メニュー
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.
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.
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.
Modify completed analysis outputs. Clarifies modification scope (figure style, statistical method, variables), executes changes, verifies outputs, and records history in PLAN.md. Can be invoked from any phase. Triggers: modify figures, change analysis method, adjust chart style, replace variables.
| name | clinpub-data-prep |
| description | 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. |
Phase 1: Data preparation. Transform raw data into analysis-ready cleaned.csv with full data quality documentation.
Handles: missing value imputation, outlier detection, derived variable creation, encoding, train/validation split. Supports re-entry: if project_config.yml exists with valid fields, auto-refreshes profiles and specs before entering discussion.
pipeline/workflows/data-prep.mdExecute the data-prep workflow end-to-end.
Before executing the workflow, check if the project is already initialized:
project_config.yml exists in project rootproject.name non-empty (not default "项目名称")variables.outcome non-emptypaths.raw_data corresponds to existing directory with data filesreinit_data_prep (full refresh)