snowflake-create-semantic-view

SkillDatabases & data

Consult Snowflake CREATE SEMANTIC VIEW parameter reference before generating any CREATE SEMANTIC VIEW DDL.

Available today. Use it from your connected AI after setup.

No other account needed.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the snowflake-create-semantic-view skill

What this skill tells your AI

The instructions your AI receives, as published by gyrus-dev/frosty in skills/snowflake-create-semantic-view/SKILL.md and read by ahel’s review.

Before writing a CREATE SEMANTIC VIEW statement:

Read references/parameters.md to review all available parameters and their defaults.
For each parameter, decide whether the user's request implies a non-default value.
Include only the parameters that differ from the default or that the user explicitly requested.
Never use CREATE OR REPLACE — always use CREATE SEMANTIC VIEW IF NOT EXISTS where supported.
Every semantic view must include a TABLES clause; at least one DIMENSIONS or METRICS clause is also required for the view to be valid.
Define RELATIONSHIPS whenever two or more logical tables must be joined; specify join type (standard, ASOF, or range) explicitly.
Populate AI_SQL_GENERATION with concise natural-language instructions that guide Cortex Analyst when generating SQL from the view.
Mark fact expressions PRIVATE when they should not be exposed directly to end users; dimensions are always PUBLIC.

Advanced