duckdb-sql

Query CSV, Parquet, and JSON files with SQL for aggregations and joins.

36|2|Updated Feb 9, 2026
One-click install
npx skills add https://github.com/malue-ai/dazee-small --skill duckdb-sql-malue-ai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: duckdb-sql
Source: https://github.com/malue-ai/dazee-small/tree/main/skills/library/duckdb-sql
Command: npx skills add https://github.com/malue-ai/dazee-small --skill duckdb-sql-malue-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires duckdb, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill allows users to query data directly from files like CSV, Parquet, and JSON using SQL, eliminating the need for traditional database setup and data import processes.

Core Features & Use Cases

  • Direct File Querying: Run SQL queries on local files without importing data into a database.
  • Large Dataset Analysis: Efficiently analyze large datasets that might be slow for other tools.
  • Multi-File Joins: Combine data from multiple CSV or Parquet files using SQL JOIN operations.
  • Use Case: Analyze sales data from sales.csv to find the total revenue per category, or join orders.csv with customers.csv to find high-value orders.

Quick Start

Use the duckdb-sql skill to count the number of rows in the file 'data.csv'.

Frequently Asked Questions about duckdb-sql

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

FAQPage Schema
How do I query CSV and Parquet files with SQL without setting up a database?

You can query CSV and Parquet files directly with SQL using an in-memory analytical engine. This approach eliminates traditional database setup and data import processes, allowing you to run complex aggregations immediately.

Can I join data across multiple CSV files using SQL?

Yes, you can join data across multiple CSV files using SQL JOIN operations. This allows you to combine data from multiple files, such as joining orders with customers, without importing them into a relational database.

What is the best way to analyze large datasets stored in JSON files?

Analyzing large JSON datasets is best handled by an in-memory analytical SQL engine that queries files directly. This method efficiently processes large-scale data that might be slow for other tools.

Does DuckDB support wildcard file matching for querying multiple Parquet files?

Yes, DuckDB supports wildcard file matching for querying multiple Parquet files. This allows you to perform large-scale data analysis across many files simultaneously using SQL.

Do I need to install a database to run SQL aggregations on local data files?

No, you do not need to install a database to run SQL aggregations on local data files. You can use an in-memory analytical engine to run complex aggregations directly on CSV, Parquet, and JSON files.