lake

Query Parquet/CSV data with a DuckDB-backed lakehouse engine.

27|9|Updated Jan 25, 2026
One-click install
npx skills add https://github.com/Leoyishou/personal-ai-company --skill lake
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: lake
Source: https://github.com/Leoyishou/personal-ai-company/tree/main/claude-global/skills/lakehouse
Command: npx skills add https://github.com/Leoyishou/personal-ai-company --skill lake

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

本地 Lakehouse 分析引擎,基于 DuckDB 提供快速的 OLAP 查询能力,支持 Parquet/CSV 文件分析,并可从 Supabase CDC 同步数据,帮助团队在本地环境实现高效的数据洞察。

Core Features & Use Cases

  • SQL-based analytics: 在本地执行高性能 DuckDB 查询,支持复杂聚合和多表 joins。
  • CDC 数据整合: 从 Supabase 实时或准实时同步数据,保持分析数据的新鲜度。
  • 多数据源协作: 处理 Parquet/CSV 文件,提供灵活的数据导入与分析工作流。
  • 集成工具链: 通过 Claude Code 的 /lake 命令实现数据分析、同步和导入的端到端操作。

Quick Start

直接对 lakehouse 运行查询以列出所有表并查看其模式。

Frequently Asked Questions about lake

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

FAQPage Schema
How do I run SQL queries on local Parquet files without setting up a database?

You can run SQL queries on local Parquet files using a DuckDB-backed lakehouse engine to execute high-performance OLAP queries with complex aggregations and multi-table joins directly on file data.

What is the best way to sync Supabase data to a local lakehouse for analysis?

Using Supabase CDC integration syncs data in real or near-real time to your local lakehouse, ensuring your analysis data remains fresh for downstream DuckDB SQL queries.

Can I use DuckDB to query both CSV and Parquet data sources in the same workflow?

Yes, DuckDB supports processing both CSV and Parquet files, providing a flexible data import workflow that allows cross-source querying within a single local lakehouse analytics session.

How do I discover tables and inspect schemas in a local DuckDB lakehouse?

You can discover tables and inspect schemas by running direct lakehouse queries through integrated Claude Code commands, which list all available tables and return their structural schema definitions.

Do I need a separate database server to perform local lakehouse analytics with DuckDB?

No, a separate server is not required; DuckDB provides a local analytical engine that runs entirely on your machine, enabling fast OLAP querying over Parquet and CSV files without external infrastructure.