duckdb

Query local DuckDB warehouses with SQL and ingest CSV, Parquet, and JSON files.

24|11|Updated Feb 19, 2026
One-click install
npx skills add https://github.com/clawdata/clawdata --skill duckdb-clawdata
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: duckdb
Source: https://github.com/clawdata/clawdata/tree/main/skills/duckdb
Command: npx skills add https://github.com/clawdata/clawdata --skill duckdb-clawdata

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Query and explore a local DuckDB database without spinning up servers, enabling fast data exploration and ad-hoc analytics.

Core Features & Use Cases

  • List and inspect tables and schemas to understand your data.
  • Run SQL queries directly against the local warehouse and ingest common data formats (CSV, Parquet, JSON) for quick analysis.
  • Use as a lightweight companion for data discovery and validation during project work.

Quick Start

Run a simple query against userdata/warehouse.duckdb to verify the setup.

Frequently Asked Questions about duckdb

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

FAQPage Schema
How do I run SQL queries on CSV and Parquet files without a database server?

You can run SQL queries directly on CSV, Parquet, and JSON files using a local DuckDB warehouse. This allows fast, serverless ad-hoc data analysis by ingesting files directly into your local environment.

What is the best way to inspect tables and schemas in a local DuckDB warehouse?

The best way to inspect tables and schemas is by querying the local DuckDB warehouse directly. This enables you to list and explore database structures to understand your data for validation and discovery.

Can I use DuckDB for ad-hoc data exploration if I only have the DuckDB binary installed?

Yes, you can perform ad-hoc data exploration with just the DuckDB binary. The setup requires no server and uses a default database file at userdata/warehouse.duckdb to store and query your data locally.

How do I ingest JSON files into a local database for quick data analysis?

To ingest JSON files for quick data analysis, you can run SQL queries against a local DuckDB warehouse. This serverless process loads JSON data directly into the local database file for immediate inspection.

Does a local DuckDB warehouse require any external dependencies or server processes?

A local DuckDB warehouse requires no external dependencies or server processes. It operates entirely serverless, needing only the DuckDB binary to query and explore data stored in the local database file.