Data engineering skills for AI agents.

The library's data engineering skills include Analytics Engineer, CSV Transformer and Data Catalog Builder. They cover pipelines and ETL, data modeling, and streaming. 18 passed Skill Guard clean. The other 1 switch on only after you have read them and said yes. Skills are written instructions, not app connections: a bot reads the one a job calls for and works the way it lays out. Add any of them to a bot in Settings → Skills, or tell your Chief of Staff the job and let it choose.

• Analytics EngineerAnalytics engineering expertise covering dbt best practices, metrics layer design, semantic modeling, dashboard design principles and KPI definition.
• CSV TransformerExpert data format transformation covering CSV parsing edge cases, encoding detection, JSON/XML/Parquet/Avro conversion and data type inference.
• Data Catalog BuilderData catalog and metadata management covering catalog architecture, DataHub and Amundsen setup, automated metadata ingestion and data lineage tracking.
• Data Contract DesignerExpertise in designing and enforcing data contracts including schema definitions, API-first data interfaces and versioning strategies.
• Data Lakehouse ArchitectArchitecture expertise for data lakehouse platforms covering Delta Lake, Apache Iceberg, Apache Hudi and medallion architecture design.
• Data Mesh StrategistStrategic expertise in data mesh architecture covering domain-oriented data ownership, data-as-a-product thinking and self-serve data infrastructure.
• Data Migration SpecialistDatabase migration expertise covering zero-downtime migration strategies, dual-write patterns, shadow tables, data reconciliation and schema evolution.
• Data ModelerExpert data modeling covering star schema, snowflake schema, Data Vault 2.0, dimensional modeling, slowly changing dimensions and bridge tables.
• Data Pipeline OrchestratorData pipeline orchestration expertise covering Airflow DAG design, dbt models, pipeline patterns (batch, micro-batch, streaming) and dependency management.
• Data Pipeline Health CheckData pipeline reliability assessment evaluating data freshness, quality metrics and monitoring coverage.
• Data Quality EngineerData quality engineering covering Great Expectations suite design, data contracts between teams and schema validation at ingestion.
• Data ValidatorData validation and quality expertise covering Great Expectations patterns, schema validation, statistical validation and referential integrity checks.
• dbt EngineerDeep expertise in dbt (data build tool) covering model design, testing strategies, documentation, materialization selection and custom macros.
• ETL ArchitectExpert ETL pipeline design covering extract patterns (CDC, full load, incremental), transform strategies (SCD types and data cleansing).
• Orchestration EngineerData pipeline orchestration covering Apache Airflow DAG design patterns, Dagster software-defined assets and Prefect flow composition.
• Spark EngineerApache Spark expertise covering RDD vs DataFrame vs Dataset APIs, partitioning strategies, shuffle optimization, broadcast joins, caching and Spark SQL.
• SQL MasterAdvanced SQL expertise including window functions, CTEs, recursive queries, query optimization with EXPLAIN plans and indexing strategies.
• Streaming ArchitectReal-time data streaming expertise covering Kafka architecture, stream processing with Flink and Kafka Streams and exactly-once semantics.
• Streaming Data EngineerHands-on streaming data engineering covering Apache Kafka producer/consumer tuning, Flink stateful stream processing and Spark Structured Streaming.