sql-queries

Write correct and performant SQL queries across major data warehouse dialects.

7|Updated Feb 6, 2026
One-click install
npx skills add https://github.com/Epiphytic/ai-plugin-translator --skill sql-queries-epiphytic
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: sql-queries
Source: https://github.com/Epiphytic/ai-plugin-translator/tree/main/packages/core/test/fixtures/regression-output/knowledge-work-plugins/data/skills/sql-queries
Command: npx skills add https://github.com/Epiphytic/ai-plugin-translator --skill sql-queries-epiphytic

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps users write correct, efficient SQL queries across different database and warehouse systems while reducing dialect errors, performance issues, and debugging time.

Core Features & Use Cases

  • Multi-Dialect SQL Support: Provides guidance for PostgreSQL, Snowflake, BigQuery, Redshift, and Databricks SQL syntax, functions, and optimization techniques.
  • Analytical Query Patterns: Helps build complex queries using CTEs, window functions, cohort analysis, funnel analysis, aggregations, and deduplication patterns.
  • Query Optimization and Debugging: Assists with performance tuning, error resolution, schema issues, type handling, and warehouse-specific best practices.

Quick Start

Use the sql-queries skill to optimize this slow customer retention query for BigQuery.

Frequently Asked Questions about sql-queries

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

FAQPage Schema
How do I optimize slow analytical SQL queries in BigQuery or Snowflake?

To optimize slow analytical SQL queries, apply warehouse-specific tuning strategies like CTEs, window functions, and proper aggregations. This approach reduces dialect errors and improves performance across BigQuery, Snowflake, Redshift, and Databricks.

What is the best way to translate complex PostgreSQL queries to Snowflake syntax?

Translating PostgreSQL queries to Snowflake requires adjusting dialect-specific syntax and functions for analytical workflows. Using structured query translation ensures correct type handling, schema validation, and optimal performance in the target warehouse.

How do I write a cohort analysis query using SQL window functions?

Writing a cohort analysis query with SQL window functions involves partitioning data by user groups and tracking events over time. This pattern, along with funnel analysis and deduplication, builds correct complex transformations for production analytics.

Does this approach work for debugging type handling and schema issues in Redshift?

Yes, debugging type handling and schema issues in Redshift is supported. It provides warehouse-specific best practices to resolve errors and validate schemas across major data warehouse dialects for production analytics workflows.

Why does my SQL query fail when moving from Databricks to BigQuery?

SQL queries fail moving from Databricks to BigQuery due to dialect-specific syntax and function differences. Resolving these requires applying warehouse-specific type handling and debugging approaches to correct the analytical query structure.