資料庫

Work with the SQLite database layer including FTS5, sqlite-vec, and schema operations. Use for database queries, indexing issues, or storage debugging.

Prisma 스키마 및 마이그레이션 설정. Use when: Prisma 초기 설정 및 서비스별 스키마 구성 필요 시

Vector database configuration and setup for pgvector, Chroma, Pinecone, Weaviate, Qdrant, and FAISS with comparison guide and migration helpers

Token-efficient codebase navigation through intelligent symbol loading and querying. Use this skill when implementing new features (find existing patterns), exploring codebase structure, searching for components/functions/types, or understanding architectural layers. Reduces token usage by 60-95% compared to loading full files. Layer split enables 50-80% additional backend efficiency.

Consult Oracle knowledge base for decisions, patterns, and wisdom. Use when user asks "should I", "what's the best way", "have we done this before", "remind me about", "what's the pattern". Use PROACTIVELY before starting new work, making decisions, or when stuck. Oracle is the external brain - always consult before reinventing.

PostgreSQL patterns for reviewing migrations and writing efficient queries. Use when reviewing Alembic migrations, optimizing queries, or debugging database issues.

Review code changes using CodeRabbit CLI - supports uncommitted files (task mode) or all PR files vs main branch (pr mode). Catches bugs, security issues, and code quality problems before committing or when reviewing pull requests. Use when: (1) Reviewing uncommitted changes before committing (task mode), (2) Reviewing all changed files in a PR against main branch (pr mode), (3) Working on subtasks and want to check progress, (4) Need feedback on work-in-progress code, (5) Preparing PR for merge, (6) When CodeRabbit review is needed, (7) For bug detection and security scanning, or (8) For automated code quality assessment. Triggers: review code, check code quality, review changes, code review, review PR, check for bugs, security scan, review uncommitted, finalize code, pre-commit review.

Create multilingual glossaries for educational content, maintain terminology consistency across translations, build translation memory databases, and define preferred terms by domain and region. Use when managing translation terminology. Activates on "glossary", "terminology management", or "translation memory".

Write efficient, secure database queries using ORMs or raw SQL, preventing N+1 problems, SQL injection, and performance issues. Use this skill when writing database queries, implementing data access layers, creating repository patterns, or optimizing query performance in service files, query builders, or data access objects. Apply this skill when using parameterized queries, implementing eager loading to avoid N+1 queries, selecting only needed columns, adding WHERE/JOIN/ORDER BY clauses, or working with query optimization, indexes, and database performance tuning. This skill ensures queries use proper SQL injection prevention, implement transactions for data consistency, cache expensive queries appropriately, and follow best practices for query timeouts, connection pooling, and database resource management.

Process and implement code review feedback systematically. Use when user provides reviewer comments, PR feedback, code review notes, or asks to implement suggestions from reviews.

Use this skill whenever the user wants to set up, configure, or refactor TypeORM within a NestJS TypeScript project, including data sources, entities, migrations, repositories, relations, and transactional patterns.

Upload estimation results to Supabase storage and register with Estimator API. Final phase of the estimation workflow.

Database schema validation tools - SQL syntax checking, constraint validation, naming convention enforcement, and schema integrity verification. Use when validating database schemas, checking migrations, enforcing naming conventions, verifying constraints, or when user mentions schema validation, migration checks, database best practices, or PostgreSQL validation.

Use when building micro-interactions between 100-200ms - tooltips appearing, dropdown opens, small feedback animations that feel quick but perceptible

Templates e patterns para scripts de automação (migration, bulk processing, maintenance). TRIGGERS: 'script', 'automação', 'migration', 'bulk processing'. Use quando criar scripts para dados, database ops, content migration, automation.

Apply critic feedback to improve an engineering spec. Use when revising a spec based on review comments to address issues and improve quality scores.

Data Lake architecture and management including medallion architecture (bronze/silver/gold zones), data catalog with AWS Glue, partitioning strategies, schema evolution, data quality, governance, cost optimization, S3 lifecycle policies, data retention, compliance, query optimization with Athena, data formats (Parquet, ORC, Avro), incremental processing, CDC patterns, and production best practices for scalable data lakes.

Production-ready authentication framework for TypeScript with Cloudflare D1 support via Drizzle ORM or Kysely. Use this skill when building auth systems as a self-hosted alternative to Clerk or Auth.js, particularly for Cloudflare Workers projects. CRITICAL: better-auth requires Drizzle ORM or Kysely as database adapters - there is NO direct D1 adapter. Supports social providers (Google, GitHub, Microsoft, Apple), email/password, magic links, 2FA, passkeys, organizations, and RBAC. Prevents 12+ common authentication errors including D1 adapter misconfiguration, schema generation issues, session serialization, CORS, OAuth flows, and JWT token handling.Keywords: better-auth, authentication, cloudflare d1 auth, drizzle orm auth, kysely auth, self-hosted auth, typescript auth, clerk alternative, auth.js alternative, social login, oauth providers, session management, jwt tokens, 2fa, two-factor, passkeys, webauthn, multi-tenant auth, organizations, teams, rbac, role-based access, google auth, github auth, micros

Query real-time parking availability in Taipei City. Shows available parking spaces, capacity, status (green/available, orange/moderate, red/full), address, phone, and payment info. Supports underground/multi-level parking and street parking for cars, motorcycles, and buses. Use when user asks about parking availability, finding parking near a location, or checking parking occupancy in Taipei.

Infrastructure guidelines for A4C-AppSuite. Covers idempotent Supabase SQL migrations with RLS policies, Kubernetes deployments for Temporal workers, CQRS projections with PostgreSQL triggers, and AsyncAPI contract-first event design. Emphasizes safety, idempotency, and SQL-first development.