菜单
Snowflake data warehouse queries and schema inspection. Use when running SQL queries against Snowflake, listing tables, or inspecting schemas.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Pull incident context from alerting platforms (PagerDuty). Use when investigating who's on-call, incident history, alert patterns, or MTTR metrics.
Opsgenie alert management and on-call scheduling. Use for listing alerts, checking on-call, computing MTTA/MTTR, and alert fatigue analysis. Supports team and priority filtering.
Amplitude product analytics. Use when querying user events, funnels, retention, or product usage data. Provides event segmentation, user activity lookup, and annotation queries.
Google BigQuery data warehouse queries and schema inspection. Use when running SQL queries, listing datasets/tables, or inspecting table schemas in BigQuery.
MySQL/MariaDB database inspection and queries. Use when investigating table schemas, running queries, checking processlist, replication status, InnoDB engine status, or lock contention.
PostgreSQL database inspection and queries. Use when investigating table schemas, running queries, checking locks, replication status, or long-running queries.
| name | database-snowflake |
| description | Snowflake data warehouse queries and schema inspection. Use when running SQL queries against Snowflake, listing tables, or inspecting schemas. |
| allowed-tools | Bash(python *) |
IMPORTANT: Credentials are injected automatically by a proxy layer. Do NOT check for SNOWFLAKE_PASSWORD in environment variables - it won't be visible to you. Just run the scripts directly; authentication is handled transparently.
Configuration environment variables you CAN check (non-secret):
SNOWFLAKE_ACCOUNT - Snowflake account identifierSNOWFLAKE_WAREHOUSE - Compute warehouseSNOWFLAKE_DATABASE - Default databaseSNOWFLAKE_SCHEMA - Default schemaAlways get the schema before writing queries.
GET SCHEMA / LIST TABLES → DESCRIBE TABLE → EXECUTE QUERY
All scripts are in .claude/skills/database-snowflake/scripts/
python .claude/skills/database-snowflake/scripts/get_schema.py
python .claude/skills/database-snowflake/scripts/list_tables.py [--database DB] [--schema SCHEMA]
python .claude/skills/database-snowflake/scripts/describe_table.py --table TABLE_NAME [--database DB] [--schema SCHEMA]
python .claude/skills/database-snowflake/scripts/execute_query.py --query "SELECT * FROM fact_incident ORDER BY started_at DESC LIMIT 10" [--limit 100]
1. get_schema.py (understand available tables)
2. execute_query.py --query "SELECT * FROM fact_incident WHERE sev = 'SEV-1' ORDER BY started_at DESC LIMIT 10"
3. execute_query.py --query "SELECT c.customer_name, ic.estimated_arr_at_risk_usd FROM fact_incident_customer_impact ic JOIN dim_customer c ON ic.customer_id = c.customer_id WHERE ic.incident_id = '<id>'"