querying-data-lake

Execute Athena SQL queries across Glue, S3 Tables, and Redshift catalogs.

Updated Jun 18, 2026

Search Tags:#sql #athena #data-lake #cost-tracking #workgroup #federated-catalogs

Ready to run

npx skills add https://github.com/AndreKurait/claude-marketplace-test --skill querying-data-lake-andrekurait

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: querying-data-lake
Source: https://github.com/AndreKurait/claude-marketplace-test/tree/main/skills/specialized-skills/analytics-skills/querying-data-lake
Command: npx skills add https://github.com/AndreKurait/claude-marketplace-test --skill querying-data-lake-andrekurait

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Execute and manage Athena SQL queries across default and federated catalogs (Glue, S3 Tables, Redshift) with workgroup selection, statement classification, and error recovery.

Core Features & Use Cases

Executes queries across multiple catalogs (Glue, S3 Tables, Redshift) with workgroup selection and cost reporting.
Resolves target assets across catalogs and classifies statements for safety before execution.
Audit logging and sandboxed execution through AWS MCP server; supports cross-catalog analytics and profiling.

Quick Start

Provide an Athena SQL statement or named query to run against the default or federated catalogs.

Frequently Asked Questions about querying-data-lake

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

FAQPage Schema

How do I run Athena SQL queries across federated catalogs?▼

Execute Athena SQL across default and federated catalogs like Glue, S3 Tables, and Redshift by providing a statement or named query. The tool resolves target assets, classifies statements for safety, and handles workgroup selection before running the query.

Can I track query costs and data scanned when running Athena SQL?▼

Yes, Athena SQL execution includes cost visibility and data-scanned accounting. It applies cost reporting to ad-hoc queries, scheduled reports, and cross-catalog analytics through selected workgroups.

How does error recovery work for Athena SQL statements?▼

Athena SQL execution classifies statements for safety and applies error recovery before and during runs. Sandboxed execution through the AWS MCP server and guarded tool calls ensure safe query processing and automatic handling of execution issues.

Do I need to specify an AWS region and output location to run Athena SQL?▼

Yes, running Athena SQL requires satisfying region prompts and output location confirmation. The tool manages argument handling and workgroup selection to ensure queries execute correctly in the proper environment.

What is the best way to perform cross-catalog analytics with Athena?▼

Use Athena SQL to run cross-catalog analytics by resolving target assets across Glue, S3 Tables, and Redshift. The tool supports profiling and audit logging while executing queries across these federated data sources.

When should I not use this approach for querying a data lake?▼

Avoid this approach if your queries require execution outside AWS or lack proper workgroup configuration. The tool relies on the AWS MCP server for sandboxed execution and needs valid federated catalog endpoints to function correctly.