AI_template/.claude/skills/db-schema/SKILL.md

name, description, disable-model-invocation, argument-hint, context, agent

name	description	disable-model-invocation	argument-hint	context	agent
db-schema	Design a database schema for an entity — tables, relationships, indexes, migration, and access patterns.	true	[entity-name]	fork	backend-architect

Design Database Schema

Design the database schema for entity $ARGUMENTS.

Steps

1. Read project context first:

   • Check docs/backend/architecture.md for database conventions
   • Check RECOMMENDATIONS.md for locked ORM (Prisma/Drizzle/other)
   • Look at existing schemas/migrations in the project

2. Gather requirements — ask the user:

   • What fields does this entity need?
   • What are the relationships (belongs to, has many, many-to-many)?
   • What are the primary query patterns (list, search, filter, aggregate)?
   • Are there soft deletes, audit fields, or multi-tenancy requirements?

3. Design the schema:

   • Table definition with column types, constraints, defaults
   • Primary key strategy (UUID v7 / auto-increment / CUID)
   • Foreign keys with ON DELETE behavior
   • Indexes based on query patterns (composite where needed)
   • Unique constraints where applicable
   • Timestamps: created_at, updated_at
   • Soft delete: deleted_at if required

4. Provide deliverables:

   • Schema definition in the project's ORM format (Prisma/Drizzle/raw SQL)
   • Migration file
   • ER diagram (Mermaid) showing relationships
   • Access pattern notes (which queries this schema optimizes for)
   • Index justification (why each index exists)

5. Verify via context7 — check current ORM syntax and best practices before writing.