planetscale/database-skills

Skills for AI agents working with databases

What it solves

It provides specialized database knowledge and operational guidance to AI coding assistants, helping them generate more accurate and optimized database-related code and configurations.

How it works

The project organizes database-specific expertise into "skills" (sub-directories containing instructions and reference documents). These skills can be integrated into AI tools like Cursor or via skills.sh, allowing the AI assistant to access targeted context on MySQL, Postgres, Neki, and Vitess.

Who it’s for

Developers using AI coding assistants who need expert-level guidance on schema design, query tuning, and database operations for PlanetScale products and standard database technologies.

Highlights

  • Specialized skills for MySQL/InnoDB, PostgreSQL, Neki, and Vitess.
  • Integration with Cursor plugins and skills.sh.
  • Modular structure allowing for easy addition of new database skills.
  • Covers advanced topics like sharding, MVCC/VACUUM, and online DDL.

Related

  • Project
    timescale/pg-aiguide

    A tool that provides AI coding assistants with semantic search over PostgreSQL documentation and curated best practices to improve the quality of generated database code.

  • Project
    firebase/agent-skills

    A collection of packaged instructions and scripts that extend AI coding agents' ability to understand and work with Firebase.

  • Project
    supabase/agent-skills

    A collection of standardized skill packages that provide AI agents with specialized knowledge and best practices for developing with Supabase and Postgres.

  • Project
    Kotlin/kotlin-agent-skills

    A collection of standardized AI agent skills that provide specialized instructions and resources to help AI coding agents perform Kotlin-specific development tasks.

  • Project
    OtterMind/Chat2DB

    An AI-powered database client and SQL workspace that allows users to generate, explain, and optimize SQL queries using natural language across 40+ supported databases.