Snowflake Development
SkillDatabases & dataOnce added, your AI can write Snowflake SQL, build data pipelines with Dynamic Tables and Streams/Tasks, and use Cortex AI functions and Snowpark Python. It can also create Cortex Agents, configure dbt for Snowflake, and help troubleshoot Snowflake errors. Use it whenever your AI needs to work with Snowflake, from writing queries to sorting out errors.
Available today. Use it from your connected AI after setup.
No other account needed.
After adding it, ask your AI to help with a Snowflake task, such as writing a query or setting up a pipeline. When something goes wrong, ask it to help troubleshoot the Snowflake error.
Then ask your AI: use the Snowflake Development skill
What your AI can do with it
- Write Snowflake SQL
- Build data pipelines with Dynamic Tables and Streams/Tasks
- Use Cortex AI functions and create Cortex Agents
- Write Snowpark Python code
- Configure dbt for Snowflake
- Troubleshoot Snowflake errors
What this skill tells your AI
The instructions your AI receives, as published by borghei/claude-skills in engineering/snowflake-development/SKILL.md and read by ahel’s review.
Category: Engineering Domain: Data Warehouse
Overview
The Snowflake Development skill provides tools for analyzing and optimizing Snowflake SQL queries, recommending warehouse sizing, and enforcing Snowflake-specific best practices. Helps data engineers reduce costs and improve query performance.
Clarify First
Before analyzing or sizing, confirm these inputs. If any is unknown or vague, ASK — do not assume:
- Action — analyze / optimize / warehouse-sizing (
--action; selects the workflow) - SQL file or query — the specific query(ies) to optimize (
--file; the subject of the analysis) - Workload type & data volume — ETL / BI / ad-hoc and the GB scale (
--workload/--data-volume; drives the warehouse recommendation)
Stop rule: ask only the 2-3 that most change the output. If the user says "just draft it," proceed and list your assumptions at the top of the artifact.
Quick Start
# Analyze a Snowflake SQL file for optimization opportunities
python scripts/snowflake_query_helper.py --file queries.sql --action analyze
# Get warehouse sizing recommendations
python scripts/snowflake_query_helper.py --action warehouse-sizing --workload "etl" --data-volume "500GB"
# Optimize a specific query
python scripts/snowflake_query_helper.py --file slow_query.sql --action optimize
Tools Overview
| Tool | Purpose | Key Flags |
|---|---|---|
snowflake_query_helper.py | Analyze, optimize Snowflake SQL and recommend warehouse sizes | --file, --action, --workload, --data-volume |
Workflows
Query Performance Optimization
- Collect slow queries from query history
- Run analyzer to identify optimization opportunities
- Apply recommended changes
- Compare before/after execution plans
Warehouse Right-Sizing
- Identify workload type (ETL, BI, ad-hoc, etc.)
- Run warehouse-sizing with data volume
- Review recommendations
- Implement multi-cluster settings if applicable
Reference Documentation
- Snowflake Best Practices - Query patterns, warehouse management, cost optimization
Common Patterns
Cost Reduction
- Right-size warehouses (don't use XL for small queries)
- Set auto-suspend to 60 seconds for ad-hoc warehouses
- Use materialized views for frequently accessed aggregations
- Partition large tables with clustering keys
- Avoid SELECT * in production queries
Signals
- GitHub stars
- 752
- Forks
- 137
- Last commit
- Aug 2026
Advanced
- Catalog kind
- skill
- Gateway key
snowflake-development- Source
- github.com/borghei/claude-skills