query-expert

Discover Snowflake tables, search historical queries, and execute SQL via natural language.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/abhiroopb/synthetic-mind --skill query-expert-abhiroopb
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: query-expert
Source: https://github.com/abhiroopb/synthetic-mind/tree/main/skills/query-expert
Command: npx skills add https://github.com/abhiroopb/synthetic-mind --skill query-expert-abhiroopb

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires databricks-sdk, snowflake-connector-python, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill simplifies complex SQL querying on Snowflake by leveraging semantic search over historical queries, table metadata, and domain knowledge, making data discovery and analysis accessible to users of all skill levels.

Core Features & Use Cases

  • Discover Tables: Find relevant tables based on natural language descriptions.
  • Search Historical Queries: Learn from expert query patterns and JOIN logic.
  • Execute SQL: Run SQL queries directly against Snowflake with SSO authentication.
  • Check Permissions: Verify access to tables and get URLs for requesting access.
  • Browse Knowledge: Access brand and domain-specific context for better query understanding.
  • Use Case: A product manager needs to understand user engagement trends. They can ask the Skill to "Find tables related to user activity" and then "Search for queries about daily active users," finally executing a refined SQL query to get the data.

Quick Start

Use the query expert skill to find tables related to payment transactions.

Frequently Asked Questions about query-expert

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

FAQPage Schema
How do I query Snowflake using natural language instead of writing SQL manually?

You can query Snowflake using natural language by leveraging semantic search over historical queries and table metadata to discover tables, understand schemas, and execute SQL directly. This approach translates plain English requests into accurate SQL queries.

How do I find relevant Snowflake tables for data analysis without knowing the exact schema?

Finding relevant Snowflake tables involves using semantic search to match natural language descriptions against indexed table metadata. This data discovery process helps analysts and business users locate the correct tables without prior schema knowledge.

Does this approach support executing SQL with Snowflake SSO authentication?

Yes, executing SQL with Snowflake SSO authentication is supported. The system uses the Snowflake connector for secure SSO-based SQL execution, allowing users to run queries directly against the database without handling manual password authentication.

Can I search historical SQL queries to learn expert JOIN logic and query patterns?

Yes, you can search historical SQL queries to learn expert patterns. The system integrates with Databricks vector search to index past queries, enabling semantic search for specific JOIN logic and query structures relevant to your analysis.

What is the best way to check Snowflake table permissions before running a data discovery query?

The best way to check Snowflake table permissions is to use the built-in access verification feature. It verifies your access to specific tables and provides URLs for requesting access if you lack the necessary permissions to execute your query.

Do I need Databricks vector search to browse knowledge bases for Snowflake query context?

Yes, Databricks vector search is required to browse knowledge bases. It indexes historical queries, table metadata, and domain knowledge, providing the semantic search capability needed to understand complex schemas and brand-specific context.