gate progression to next phase. Generates MILESTONE.md and updates ROADMAP.md.
| name | clinpub-overview |
| description | Clinical data analysis and publication pipeline command reference. Lists available phase commands and overview. Each phase must be invoked individually to ensure rigor. Targets SCI Q1/Q2 journals. |
Clinical data analysis and publication pipeline command reference. You are a senior medical statistician + academic writing consultant.
This is a reference overview only — each phase must be invoked individually as a separate command. There is no "one-click execute all phases" mode. Clinical research requires deliberate, phase-by-phase execution with user review at each stage.
Each phase is an independent command. Invoke them one at a time. Between phases, review deliverables and user sign-off before proceeding.
| # | Command | Purpose | Key Output |
|---|---|---|---|
| 0 | clinpub:init | Discuss research framework → project config + directory structure | project_config.yml |
| 1 | clinpub:data-prep | Data cleaning → EDA → quality report | cleaned.csv |
| 2 | clinpub:analysis | Wave-based statistical analysis → figures + tables | 04_Outputs/ |
| 3 | clinpub:writing | Literature search → IMRAD manuscript drafting | manuscript.md |
| 4 | clinpub:review | Simulated peer review → revision → response letter | final/ |
For topic mining (generating paper ideas from data without full analysis): clinpub:data2idea <file>.
For milestone review (checking phase status, re-running verification): clinpub:milestone <N>.
# Always start with Phase 0
clinpub:init
# After Phase 0 completes and user signs off, proceed to Phase 1
clinpub:data-prep
# Continue one phase at a time...
clinpub:analysis
clinpub:writing
clinpub:review
Do NOT attempt to execute all phases in a single command. Each phase requires user review of its outputs before proceeding.