read-file

Read CSV, JSON, and Parquet files from local paths or S3 and GCS.

527|26|Updated Mar 10, 2026
One-click install
npx skills add https://github.com/duckdb/duckdb-skills --skill read-file-duckdb
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: read-file
Source: https://github.com/duckdb/duckdb-skills/tree/main/skills/read-file
Command: npx skills add https://github.com/duckdb/duckdb-skills --skill read-file-duckdb

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill resolves the challenge of quickly and easily reading various types of data files (CSV, JSON, Parquet, etc.) into a usable format for analysis and further processing.

Core Features & Use Cases

  • Universal File Format Support: Handles CSV, JSON, Parquet, Avro, Excel, spatial files, and more.
  • Remote Data Access: Can access and analyze data from remote storage like S3, GCS, Azure, or HTTPS URLs.
  • Automated Data Discovery: Automatically detects the file format based on the file extension and suggests next steps like data analysis.
  • Use Case: A user could query a dataset stored on S3 or local system, and get immediate information about its schema and data, making it easier to proceed with more advanced analytics or visualization.

Quick Start

Use the read-file skill to explore a Parquet file named 'sales_data.parquet'.

Frequently Asked Questions about read-file

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

FAQPage Schema
How do I read and analyze local data files like CSV, JSON, and Parquet?

You can read and analyze local data files like CSV, JSON, and Parquet using automated format detection. It automatically identifies the file type based on the extension and previews the schema for immediate analysis.

Can I read data files directly from remote cloud storage like S3 or GCS?

Yes, you can read data files directly from remote cloud storage like S3, GCS, or Azure. It accesses remote URLs to query datasets and retrieve schema information without requiring local downloads.

What is the best way to preview a dataset schema before running ETL operations?

The best way to preview a dataset schema before ETL operations is using automated data discovery. It detects file formats automatically and provides immediate schema and data analysis capabilities to facilitate downstream processing.

Does DuckDB support analyzing spatial files and Excel documents?

Yes, DuckDB supports analyzing spatial files and Excel documents alongside Avro and Parquet. It utilizes native file I/O mechanisms to provide comprehensive data exploration and schema analysis for these varied formats.

How do I handle data exploration for files with unknown formats?

For data exploration of files with unknown formats, the system uses automated data discovery based on file extensions. It detects the format, reads the data using native I/O, and suggests next steps for analysis without manual configuration.