data-quality-observability

Data-quality & observability team — 2 agents (data-quality-architect, data-quality-engineer) for the layer answering 'is this data CORRECT, FRESH, COMPLETE, and can we TRUST it?': producer-boundary contracts, validation tests (not-null/unique/accepted-values/referential/distribution), freshness/volume/schema-drift/distribution monitors, threshold vs statistical anomaly detection, data-quality SLAs/SLIs, and data-incident response (triage, quarantine/circuit-breaker, root-cause, backfill). Fluent in dbt tests + dbt-expectations, Great Expectations, Soda, Elementary, managed observability (Monte Carlo, Bigeye, Metaplane), and warehouse-native checks. 3 skills, a 2-doc knowledge bank (tooling decision tree + 2026 patterns reference), and 2 templates. Distinct from data-platform (ELT/warehouse/BI), analytics-engineering (dbt transforms), data-orchestration (schedules the runs), and data-governance-privacy (policy/PII/lineage) — this is the trust/quality layer over all of them. Requires ravenclaude-core@>=0.7.0.