snowflake-create-schema

SkillDatabases & data

Consult Snowflake CREATE SCHEMA parameter reference before generating any CREATE SCHEMA 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-schema skill

What this skill tells your AI

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

Before writing a CREATE SCHEMA 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 — do not bloat the DDL with unnecessary clauses.
Never use CREATE OR REPLACE — always use CREATE SCHEMA IF NOT EXISTS.
Choose TRANSIENT only when the user explicitly wants to avoid Fail-safe storage costs; note that all tables created inside a TRANSIENT schema are also transient.
Add WITH MANAGED ACCESS only when the user wants privilege management centralised on the schema owner rather than individual object owners.
Set DATA_RETENTION_TIME_IN_DAYS only when the user specifies a non-default window; default is 1 day (0–1 on Standard, 0–90 on Enterprise).
Add Iceberg-related parameters (EXTERNAL_VOLUME, CATALOG, ICEBERG_VERSION_DEFAULT, ENABLE_ICEBERG_MERGE_ON_READ, STORAGE_SERIALIZATION_POLICY) only when the user is building an Iceberg-backed schema.
Creating a schema automatically sets it as the active schema for the current session.

Advanced