schema-builder

SKILL.md

Design and generate Convex database schemas with proper validation, indexes, and relationships.

Provides schema templates and patterns for one-to-many, many-to-many, and hierarchical relationships using ID references instead of nesting

Includes validator reference for all Convex types (v.string(), v.id(), v.union(), etc.) and guidance on when to use arrays versus relational structures

Covers index strategy with single-field and compound index examples for common query patterns

Offers migration patterns for converting nested data structures to flat, relational designs following Convex best practices

Convex Schema Builder

Build well-structured Convex schemas following best practices for relationships, indexes, and validators.

When to Use

Creating a new convex/schema.ts file

Adding tables to existing schema

Designing data model relationships

Adding or optimizing indexes

Converting nested data to relational structure

Schema Design Principles

Document-Relational: Use flat documents with ID references, not deep nesting

Index Foreign Keys: Always index fields used in lookups (userId, teamId, etc.)

Limit Arrays: Only use arrays for small, bounded collections (<8192 items)

Type Safety: Use strict validators with v.* types