How does the skill handle different date formats?

Phase 3 specifically addresses date standardization, detecting various formats (like MM/DD/YYYY or DD/MM/YYYY) and providing rules to convert them into the ISO 8601 standard (YYYY-MM-DD).

What happens if my CSV has encoding issues?

The skill includes a discovery phase that uses system tools to detect character sets (like UTF-8 vs ISO-8859-1), identifying necessary conversions before the import begins.

Does this skill support databases other than SQLite?

Yes. While the skill is optimized for DataPeeker's SQLite environment, the 5-phase process and standardization rules are designed to work with any SQL-compliant database including PostgreSQL and MySQL.

Can I use this for very large CSV files?

Absolutely. For files larger than 100K rows, the skill implements a sample-based profiling strategy to ensure efficient schema design without loading the entire file into memory.

Systematic Data Import

Name: Systematic Data Import
Author: tilmon-engineering

bytilmon-engineering

•

Database Management

Standardizes the CSV import process through automated discovery, schema design, and data normalization for relational databases.

The Systematic Data Import skill provides a rigorous 5-phase framework for transforming raw CSV files into structured database tables. It guides users through deep file profiling, intelligent SQL type inference, and mandatory data standardization rules for dates and numbers. By replacing fragile ad-hoc scripts with a documented, step-by-step workflow, this skill ensures data integrity from the moment of ingestion, making it an essential prerequisite for any DataPeeker analysis or data science project requiring a reliable SQLite or SQL backend.

Key Features

012 GitHub stars

02Standardization of dates to ISO 8601 and normalization of numeric fields

03Detailed 5-phase documentation and quality reporting within the workspace

04Intelligent schema inference with custom NULL mapping and type rationale

05Dual-path import execution via SQLite CLI or Python for complex transformations

06Automated encoding and delimiter detection to prevent import errors

Use Cases

01Converting legacy spreadsheet data into clean, indexed relational database tables

02Building a standardized 'raw' data layer for reproducible data science workflows

03Preparing inconsistent external CSV datasets for professional SQL analysis

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add tilmon-engineering/claude-skills importing-data

For use in Claude.ai and ChatGPT

Download Skill