Which specific Hazel Health tables does this skill optimize for?

It is specifically tuned for tables such as MART_VISIT, DIM_PATIENT, and TETRIS_RANKED_SCHEDULING, as well as schemas within HAZEL_EDW and HAZEL_STREAM.

What happens if the semantic layer files are not found?

The skill will provide setup instructions and links to the official documentation, but it can still perform queries by using DESCRIBE commands to discover table structures manually.

Do I need to have the Snowflake CLI installed to use this skill?

Yes, this skill requires the Snowflake CLI (snow) to be installed and configured with a working connection on your local machine.

How does the skill handle complex SQL joins and business logic?

It reads from a semantic layer that includes 'domain' files and 'gotchas' documentation to ensure Claude follows the correct join patterns and metric definitions used by Hazel Health.

Hazel Snowflake Query

Name: Hazel Snowflake Query
Author: winsthuang

bywinsthuang

0•

Gestión de Bases de Datos

Enables Claude to execute accurate SQL queries against Hazel Health’s Snowflake data warehouse using a specialized semantic layer.

The hazel-snowflake-query skill provides a robust harness for interacting with Hazel Health’s Snowflake infrastructure within Claude Code. It streamlines the data analysis process by automatically detecting the Snowflake CLI, locating the organizational semantic layer (even across Google Drive for Desktop), and applying domain-specific business logic. By utilizing pre-defined patterns for tables like MART_VISIT and DIM_PATIENT, the skill ensures Claude writes high-quality SQL that respects schema paths, enum values, and complex join patterns, reducing errors in data retrieval and reporting.

Características Principales

01Graceful fallback to schema discovery via DESCRIBE commands when metadata is missing.

02Integrated sanity checks and validation queries for result accuracy.

03Automated Snowflake CLI integration and connection verification.

040 GitHub stars

05Context-aware SQL generation using domain-specific column definitions and enums.

06Multi-path semantic layer discovery across local and cloud-synced directories.

Casos de Uso

01Generating complex RCM and billing reports using validated join patterns and metrics.

02Performing data discovery and schema exploration for Hazel Health's EDW and STREAM schemas.

03Analyzing patient visit trends and scheduling metrics from the MART_VISIT table.

Características Principales

01Graceful fallback to schema discovery via DESCRIBE commands when metadata is missing.

02Integrated sanity checks and validation queries for result accuracy.

03Automated Snowflake CLI integration and connection verification.

040 GitHub stars

05Context-aware SQL generation using domain-specific column definitions and enums.

06Multi-path semantic layer discovery across local and cloud-synced directories.

Casos de Uso

01Generating complex RCM and billing reports using validated join patterns and metrics.

02Performing data discovery and schema exploration for Hazel Health's EDW and STREAM schemas.

03Analyzing patient visit trends and scheduling metrics from the MART_VISIT table.