snowflake-create-internal-stage

SkillDatabases & data

Consult Snowflake CREATE STAGE parameter reference before generating any CREATE STAGE DDL for internal stages.

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-internal-stage skill

What this skill tells your AI

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

Before writing a CREATE STAGE statement for an internal stage:

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 STAGE IF NOT EXISTS.
Named internal stages are the correct choice for sharing data across multiple tables or users within an account; use user stages (@~) or table stages (@%table) only when the user explicitly requests them (they cannot be created with DDL).
The default encryption for internal named stages is SNOWFLAKE_FULL (client-side + server-side). Use SNOWFLAKE_SSE only when the user explicitly wants server-side-only encryption.
Attach a FILE_FORMAT only when the user specifies a non-CSV format or custom format options; omit otherwise to rely on COPY INTO defaults.
Enable the DIRECTORY table (DIRECTORY = ( ENABLE = TRUE )) only when the user needs to browse or query staged files via directory table functions.

Advanced