snowflake-create-compute-pool

SkillDatabases & data

Consult Snowflake CREATE COMPUTE POOL parameter reference before generating any CREATE COMPUTE POOL 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-compute-pool skill

What this skill tells your AI

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

Before writing a CREATE COMPUTE POOL 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 COMPUTE POOL IF NOT EXISTS.
Always set MIN_NODES, MAX_NODES, and INSTANCE_FAMILY — these are required. Choose INSTANCE_FAMILY based on workload: CPU_X64_XS/S/M/L for general workloads, HIGHMEM_X64_S/M/L for memory-intensive workloads, GPU_NV_S/M/L for GPU workloads. Set INITIALLY_SUSPENDED = TRUE for pools that should not incur cost immediately. Set AUTO_SUSPEND_SECS conservatively (default 3600) to avoid runaway costs. Use FOR APPLICATION only when the pool is dedicated to a Snowflake Native App.

Advanced