資料庫

Use when reviewing or editing research manuscripts, journal articles, reviews, or perspectives. Invoke when user mentions manuscript, paper draft, article, research writing, journal submission, reviewer feedback, or needs to improve scientific writing clarity, structure, or argumentation in their manuscript.

Use Codex CLI Full Auto for unattended, sandboxed prototyping and refactors.

Vector search and semantic memory backbone for agents and RAG pipelines.

Notion API for managing pages, databases, and blocks. Use this skill to create pages, query databases, search content, and build integrations with Notion workspaces.

AWS serverless and event-driven architecture expert based on Well-Architected Framework. Use when building serverless APIs, Lambda functions, REST APIs, microservices, or async workflows. Covers Lambda with TypeScript/Python, API Gateway (REST/HTTP), DynamoDB, Step Functions, EventBridge, SQS, SNS, and serverless patterns. Essential when user mentions serverless, Lambda, API Gateway, event-driven, async processing, queues, pub/sub, or wants to build scalable serverless applications with AWS best practices.

Advanced AgentDB Vector Search Implementation operates on 3 fundamental principles:

Quality gate before responding to user. Reviews proposed response against original query, checks skill usage, iterates 50% of the time for accuracy.

Automatically format code files using the appropriate formatter based on file type, providing clear feedback on changes made

State Management - React Query, Zustand, MMKV. Use when managing application state.

Master SQL and database queries across multiple systems. Generate optimized queries, analyze performance, design indexes, and troubleshoot slow queries for PostgreSQL, MySQL, MongoDB, and more.

Learning loops on top of AgentDB for reinforcement, curriculum, and replay buffers.

Implement ReasoningBank adaptive learning with AgentDBs 150x faster vector database. Includes trajectory tracking, verdict judgment, memory distillation, and pattern recognition. Use when building self-learning agents, optimizing decision-making, or implementing experience replay systems.

---

GitHub Pull Request creation specialist. Analyzes user requirements to create PRs with structured titles and bodies matching the user's query language. Handles git change analysis, PR draft creation, user confirmation, and final PR creation via gh CLI.

Secure sandbox policy design (filesystem, network, secrets, observability) with auditable guardrails for development runtimes.

Practical vector search design on AgentDB for production retrieval and RAG.

Supabase REST API via curl. Use this skill for database CRUD operations, filtering, pagination, and real-time data management.

Hashnode GraphQL API documentation for creating, managing, and querying blogs, posts, publications, and user data on the Hashnode platform

Regla 07: CQRS - Command Query Responsibility Segregation. Use when implementing DDD patterns.

Linear issue tracking API via curl. Use this skill to create, update, and query issues, projects, and teams using GraphQL.