skills.rest
mutsumi-yamamoto
mutsumi-yamamotoCOMMUNITY
Explore all skills by this author →
GitHub

data-clean

Cleanse, normalize, and deduplicate datasets for ETL pipelines.

Updated Mar 3, 2026
Search Tags:#ETL#deduplication#data-quality#data-cleaning#data-preparation#text-normalization#data-standardization
One-click install
npx skills add https://github.com/mutsumi-yamamoto/claude-data-analysis-marketplace --skill data-clean
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: data-clean
Source: https://github.com/mutsumi-yamamoto/claude-data-analysis-marketplace/tree/main/plugins/data-analysis/skills/data-clean
Command: npx skills add https://github.com/mutsumi-yamamoto/claude-data-analysis-marketplace --skill data-clean

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Data quality is foundational for reliable analytics. This Skill evaluates and cleanses data to improve accuracy, completeness, and consistency, enabling trustworthy insights and smooth downstream processing.

Core Features & Use Cases

  • Data quality assessment across key dimensions (accuracy, completeness, consistency,Uniqueness, validity, timeliness) and automatic cleansing guidance.
  • Cleansing operations including deduplication, normalization, standardization, and entity resolution to create clean, structured datasets ready for modeling and reporting.
  • Use Case: Prepare a customer dataset with duplicates, inconsistent spellings, and divergent date formats so it can feed a data warehouse and analytics dashboards.

Quick Start

Apply data-clean to your dataset to evaluate quality, perform deduplication, and normalize text and dates.

Frequently Asked Questions about data-clean

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

FAQPage Schema
How do I clean and deduplicate data for an ETL pipeline?▼

To clean data for an ETL pipeline, apply a repeatable workflow that assesses accuracy, completeness, and consistency, then executes deduplication, text normalization, and standardization to output structured datasets ready for analytics.

What is data normalization and entity resolution in master data management?▼

Data normalization standardizes divergent text and date formats, while entity resolution identifies and merges duplicate records. Together they ensure consistency and uniqueness across master data management systems for reliable analytics.

How do I prepare a customer dataset with inconsistent spellings and date formats?▼

Preparing an inconsistent dataset requires applying text normalization to resolve spelling variations and standardizing divergent date formats, resulting in clean, structured data ready to feed data warehouses and analytics dashboards.

Can I use this data cleaning approach for analytics data preparation without dependencies?▼

Yes, this data cleaning approach requires no external dependencies and can be applied directly to datasets to perform quality checks, optional imputation, and deduplication as part of a repeatable analytics data preparation workflow.

When should I use an automated data quality assessment workflow?▼

You should use an automated data quality assessment workflow when preparing datasets for modeling and reporting, ensuring foundational accuracy, completeness, consistency, and lineage to enable trustworthy insights and smooth downstream processing.

Related Skills

Explore More Data & Analytics Skills→
zjykzkzjykzk

data-ingest

Ingest raw text data into an Obsidian wiki as searchable knowledge.

Community
Intermediate
KaranKathur06KaranKathur06

data-pipeline

Build scheduled ETL workflows that extract, transform, and load data into analytics destinations.

Community
Intermediate
amanhsnamanhsn

senior-data-engineer

Design and build scalable data pipelines with Python, SQL, Spark, Airflow, dbt, and Kafka.

Community
Advanced
zilliztechzilliztech
3

duplicate-detection

Detect exact and near-duplicate records using hash checks and semantic similarity.

Official
Advanced