duckdb-en

Run SQL queries on CSV, Parquet, and JSON files using the DuckDB CLI.

1|Updated Feb 1, 2026
One-click install
npx skills add https://github.com/xukrutdonut/openclaw-skills --skill duckdb-en
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: duckdb-en
Source: https://github.com/xukrutdonut/openclaw-skills/tree/main/duckdb-cli-ai-skills
Command: npx skills add https://github.com/xukrutdonut/openclaw-skills --skill duckdb-en

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill enables rapid data analysis and file format conversion using the DuckDB CLI, helping you perform in-context SQL queries and transform data without leaving the command line.

Core Features & Use Cases

  • SQL analytics on CSV, Parquet and JSON: Run ad-hoc queries, transform data, and generate reports directly from CLI.
  • Data conversion & export: Convert between formats (CSV, Parquet, JSON) and produce ready-to-use outputs.
  • Reproducible workflows: Use CLI flags and dot commands to build repeatable analysis pipelines.

Quick Start

  • To run a quick query on a CSV file: duckdb -c "SELECT * FROM 'data.csv' LIMIT 10"
  • To read a Parquet file and export to CSV: duckdb -c "COPY (SELECT * FROM read_parquet('data.parquet')) TO 'out.csv' (FORMAT CSV)"
  • To inspect outputs and adjust formatting, use commands like .mode, .headers, and .separator as needed.

Frequently Asked Questions about duckdb-en

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

FAQPage Schema
How do I query a CSV file using SQL from the command line?

You can query a CSV file using SQL from the command line by running DuckDB with the -c flag, such as duckdb -c "SELECT * FROM 'data.csv' LIMIT 10", to perform rapid data analysis without loading a separate database engine.

What is the best way to convert Parquet to CSV?

The best way to convert Parquet to CSV is using the DuckDB CLI COPY command, for example: duckdb -c "COPY (SELECT * FROM read_parquet('data.parquet')) TO 'out.csv' (FORMAT CSV)" to directly export transformed query results.

Can I run ad-hoc SQL queries directly on JSON files?

Yes, you can run ad-hoc SQL queries directly on JSON files using the DuckDB CLI, enabling fast data analysis and transformation workflows without needing to import the JSON data into a traditional database first.

How do I customize CLI output formatting for SQL query results?

You customize CLI output formatting for SQL query results using DuckDB dot commands like .mode, .headers, and .separator, which allow you to adjust how data is displayed and exported across CSV, Parquet, and JSON formats.

Do I need a separate database server to analyze local data files?

No, you do not need a separate database server to analyze local data files; the DuckDB CLI operates entirely in-process, allowing you to build reproducible analysis pipelines directly on CSV, Parquet, and JSON files.

How do I build reproducible data analysis pipelines using CLI flags?

You build reproducible data analysis pipelines using DuckDB CLI flags and dot commands to script repeatable SQL queries, data transformations, and format conversions across CSV, Parquet, and JSON files directly from the command line.