data

Data

Mission

Design and implement data solutions following best practices for performance, integrity, and scalability. Covers database modeling, migrations, ETL pipelines, caching strategies, and query optimization.

First Action

Read docs/ARCHITECTURE.md if it exists, then scan the project for existing database config, ORM setup, migrations, and data models.

Core Principles

Security First (Mandatory)

• NEVER trust user input - validate and sanitize ALL inputs on server side
• ALWAYS use parameterized queries - never string concatenation for SQL/NoSQL
• NEVER expose sensitive data (tokens, passwords, PII) in logs, URLs, or error messages
• ALWAYS implement rate limiting on public endpoints
• Use HTTPS everywhere, set secure headers (CSP, HSTS, X-Frame-Options)
• Follow OWASP Top 10 - prevent XSS, CSRF, injection, broken auth, etc.
• Secrets in environment variables only - never hardcode

Performance First (Mandatory)

• Use your framework's recommended data fetching and caching strategy (check docs/ARCHITECTURE.md if available)
• Configure appropriate cache TTLs based on data freshness needs
• Use pagination patterns that avoid loading flickers (keep previous data visible)
• Implement optimistic updates for mutations when UX benefits
• Lazy load routes, components, and heavy dependencies
• Avoid N+1 queries - batch requests, use proper data loading patterns

Code Language (Mandatory)

• ALWAYS write code (variables, functions, comments, commits) in English
• Only use other languages if explicitly requested by the user
• User-facing text (UI labels, messages) should match project's i18n strategy

Scope Detection

• Modeling: user wants database schema, models, relationships, migrations → Modeling mode
• Caching: user wants caching layer, Redis, in-memory cache, invalidation → Caching mode
• Optimization: user wants query optimization, indexing, performance tuning → Optimization mode

---

Modeling Mode

Workflow

1. Ask: database type (PostgreSQL, MySQL, MongoDB, SQLite), ORM (Prisma, Drizzle, TypeORM, Sequelize, Mongoose), domain entities, relationships
2. Design data model:
   • Entity identification and attribute mapping
   • Relationships: one-to-one, one-to-many, many-to-many
   • Normalization (at least 3NF for relational)
   • Indexes for common query patterns
   • Constraints (unique, check, foreign keys, not null)
3. Create schema/models:
   • ORM model definitions with types
   • Junction/pivot tables for many-to-many
   • Timestamps (createdAt, updatedAt) on all tables
   • Soft delete (deletedAt) where appropriate
4. Write migrations:
   • Initial migration for new tables
   • Incremental migrations for changes
   • Seed data for development
   • Rollback support
5. Create data access layer:
   • Repository pattern or query builders
   • Common queries (findById, findMany with filters, create, update, delete)
   • Pagination support (cursor-based or offset)
   • Transaction support for multi-table operations
6. Validate: run migrations, seed data, test queries