microwind

以聚合根为边界，包含多个相关Entity和ValueObject的集合。保证数据一致性和事务边界。

在DDD中具有唯一身份标识和生命周期的对象，通过身份而非属性值相等判断。

封装复杂对象和聚合的创建过程，将创建职责从领域对象中剥离，保证聚合创建时的不变量满足。

没有身份标识，通过属性值判断相等的对象。不可变，通常代表领域中的度量或描述。

命令查询责任分离，将数据的写入操作和读取操作分别用不同的模型处理，优化各自的性能。

将DDD战略设计应用于微服务架构，限界上下文指导服务拆分，领域事件实现服务间通信。

对比 MVC 模式与 DDD 方法论的差异，分析 MVC 在复杂业务下的局限性，帮助团队判断何时应采用 DDD。

以领域层为核心的应用分层架构，分为接口门面层、应用层、领域层、仓储层、基础设施层，保证高内聚低耦合和业务逻辑稳定。

Bootstrap and standardize Spring Boot 4.0.3 + Spring AI backend projects for new implementations. Use when Codex needs to initialize a project, set Maven dependencies/BOM, define package and module layout, configure environment profiles, or create baseline API/AI/database scaffolding.

Build a movie-poster one-line recommendation pipeline that takes movie title and description, gathers context from Douban and encyclopedia pages, and generates 3-5 Chinese recommendation lines with exactly 12 Chinese characters each. Use when Codex needs to implement crawler-to-prompt workflows, output validation, and recommendation generation APIs.

Build RAG pipelines for media-asset knowledge bases using Spring AI and PostgreSQL pgvector. Use when Codex needs to design database schema, ingestion/chunking/embedding workflow, and retrieval logic that prioritizes internal media knowledge before falling back to general model knowledge.

Generate structured A-share market commentary for three fixed trading sessions using supplied market data: within 30 minutes after market open, after midday close, and after market close. Use this skill when the user wants factual market observation, intraday commentary, or end-of-day review content based on real A-share inputs. Do not use it for stock picking, trading advice, or fabricated commentary without data.