duckdb-acp

🥈Silver

DuckDB ACP enables natural language to SQL queries using AI agents like Claude Code. Operations teams can query data in plain English, reducing SQL dependency and speeding up analysis. It integrates directly into DuckDB workflows, connecting with existing data pipelines and tools.

5320Updated 2w ago

Intermediate30min to implementautomation

Saves ~75 min per use

Quick InstallView Source

git clone https://github.com/sidequery/duckdb-acp.git

Works with:

Claude

Overview

About This Skill

How to Use

["Install DuckDB ACP and ensure it's connected to your [DATABASE_NAME]. Use `pip install duckdb-acp` if starting from scratch.","Paste the prompt template into your AI assistant (Claude/ChatGPT) and replace [DATABASE_NAME] with your actual database name and [NATURAL_LANGUAGE_QUERY] with your question.","Review the generated SQL for accuracy—DuckDB ACP handles most cases, but complex queries may need minor adjustments.","Execute the SQL directly in your DuckDB environment or pipeline. For large datasets, add a `LIMIT` clause to test first.","For iterative analysis, refine the query by adding follow-up questions like 'Now filter this to only include products with inventory > 100.'"]

Setup & Installation

Quick Install

No install command available. Check the GitHub repository for manual installation instructions.

Alternative Install (Git Clone)

git clone https://github.com/sidequery/duckdb-acp

Requirements

Claude Code or compatible AI agent
Works with: Claude

Quick Start Guide

Install the Skill

Copy the install command above and run it in your terminal.

Open Your AI Agent

Launch Claude Code, Cursor, or your preferred AI coding agent.

Try It Out

Use the prompt template or examples below to test the skill.

Customize

Adapt the skill to your specific use case and workflow.

Usage Examples

Prompt Template

Use DuckDB ACP to translate this natural language query into a SQL query for [DATABASE_NAME]: '[NATURAL_LANGUAGE_QUERY]'. Execute the query and return the results in a clean table format. If the query involves joins, aggregations, or complex filtering, break down the steps in comments before the SQL. Example: 'Show me the top 5 products by revenue in Q2 2024, grouped by category.'

Example Output

```sql
-- Step 1: Filter sales data for Q2 2024 (April 1 - June 30)
-- Step 2: Group by product_id and category, sum revenue
-- Step 3: Sort by total revenue descending, limit to top 5

SELECT 
    p.product_id,
    p.category,
    SUM(s.revenue) AS total_revenue,
    COUNT(*) AS transaction_count
FROM sales s
JOIN products p ON s.product_id = p.product_id
WHERE s.sale_date BETWEEN '2024-04-01' AND '2024-06-30'
GROUP BY p.product_id, p.category
ORDER BY total_revenue DESC
LIMIT 5;
```

**Query Results:**
| product_id | category     | total_revenue | transaction_count |
|------------|--------------|---------------|-------------------|
| PRD-789    | Electronics  | $124,560.00   | 245               |
| PRD-456    | Home & Garden| $98,720.00    | 189               |
| PRD-123    | Clothing     | $87,340.00    | 312               |
| PRD-321    | Sports       | $76,500.00    | 156               |
| PRD-654    | Books        | $65,200.00    | 287               |

*Note: Revenue figures are in USD. Data includes all completed transactions in Q2 2024.*