SQL & Databases Agent Skills

Reference for MariaDB's vector functions and VECTOR data type, covering VEC_Distance, VEC_Distance_Euclidean, VEC_Distance_Cosine, VEC_FromText, VEC_ToText, and MHNSW vector index usage for SQL queries over embeddings.

Reference for MariaDB information functions, covering session and server metadata such as LAST_INSERT_ID, ROW_COUNT, FOUND_ROWS, USER, and VERSION, with usage guidance for writing SQL that reads auto-increment IDs, row counts, and connection details.

Reference for MariaDB control-flow functions and operators, including IF(), IFNULL(), NULLIF(), COALESCE(), CASE, NVL2(), and DECODE_ORACLE, with guidance on correct usage and common pitfalls.

Scaffold a MariaDB Schema Management (MSM) project and author the initial schema in the development folder, creating the project with msm.create_project and writing the first version's tables, objects, and grants into the MSM sections of <schema>_next.sql.

Modify existing MariaDB REST Service endpoints using ALTER and DROP REST statements, including renaming request paths, enabling/disabling, publishing, and merging JSON options.

Provides ClickHouse-specific patterns for schema design, query optimization, data ingestion, and analytics, including materialized views and performance monitoring.

Manage Amazon Aurora DSQL clusters, schemas, and migrations with MCP tools and CLI scripts, including multi-tenant patterns and IAM-based authentication.

Transforms raw data into analytics-ready models using dbt, covering models, tests, macros, sources, snapshots, documentation, and packages.

Documents the required and optional keys for defining unit tests in a dbt YAML schema file.

Explains syntax differences for common SQL operations across PostgreSQL, MySQL, SQL Server, and Oracle, including auto-increment keys, string concatenation, date functions, pagination, booleans, JSON, case sensitivity, and recursive CTEs.

Perform create, read, update, and delete operations in MongoDB, covering query and update operators, atomic operations, and bulk writes.

Provisions disposable TiDB Cloud Zero databases via API and CLI, returning connection strings for immediate SQL use.

Build reactive backends with Convex: schema design, TypeScript functions, real-time subscriptions, auth, file storage, scheduling, and deployment.

Creates executable Polars dataframe contracts using Pandera's Polars backend for runtime validation of schemas, columns, and checks.

Choose between scikit-learn for predictive workflows and statsmodels for inferential modeling, with guidance on preprocessing, leakage prevention, validation, and result handoff.

Guides database design, implementation, query optimization, migrations, data pipeline development, and operations across SQL and NoSQL platforms.