This gives Claude the ability to run SQL queries directly on your data files without spinning up a database server. Point it at CSVs, Parquet files, or JSON and write analytical queries with joins, window functions, and aggregations. It can also query pandas and Polars DataFrames in place, which is genuinely useful when you're neck-deep in a Jupyter notebook and don't want to wrestle with method chaining. The performance is solid for medium to large datasets since it's built for OLAP workloads. Think of it as SQLite's analytical cousin. Best when you need complex SQL on local files or want to join data across different formats without loading everything into memory first.

skills.sh installs
317
GitHub stars
3
last updated
Aug 21, 2026

Install

$ npx -y skills add silvainfm/claude-skills --skill duckdb --agent claude-code

Installs into .claude/skills of the current project.

Files

DuckDB

Overview

DuckDB is a high-performance, in-process analytical database management system (often called "SQLite for analytics"). Execute complex SQL queries directly on CSV, Parquet, JSON files, and Python DataFrames (pandas, Polars) without importing data or running a separate database server.

When to Use This Skill

Activate when the user:

  • Wants to run SQL queries on data files (CSV, Parquet, JSON)
  • Needs to perform complex analytical queries (aggregations, joins, window functions)
  • Asks to query pandas or Polars DataFrames using SQL
  • Wants to explore or analyze data without loading it into memory
  • Needs fast analytical performance on medium to large datasets
  • Mentions DuckDB explicitly or wants OLAP-style analytics

Installation

Check if DuckDB is installed:

python3 -c "import duckdb; print(duckdb.__version__)"

If not installed:

pip3 install duckdb

For Polars integration:

pip3 install duckdb 'polars[pyarrow]'

Core Capabilities

1. Querying Data Files Directly

DuckDB can query files without loading them into memory:

import duckdb

Sponsors

Details

Repository
github.com/silvainfm/claude-skills
Categories
Backend & APIs, Data Science & ML, Python, Marketing & SEO, Databases
First seen
Jun 3, 2026

More from silvainfm/claude-skills

All 2
1incept5 avatareve-new-project-setupincept5/eve-skillpacksConfigure a new Eve Horizon project after running eve init (profile, auth, manifest, and repo linkage).316skills.sh installs
2jezweb avatarvercel-kvjezweb/claude-skillsIntegrate Redis-compatible Vercel KV for caching, session management, and rate limiting in Next.js. Powered by Upstash with strong consistency and TTL support. 314skills.sh installs
3jezweb avatarmcp-cli-scriptsjezweb/claude-skillsBuild CLI scripts alongside MCP servers for terminal environments. File I/O, batch processing, caching, richer output formats. Templates for TypeScript scripts 313skills.sh installs
4incept5 avatareve-read-eve-docsincept5/eve-skillpacksLoad first. State-today index of distilled Eve Horizon system docs with task-based routing for CLI/API usage, manifests, pipelines, jobs, secrets, agents, build305skills.sh installs
5jezweb avatartinacmsjezweb/claude-skillsBuild content-heavy sites with Git-backed TinaCMS. Provides visual editing for blogs, documentation, and marketing sites. Supports Next.js, Vite+React, and Astr304skills.sh installs
6mhattingpete avatarcode-refactormhattingpete/claude-skills-marketplacePerform bulk code refactoring operations like renaming variables/functions across files, replacing patterns, and updating API calls. Use when users request rena301skills.sh installs