資料庫

Gather design feedback from AI consultants (Gemini and Codex). Use for architecture decisions, design review, or when you want multiple expert perspectives on SENTINEL development.

Use when search queries need better recall through query expansion - generates multiple query variants, retrieves with each, and fuses results using RRF for improved retrieval quality especially with ambiguous or under-specified queries

World-class data engineering skill for building scalable data pipelines, ETL/ELT systems, and data infrastructure. Expertise in Python, SQL, Spark, Airflow, dbt, Kafka, and modern data stack. Includes data modeling, pipeline orchestration, data quality, and DataOps. Use when designing data architectures, building data pipelines, optimizing data workflows, or implementing data governance.

Enterprise-grade cloud architecture expertise with production-ready patterns for AWS (Lambda 3.13, ECS/Fargate 1.4.0, RDS, CDK 2.223.0), GCP (Cloud Run Gen2, Cloud Functions 2nd gen, Cloud SQL), Azure (Functions v4, Container Apps, AKS), and multi-cloud orchestration (Terraform 1.9.8, Pulumi 3.x, Kubernetes 1.34). Covers serverless architectures, container orchestration, multi-cloud deployments, cloud-native databases, infrastructure automation, cost optimization, security patterns, and disaster recovery for 2025 stable versions.

Comprehensive database management workflow that orchestrates database architecture, schema design, performance optimization, and data governance. Handles everything from database design and implementation to performance tuning, backup strategies, and data migration.

dbt best practices for models, tests, documentation, and project organization.

Database query optimization strategies. Use when improving query performance.

Expert SQL Server / T-SQL developer for stored procedures, functions, query optimization, and database programming. Use for .sql files, stored procedures, functions, views, or when user mentions SQL Server, T-SQL, or database queries.

This skill should be used when the user asks to "detect asyncpg usage", "find asyncpg patterns", "scan for asyncpg imports", or "identify asyncpg database code in FastAPI projects". It automatically scans Python files to identify asyncpg imports, connection patterns, and query execution methods that need conversion to SQLAlchemy.

Manage PrismaClient lifecycle with graceful shutdown, proper disconnect timing, and logging configuration. Use when setting up application shutdown handlers, configuring logging for development or production, or implementing proper connection cleanup in Node.js servers, serverless functions, or test suites.

Implement comprehensive input validation on server-side with complementary client-side validation for user experience, using allowlists, type checking, and sanitization to prevent injection attacks. Use this skill when validating user inputs, form data, API requests, file uploads, query parameters, or any external data entering the application. Apply this skill when implementing server-side validation as the primary security layer, adding client-side validation for immediate user feedback, validating data types and formats, checking ranges and required fields, sanitizing inputs to prevent SQL injection and XSS attacks, using allowlists over blocklists, providing field-specific error messages, or enforcing business rules at appropriate application layers. This skill ensures validation happens at all entry points consistently, security is never dependent on client-side checks alone, users receive helpful immediate feedback, and data integrity is maintained through multiple layers of validation.

Create Mermaid diagrams for technical documentation including ERDs, sequence diagrams, flowcharts, and architecture diagrams. Use when: (1) designing database schemas (ERD), (2) documenting API interactions (sequence), (3) illustrating process flows (flowchart), (4) visualizing system architecture.

Comprehensive guide for building Next.js 15.5+ applications with Firebase, including App Router, TypeScript, MUI v7, Turbopack production builds (beta), and Firebase services. Use when configuring Next.js projects, troubleshooting errors, setting up Firebase integration, working with App Router patterns, or implementing best practices for Next.js + Firebase development.

Expert guide for Supabase integration - database schemas, RLS policies, auth, Edge Functions, and real-time subscriptions. Use when working with Supabase backend features.

Use when writing systematic review manuscript sections following PRISMA 2020 guidelines. Covers abstract, introduction, methods, results, and discussion drafting for medical journals. Invoke for academic writing assistance.

Search WaveCap transcriptions with text queries and filters. Use when the user wants to find specific transcriptions, search for keywords, or query transcription history.

This skill should be used when the user requests to scaffold, create, or initialize a full-stack Next.js application with a modern tech stack including Next.js 16, React 19, TypeScript, Tailwind CSS v4, shadcn/ui, Supabase auth, Prisma ORM, and comprehensive testing setup. Use it for creating production-ready starter templates with authentication, protected routes, forms, and example features. Trigger terms scaffold, create nextjs app, initialize fullstack, starter template, boilerplate, setup nextjs, production template, full-stack setup, nextjs supabase, nextjs prisma.

Use when working with Qdrant vector database for semantic search and RAG. Covers collection setup, embedding generation, vector upsert/search, HNSW indexing, filtering, and integration with OpenAI embeddings for textbook content retrieval.

Design and implement Next.js 15 + Supabase architecture for web-based escape room games. Handles database schema design, game engine class structure, scene transition logic, evidence discovery systems, and ending branches. Use when architecting web escape room games, designing game state management, or implementing murder mystery game mechanics with Next.js and Supabase.

Analyze and resolve Sentry comments on GitHub Pull Requests. Use this when asked to review or fix issues identified by Sentry in PR comments. Can review specific PRs by number or automatically find recent PRs with Sentry feedback.