snowflake-expert — Claude Code skill: what it does, how to install
snowflake-expert — a skill that walks your agent through Snowflake warehouse sizing, clustering, streams and query tuning.
Apache-2.0 239 installs ★ 45 updated 2026-10-12
npx skills add personamanagmentlayer/pcl --skill snowflake-expert -a claude-codeWhat snowflake-expert does
snowflake-expert turns the agent into a Snowflake reviewer. It knows virtual warehouse sizing, how to split databases and schemas, stages and loading, streams and tasks, time travel, zero-copy cloning, data sharing, and SQL tuning.
Inside are short best-practice blocks on warehouse management, data organization, cost, performance, and access control. A separate section lists anti-patterns with SQL: too many clustering keys, an X-SMALL warehouse behind a large ETL job, scanning a whole table instead of reading a stream, never opening SNOWFLAKE.ACCOUNT_USAGE.QUERY_HISTORY. Deeper material sits in references/CORE_CONCEPTS.md and is read only when needed.
The skill lists snowflake-connector-python 3.0.0 or newer as a requirement, and it works with Read, Write, Edit, Bash, Glob and Grep. Miss the package in a fresh environment and the first query against a warehouse stops there.
What it helps with
- Pick a warehouse size for a nightly load
- Cut clustering keys down to 1–3 columns
- Swap a full scan of
ordersfor a stream when tracking changes - Surface the slowest queries in
QUERY_HISTORY - Keep scratch data in transient tables to trim storage costs
Example prompts for the agent
- Which warehouse size should
etl_whuse for the nightly load? - Rewrite this change-tracking query to read from
orders_streaminstead of scanning byupdated_at - Review the clustering keys on
ordersand tell me what to drop
How to install snowflake-expert
1Skills CLI (Vercel)
npx skills add personamanagmentlayer/pcl --skill snowflake-expert -a claude-code2Manually: put the files in place
~/.claude/skills/snowflake-expert/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/snowflake-expert/
1Skills CLI (Vercel)
npx skills add personamanagmentlayer/pcl --skill snowflake-expert -a codex2Manually: put the files in place
.agents/skills/snowflake-expert/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add personamanagmentlayer/pcl --skill snowflake-expert -a cursor2Manually: put the files in place
.cursor/skills/snowflake-expert/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install personamanagmentlayer/pcl stdlib/data/snowflake-expert2Manually: put the files in place
.github/skills/snowflake-expert/SKILL.md1Skills CLI (Vercel)
npx skills add personamanagmentlayer/pcl --skill snowflake-expert -a gemini-cli2Platform CLI
gemini skills install https://github.com/personamanagmentlayer/pcl --path stdlib/data/snowflake-expertManually: put the files in place
.devin/skills/snowflake-expert/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add personamanagmentlayer/pcl --skill snowflake-expert -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about snowflake-expert
How do I install snowflake-expert in Claude Code?
Run npx skills add personamanagmentlayer/pcl --skill snowflake-expert -a claude-code. The skill file lands at ~/.claude/skills/snowflake-expert/SKILL.md.
What does snowflake-expert do?
It gives the agent Snowflake rules: warehouse sizing, database and schema layout, streams and tasks, SQL tuning, and a set of anti-patterns with sample queries.
What does the skill need to run?
snowflake-connector-python 3.0.0 or newer, and permission for Read, Write, Edit, Bash, Glob and Grep.
Source text
SKILL.md · Apache-2.0
---
name: snowflake-expert
version: 1.1.0
description: >-
Expert-level Snowflake data warehouse platform, virtual warehouses, data sharing,
streams, tasks, and SQL optimization. Use when the user mentions data warehouse, SQL,
analytics, or cloud, or when the task involves Architecture and Virtual Warehouses,
Database Objects and Organization, Data Loading and Stages, or Streams and Tasks.
category: data
author: PCL Team
license: Apache-2.0
tags:
- snowflake
- data-warehouse
- sql
- analytics
- cloud
allowed-tools:
- Read
- Write
- Edit
- Bash
- Glob
- Grep
requirements:
snowflake-connector-python: '>=3.0.0'
---
# Snowflake Expert
You are an expert in Snowflake with deep knowledge of virtual warehouses, data sharing, streams, tasks, time travel, zero-copy cloning, and SQL optimization. You design and manage enterprise-scale data warehouses that are performant, cost-effective, and secure.
## Best Practices
### 1. Warehouse Sizing and Management
- Start with smaller warehouses and scale up as needed
- Use multi-cluster warehouses for concurrency
- Set AUTO_SUSPEND to 5-10 minutes to avoid cold starts
- Monitor credit usage with resource monitors
- Use separate warehouses for different workloads (ETL, BI, ad-hoc)
### 2. Data Organization
- Use databases for major boundaries (prod/dev/test)
- Use schemas for logical grouping
- Implement clustering for large tables (>1TB)
- Use transient tables for temporary data to reduce storage costs
- Leverage zero-copy cloning for development/testing
### 3. Cost Optimization
- Use table types appropriately (permanent, transient, temporary)
- Set data retention periods based on needs
- Monitor and drop unused objects
- Use result caching for repeated queries
- Implement query timeouts to prevent runaway queries
### 4. Performance Optimization
- Cluster large tables on commonly filtered columns
- Use materialized views for expensive aggregations
- Leverage search optimization for point lookups
- Partition pruning with proper WHERE clauses
- Monitor query profile for bottlenecks
### 5. Security and Governance
- Implement role-based access control
- Use row-level and column-level security
- Enable network policies for IP whitelisting
- Use secure views for data sharing
- Enable MFA for privileged accounts
## Anti-Patterns
### 1. Over-Clustering
```sql
-- Bad: Too many clustering keys
ALTER TABLE orders CLUSTER BY (order_date, customer_id, status, product_id);
-- Good: 1-3 columns, most selective first
ALTER TABLE orders CLUSTER BY (order_date, customer_id);
```
### 2. Undersized Warehouses
```sql
-- Bad: Using X-Small for large ETL jobs
CREATE WAREHOUSE etl_wh WITH WAREHOUSE_SIZE = 'X-SMALL';
-- Good: Appropriately sized for workload
CREATE WAREHOUSE etl_wh WITH WAREHOUSE_SIZE = 'LARGE';
```
### 3. Not Using Streams for CDC
```sql
-- Bad: Full table scan for changes
SELECT * FROM orders WHERE updated_at > LAST_PROCESSED_TIME;
-- Good: Use streams
CREATE STREAM orders_stream ON TABLE orders;
SELECT * FROM orders_stream;
```
### 4. Ignoring Query History
```sql
-- Bad: Not monitoring expensive queries
-- Good: Regular review of query history
SELECT
query_text,
total_elapsed_time,
bytes_scanned
FROM SNOWFLAKE.ACCOUNT_USAGE.QUERY_HISTORY
WHERE execution_status = 'SUCCESS'
AND start_time >= DATEADD(day, -7, CURRENT_TIMESTAMP())
ORDER BY total_elapsed_time DESC
LIMIT 20;
```
## Reference Documentation
Detailed material lives alongside this skill and is read on demand:
- [Core Expertise](references/CORE_CONCEPTS.md) — Architecture and Virtual Warehouses, Database Objects and Organization, Data Loading and Stages, Streams and Tasks, Time Travel and Zero-Copy Cloning, Data Sharing, Advanced SQL and Optimization, Access Control and Security
## Resources
- [Snowflake Documentation](https://docs.snowflake.com/)
- [Snowflake Best Practices](https://docs.snowflake.com/en/user-guide/best-practices)
- [Snowflake University](https://learn.snowflake.com/)
- [Snowflake Community](https://community.snowflake.com/)
- [Snowflake SQL Reference](https://docs.snowflake.com/en/sql-reference)
- [Snowflake Performance Optimization](https://docs.snowflake.com/en/user-guide/performance)
- [Snowflake Security](https://docs.snowflake.com/en/user-guide/security)
© PCL Team · Apache-2.0 · personamanagmentlayer/pcl