Skip to main content
skill CX Codex

using-duckdb — Claude Code skill: what it does, how to install

Query Delta tables and raw files in Fabric OneLake using DuckDB either on your machine or inside a Fabric notebook.

GPL-3.0 ★ 1,104 updated 2026-10-28

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add data-goblin/power-bi-agentic-development
/plugin install etl@power-bi-agentic-development
Open on GitHub

What using-duckdb does

The skill sets up direct SQL queries against Microsoft Fabric OneLake storage without launching heavy Spark clusters. It reads Delta Lake tables alongside raw Parquet, CSV, and JSON files stored across lakehouses and warehouses.

Execution splits into two environments. In a local terminal, DuckDB queries OneLake using Azure CLI authentication paired with the delta and azure extensions. Inside a Fabric notebook, it uses storage tokens through notebookutils, speeding up ad-hoc analytical queries on a single node. Cross-item joins work directly in a single SQL statement via full ABFSS paths.

This integration strictly handles read-only workloads. Writing data back into storage requires Spark, and local execution fails unless you authenticate via az login first.

What it helps with

  • query Fabric Delta tables directly from a local terminal
  • run fast analytical SQL queries in Fabric notebooks without Spark SQL
  • inspect raw Parquet, JSON, and CSV files stored in OneLake
  • perform cross-item joins across separate lakehouses and warehouses

Example prompts for the agent

  • Query Delta tables locally with DuckDB to check row counts
  • Attach DuckDB to the lakehouse in this Fabric notebook
  • Scan raw parquet files in OneLake using DuckDB

How to install using-duckdb

1Plugin marketplace

/plugin marketplace add data-goblin/power-bi-agentic-development
/plugin install etl@power-bi-agentic-development

This installs the whole etl plugin with all its skills

2Skills CLI (Vercel)

npx skills add data-goblin/power-bi-agentic-development --skill using-duckdb -a claude-code

3Manually: put the files in place

~/.claude/skills/using-duckdb/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/using-duckdb/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about using-duckdb

How to install using-duckdb in Claude Code?

Run these two commands in order: /plugin marketplace add data-goblin/power-bi-agentic-development and then /plugin install etl@power-bi-agentic-development.

What does using-duckdb do?

It lets you run SQL queries on Microsoft Fabric OneLake Delta tables and raw data files using DuckDB, either on your developer machine or inside a notebook.

Can using-duckdb write data back to OneLake?

No, it is strictly read-only. Modifying or writing data back to Fabric lakehouses requires running Spark jobs instead.

Similar skills

All skills for Data and databases →

From the same set59

The whole set →
dax A skill for diagnosing and speeding up DAX queries in Power BI semantic models, working through slow measures tier by tier. CX Codex +1 ★ 1,104repo stars bpa-expression-helper bpa-expression-helper — a subagent for debugging, fixing, and explaining Best Practice Analyzer rule expressions with Dynamic LINQ and TOM properties in Power BI. CX Codex +1 ★ 1,104repo stars query-listener query-listener — a Claude Code subagent that hooks into the local Analysis Services instance and grabs the DAX a Power BI Desktop visual sends. Fire it off when you need to see the query behind a click. CX Codex +1 ★ 1,104repo stars lineage-analysis lineage-analysis finds every Power BI report tied to a semantic model across Fabric workspaces, without needing admin rights. CX Codex +1 ★ 1,104repo stars powerbi-custom-visuals powerbi-custom-visuals is a Claude Code skill for building interactive Power BI visuals with the pbiviz toolchain, from project setup through packaging and certification prep. It supports visuals reused across reports. CX Codex +1 ★ 1,104repo stars fabric-capacity fabric-capacity — a skill that tracks utilization of Microsoft Fabric capacities in real time, identifies which workloads consume CU, and manages capacity state through the API. CX Codex +1 ★ 1,104repo stars te-docs te-docs enables documentation searches for Tabular Editor and guides configuration of TE3 settings files. CX Codex +1 ★ 1,104repo stars executing-spark executing-spark is a Claude Code skill that runs Python or PySpark on Fabric Spark through Livy without creating a notebook. It supports temporary transformations and lakehouse table queries. CX Codex +1 ★ 1,104repo stars

Project sponsors

Companies that keep this analytics open