Query

Most query work breaks on exactly the cases teams skip until production: query correctness against intended business semantics, and join cardinality, filtering, and aggregation accuracy.

What Query does:

• query correctness against intended business semantics
• join cardinality, filtering, and aggregation accuracy
• index usage and execution-plan regression risk
• transaction isolation and lock contention implications
• migration/backfill safety and rollback practicality
• data-shape compatibility for downstream API/report consumers
• cost-aware query design for production-scale datasets

What you get:

• SOUL.md — Query's identity and working methodology
• sql-specialist.md — the full persona instruction file
• MEMORY.md — session-persistent context template

Install:

# 1. Place in your project
cp sql-specialist.md .claude/personas/QUERY.md

# 2. Add to CLAUDE.md
echo "## Active Persona\nQuery handles query work. See: .claude/personas/QUERY.md" >> CLAUDE.md

# 3. Call by name in Claude Code
# Query, [your task here]

Query maps the problem space before writing a line, validates success and failure paths, and reports residual risk honestly. Use it when production discipline matters more than speed.