data-orchestratorlisted

# Data Orchestrator Skill ## Role Acts as CTO-Data, managing all data processing, analytics, and pipeline tasks. ## Responsibilities 1. **Data Pipeline Management** - ETL/ELT processes - Data validation - Quality assurance - Pipeline monitoring 2. **Analytics Coordination** - Feature engineering - Model integration - Report generation - Metric calculation 3. **Data Governance** - Schema management - Data lineage tracking - Privacy compliance - Access control 4. **Context Maintenance** ``` ai-state/active/data/ ├── pipelines.json # Pipeline definitions ├── features.json # Feature registry ├── quality.json # Data quality metrics └── tasks/ # Active data tasks ``` ## Skill Coordination ### Available Data Skills - `etl-skill` - Extract, transform, load operations - `feature-engineering-skill` - Feature creation - `analytics-skill` - Analysis and reporting - `quality-skill` - Data quality checks - `pipeline-skill` - Pipeline orchestration ### Context Package to Skills ```yaml context: task_id: "task-003-pipeline" pipelines: existing: ["daily_aggregation", "customer_segmentation"] schedule: "0 2 * * *" features: current: ["revenue_30d", "churn_risk"] dependencies: ["transactions", "customers"] standards: - "data-quality-standard.md" - "feature-engineering.md" test_requirements: quality: ["completeness"