Auto-activate for .duckdb files, duckdb imports. Comprehensive DuckDB expertise: advanced analytical SQL patterns, performance tuning, data engineering (ETL, multi-source reads, cloud storage), client APIs for Python/Node/Rust/Java/R/Go/WASM, extension development, function reference, and configuration/administration. Use when: writing DuckDB queries, optimizing performance, building data pipelines, connecting from any language, developing extensions, importing/exporting CSV/Parquet/JSON/Delta/Iceberg, or configuring DuckDB for production analytics workloads. Not for OLTP databases (see postgres/mysql) or traditional data warehouses.
From flownpx claudepluginhub cofin/flow --plugin flowThis skill uses the workspace's default tool permissions.
references/cli.mdreferences/configuration.mdreferences/connections.mdreferences/core.mdreferences/data_engineering.mdreferences/extensions.mdreferences/functions.mdreferences/performance.mdreferences/python_client.mdreferences/sql_patterns.mdSearches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Searches prompts.chat for AI prompt templates by keyword or category, retrieves by ID with variable handling, and improves prompts via AI. Use for discovering or enhancing prompts.
Compares coding agents like Claude Code and Aider on custom YAML-defined codebase tasks using git worktrees, measuring pass rate, cost, time, and consistency.
DuckDB is an in-process analytical database with rich SQL dialect, first-class support for Parquet/CSV/JSON, and client APIs for Python, Node.js, Rust, Java, R, Go, WASM, and more. It excels at OLAP workloads, local data exploration, embedded analytics, and data engineering pipelines across local and cloud data sources.
import duckdb
con = duckdb.connect() # in-memory
result = con.sql("SELECT 42 AS answer").fetchall()
# CLI
duckdb mydb.duckdb "SELECT * FROM read_parquet('data/*.parquet')"
</example>
For detailed guides and patterns, refer to the following documents in references/:
SELECT * EXCLUDE (col) -- select all columns except specific onesSELECT COLUMNS('pattern') -- select columns matching a regexPIVOT / UNPIVOT -- built-in pivot supportLIST, STRUCT, MAP nested types with full query supportGROUP BY ALL, ORDER BY ALL -- automatic grouping/orderingFROM tbl SELECT col syntax, implicit SELECT *