analyzing-data

Name: analyzing-data
Availability: InStock
Author: Astronomer

Query data warehouses with SQL and return Polars/Pandas dataframes.

419|61|Updated Jan 13, 2026

Search Tags:#SQL #patterns #data-analysis #kernel #analyze #concepts #data-warehouse

Ready to run

npx skills add https://github.com/astronomer/agents --skill analyzing-data-astronomer

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: analyzing-data
Source: https://github.com/astronomer/agents/tree/main/skills/analyzing-data
Command: npx skills add https://github.com/astronomer/agents --skill analyzing-data-astronomer

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires ipykernel, jupyter-client, polars, pandas, numpy, sqlalchemy, psycopg[binary,pool], psycopg2-binary, pymysql, mysql-connector-python, mysqlclient, oracledb, pyathena, databricks-sql-connector, sqlalchemy-bigquery, sqlalchemy-spanner, duckdb, duckdb-engine, google-cloud-bigquery[pandas,pyarrow], db-dtypes, snowflake-connector-python[pandas], snowflake-sqlalchemy, vertica-python, clickhouse-driver, clickhouse-sqlalchemy, ibm_db_sa, fdb, hdbcli, teradatasqlalchemy, cryptography, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This skill enables AI agents to answer business questions by querying data warehouses and presenting concise results without manual, ad-hoc SQL scripting.

Core Features & Use Cases

Data warehouse querying: generate SQL-based insights (counts, trends, and aggregations) across Snowflake, BigQuery, Postgres, and other warehouses.
Answer business questions: provide answers like "how many customers" or "top products" by creating and executing targeted queries and returning structured results.
Contextual execution: uses a persistent kernel with integrated connectors to run queries and return results in Polars/DataFrames, ready for further analysis.

Quick Start

Use the analyzing-data skill to run a sample query against your warehouse, for example counting rows in a known table and returning the result in a dataframe.

Frequently Asked Questions about analyzing-data

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

FAQPage Schema

How do I analyze data warehouse tables to answer business questions without writing manual SQL?▼

To analyze data warehouse tables, this skill generates and executes targeted SQL queries to provide counts, trends, and aggregations, returning structured Polars or Pandas dataframes for immediate business insights.

Can I query Snowflake, BigQuery, and Postgres from a single Python environment?▼

You can query Snowflake, BigQuery, and Postgres using integrated Python-based connectors like snowflake-sqlalchemy, google-cloud-bigquery, and psycopg, which execute warehouse queries within a persistent kernel.

What is the best way to return data warehouse query results as a Polars dataframe?▼

Returning data warehouse query results as a Polars dataframe is handled automatically by running SQL queries through a persistent Python kernel, yielding structured dataframes ready for downstream analysis.

Does querying a data warehouse through a Python kernel require specific database drivers?▼

Querying a data warehouse through a Python kernel requires specific database drivers and connectors, including SQLAlchemy, psycopg2-binary, pymssql, or databricks-sql-connector, depending on your target warehouse platform.

How does SQL-driven analytics handle ad-hoc lookups and aggregations across multiple warehouses?▼

SQL-driven analytics handles ad-hoc lookups and aggregations by automatically generating and executing SQL across multiple warehouses, enabling rapid trend analysis and counts without manual scripting.