| name | sql-review |
| description | SQL-specific code review — delegates to de-sql-optimizer + python-code-
reviewer agents. Use when reviewing SQL for anti-patterns, performance issues,
or cross-dialect correctness.
|
SQL Review Command
Review SQL code for anti-patterns, performance, and cross-dialect correctness
Usage
/sql-review <file-or-directory>
Examples
/sql-review models/marts/mart_revenue.sql
/sql-review models/staging/
/sql-review "Review all SQL in this PR for Snowflake compatibility"
What This Command Does
- Invokes the python-code-reviewer agent with DE capability enabled
- Escalates SQL optimization questions to de-sql-optimizer agent
- Loads KB patterns from
sql-patterns, data-quality, and dbt domains
- Reviews for:
- SQL anti-patterns (
SELECT *, implicit coercion, missing partition filters)
- Performance issues (full table scans, N+1 patterns, missing indexes)
- Cross-dialect correctness (Snowflake, BigQuery, Postgres, DuckDB)
- PII detection and masking compliance
- dbt-specific issues (ref usage, incremental guards, test coverage)
Agent Delegation
| Agent | Role |
|---|
python-code-reviewer | Primary — DE review capability (anti-patterns, PII, tests) |
de-sql-optimizer | Escalation — query plan analysis, window functions |
de-dbt-specialist | Escalation — dbt-specific patterns and macros |
KB Domains Used
sql-patterns — SQL anti-patterns, window functions, CTEsdata-quality — quality checks, PII detectiondbt — model patterns, testing conventions
Output
A structured review report with severity-classified issues and fix suggestions.
