clean-data

Profile clinical CSV/Excel datasets and generate reproducible cleaning scripts.

243|60|Updated Apr 6, 2026
One-click install
npx skills add https://github.com/Aperivue/medsci-skills --skill clean-data
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: clean-data
Source: https://github.com/Aperivue/medsci-skills/tree/main/skills/clean-data
Command: npx skills add https://github.com/Aperivue/medsci-skills --skill clean-data

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Profile clinical datasets to identify quality gaps and generate clean-data workflows.

Core Features & Use Cases

  • Three-stage interactive workflow (profile, flag, code-generation) with researcher approval at each step
  • Generate profiling reports, flag tables, and reproducible cleaning scripts without applying changes automatically
  • De-identification guidance and templates to support privacy-preserving data processing

Quick Start

Upload your dataset and run the profiling tool to produce a data profile, review flagged issues, and generate cleaning scripts for approved actions.

Frequently Asked Questions about clean-data

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I profile clinical datasets to identify data quality gaps?▼

You can profile clinical datasets by uploading CSV or Excel research files to generate a detailed data profile. The automated workflow identifies missing values, outliers, duplicates, and type mismatches, outputting a profiling report and flag table for your review.

What is the best way to clean clinical research data without losing reproducibility?▼

To clean clinical research data while maintaining reproducibility, use an automated code-generation workflow that produces cleaning scripts instead of applying changes directly. This approach ensures a complete audit log and reproducible code through researcher approval gates at each stage.

Does this data cleaning workflow support de-identification for clinical registries?▼

Yes, this data cleaning workflow includes de-identification guidance and templates for clinical registries. It supports privacy-preserving data processing during the profiling and cleaning stages of your research datasets.

Can I review and approve flagged data quality issues before generating cleaning scripts?▼

Yes, you can review and approve flagged data quality issues before generating scripts. The workflow uses a three-stage process—profile, flag, and code-generation—with explicit researcher approval gates at each step to ensure full control over all cleaning actions.

What types of data issues are handled when profiling clinical registries?▼

When profiling clinical registries, the workflow handles missing values, outliers, duplicates, and type mismatches. It identifies these specific data quality gaps and compiles them into a flag table for your review before generating any reproducible cleaning scripts.