data-tools

Inspect, profile, and query local or S3 data files with DuckDB.

Updated Apr 16, 2026

Search Tags:#profiling #s3 #duckdb #inspect #data-query #datascience

Ready to run

npx skills add https://github.com/ejoliet/claude-skills --skill data-tools

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: data-tools
Source: https://github.com/ejoliet/claude-skills/tree/main/data-tools
Command: npx skills add https://github.com/ejoliet/claude-skills --skill data-tools

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill makes it fast and easy to understand data files before building pipelines by enabling quick schema discovery, sampling, and lightweight querying.

Core Features & Use Cases

Schema sniffing and quick profiling using DuckDB for Parquet, CSV, JSON, and FITS.
Ad-hoc SQL exploration across local or S3 data with simple CLI patterns.
Lightweight data CLI patterns to validate datasets before committing to a full pipeline.

Quick Start

Ask me to inspect a file path or S3 URI and I will reveal the schema, sample rows, and a quick data profile.

Frequently Asked Questions about data-tools

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

FAQPage Schema

How do I inspect and profile data files directly from S3?▼

You can inspect and profile S3 data files by providing an S3 URI, which triggers in-process DuckDB to perform schema sniffing, row sampling, and quick profiling on Parquet, CSV, or JSON formats.

Can I run ad-hoc SQL queries on local Parquet and CSV files?▼

Yes, you can run ad-hoc SQL queries on local Parquet and CSV files using DuckDB core patterns, enabling lightweight data exploration and validation before committing to a full pipeline.

Does DuckDB support schema sniffing and querying for FITS files?▼

DuckDB supports schema sniffing for FITS files with optional support from astropy Table, allowing you to sample rows and profile astronomical data formats alongside standard CSV and JSON files.

What is the best way to validate datasets before building pipelines?▼

The best way to validate datasets before building pipelines is using lightweight CLI patterns to perform schema discovery and ad-hoc SQL queries, ensuring data structure and content meet requirements early.

Can I use pandas and awswrangler for AWS and format-specific data workflows?▼

Yes, pandas and awswrangler provide optional support for AWS and format-specific workflows, complementing DuckDB core patterns to handle complex data inspection and querying tasks across S3.

Are there limitations when using in-process DuckDB for large-scale data profiling?▼

In-process DuckDB is designed for quick schema discovery and lightweight querying rather than heavy pipeline execution, so users should anticipate performance constraints when profiling extremely large-scale datasets.