database-snowflake

Executes SQL queries and inspects schemas in Snowflake data warehouses.

Updated Mar 26, 2026
One-click install
npx skills add https://github.com/erwinv2k-TKG/AgentesVSC --skill database-snowflake-erwinv2k-tkg
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: database-snowflake
Source: https://github.com/erwinv2k-TKG/AgentesVSC/tree/main/packs/incidentfox/sre-agent/.claude/skills/database-snowflake
Command: npx skills add https://github.com/erwinv2k-TKG/AgentesVSC --skill database-snowflake-erwinv2k-tkg

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve? Investigating incidents often requires querying a Snowflake data warehouse, but writing queries without knowing the schema leads to errors and wasted time. This Skill enforces a schema-first workflow so you can reliably explore tables, inspect columns, and run SQL against incident enrichment data. ## Core Features & Use Cases - Schema Discovery: Retrieve the known incident enrichment schema, list tables in any database or schema, and describe column details for any table. - SQL Query Execution: Run arbitrary SQL queries with automatic row limits and JSON-formatted results, including safe handling of timestamps and binary values. - Use Case: During a SEV-1 incident investigation, list recent incidents from fact_incident, then join fact_incident_customer_impact with dim_customer to calculate the ARR at risk per affected customer. ## Quick Start Ask the agent to show the most recent SEV-1 incidents from Snowflake along with the estimated ARR at risk for each affected customer.

Frequently Asked Questions about database-snowflake

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

FAQPage Schema
How do I run a SQL query against Snowflake from Python?

Use the execute_query.py script with a --query argument containing your SQL statement. It connects via snowflake-connector-python, applies a default row limit of 100 if none is specified, and returns results as JSON.

How do I list tables in a Snowflake database or schema?

Run list_tables.py with optional --database and --schema arguments to filter the scope. It executes a SHOW TABLES command and returns table names, owners, row counts, and sizes in JSON format.

Why is SNOWFLAKE_PASSWORD not visible in environment variables?

Credentials are injected transparently by a proxy layer, so SNOWFLAKE_PASSWORD is not directly readable. You can still check non-secret variables like SNOWFLAKE_ACCOUNT, SNOWFLAKE_WAREHOUSE, SNOWFLAKE_DATABASE, and SNOWFLAKE_SCHEMA.

How do I get column details for a Snowflake table?

Run describe_table.py with --table and optional --database and --schema flags. It executes DESCRIBE TABLE and returns each column's name, type, nullability, default value, and key constraints as JSON.

What is the correct order for investigating Snowflake incident data?

Follow the schema-first workflow: run get_schema.py to understand available tables, then describe specific tables, and only then execute queries. This prevents writing SQL against unknown columns or incorrect table names.