MCPInstall

eliteforge-java-uml

根据业务需求生成可落地的 Java 25 PlantUML 类图设计,统一分层建模、关系落点、分页查询、枚举实例展示、类内说明和模块配色规则。用户提到“Java UML”“PlantUML 类图”“领域建模”“分层架构设计”“Repository 查询设计”“类图评审”时使用;优先产出 UML 文件,禁止臆造与无落点关系。

Installs
47
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/cloudsen/eliteforge-skills --skill eliteforge-java-uml
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads eliteforge-java-uml automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

EliteForge Java UML

目标

  • 生成可落地、结构清晰、边界明确、关系准确的 Java 25 UML 类设计。
  • 优先保证正确性和可实现性,宁可少画,不可错画。

Environment Variables

  • ELITEFORGE_SKILL_JAVA_UML_PLANTUML_ASL_JAR [required] Absolute path to the ASL PlantUML jar used to render and validate generated UML SVG output.

执行顺序(每次都做)

  1. 识别业务中的聚合根、核心对象、规则对象、持久化对象、查询职责组件、操作职责组件。
  2. 区分分层:基础层采用 Controller、Service、Repository、Domain、Enums、External;Service 下游可按功能类型拆分子块(如存储/规则/缓存/网关),不限制为固定单一层次。
  3. 识别闭集概念并优先建模为枚举(状态、类型、阶段、来源等)。
  4. 为每个业务模块分配颜色,同模块统一同色系,不同模块区分色系。
  5. 判断哪些对象需要审计字段,并补齐固定 6 个字段(见参考规则)。
  6. 校验每条关系是否有落点:字段或方法签名(参数/返回值)。
  7. 删除技术噪音节点:POJO 转换类(*Converter/*Assembler/*MapperStruct)与 MyBatis 技术类(*Mapper/*Example/*Criteria/SqlSession)不入图。
  8. 校验查询职责组件是否满足分页约束(queryPage 或 queryByCursor)。
  9. 校验表归属说明:关系型持久化模型的 Entity 节点必须明确写 表: xxx(复用同表可写 复用表: xxx);Repository 节点不写表归属注释。
  10. 校验 Controller 节点说明:必须标注接口前缀 接口前缀: /api/.../;职责拆分的 Controller 必须分别标注自己的前缀。
  11. 先生成并写入 .puml 文件;信息不足时先写入可确定部分,再在图内注释不确定项。
  12. 检查泛型写法:方法签名与字段类型中的泛型必须直接使用 <>;禁止出现 ~ 泛型和 &lt;/&gt; 实体。
  13. 按自检清单逐条检查后再给最终结果。

强制输出约束

  • 仅生成 PlantUML 类图文件,源文件扩展名固定为 .puml。
  • 必须先写入 UML 文件,再补充必要说明(路径/渲染结果)。
  • 禁止为了“看起来完整”而臆造类、字段、方法、关系、枚举。
  • 禁止绘制 Dto / Vo / ResVo 节点;它们只允许出现在方法签名中。
  • 禁止绘制 Page / PageResult / PageResponse 等分页容器节点。
  • 禁止体现 POJO 转换链路;禁止绘制 *Converter/*Assembler/*MapperStruct 节点和 toXxx/fromXxx 转换方法。
  • 禁止绘制 MyBatis 技术类(*Mapper/*Example/*Criteria/SqlSession)与 XML 映射细节。
  • 禁止无落点连线、禁止连线 label、禁止无必要噪音连线。
  • 列表查询必须分页;禁止 findAll / selectAll / queryAll / listAll / loadAll。
  • 关系型持久化模型的 Entity 节点说明必须标注表归属:表: xxx(可写 复用表: xxx);Repository 节点禁止标注 表: / 复用表: / 无表:。
  • Controller 节点说明必须标注接口前缀:接口前缀: /api/.../。
  • 所有节点(类/接口/枚举)必须写类内说明:<<说明标题>> + 至少 1 行说明。
  • 枚举只展示实例(常量),不展示成员变量和内部方法。
  • 方法签名与字段类型中的泛型必须直接使用 <>;禁止出现 ~ 泛型和 &lt;/&gt; 实体。
  • 颜色必须按模块划分;禁止只按技术层固定上色而忽略模块边界。
  • 不单独绘制 Persistence 层;Entity 归入 Repository 的功能子块,避免技术实现细节入图。
  • 技能运行时必须先检测 ELITEFORGE_SKILL_JAVA_UML_PLANTUML_ASL_JAR 环境变量;未设置则直接结束,并提醒用户先配置。
  • 只要新增或修改了 UML 内容,必须使用 ELITEFORGE_SKILL_JAVA_UML_PLANTUML_ASL_JAR 重新渲染成功,否则不输出最终结果。
  • 最终产物只允许输出一个 *.puml 源文件与同级 *.svg,禁止额外生成 *.plantuml。
  • 对话中不回显 UML 正文;仅返回输出文件路径、渲染结果与必要错误信息。

参考文件读取策略

  • 处理普通 UML 设计请求时,先读 references/uml-core-rules.md。
  • 用户强调布局、颜色、可读性、类内说明时,再读 references/plantuml-template.md。
  • 用户要求“给我一个可直接改的模板/示例”时,读 references/plantuml-example-template.md。
  • 用户担心渲染失败或版本兼容时,读 references/plantuml-validation.md。

输出风格基线

  • 默认使用 top to bottom direction + skinparam linetype ortho。
  • 先按模块上色,再在模块内组织分层节点;除非用户明确要求,避免使用外部 note。
  • 枚举默认不连线,减少噪音。

输出模板

@startuml
top to bottom direction
skinparam linetype ortho

' 先放分层包,再放类定义与关系
' 信息不足时,用注释列出不确定项,仍保持 PlantUML 输出

@enduml

参考资料

  • 通用 UML 规则与自检
  • PlantUML 输出模板
  • PlantUML 示例模板
  • PlantUML 版本与校验

FAQ

What does the eliteforge-java-uml skill do?

根据业务需求生成可落地的 Java 25 PlantUML 类图设计,统一分层建模、关系落点、分页查询、枚举实例展示、类内说明和模块配色规则。用户提到“Java UML”“PlantUML 类图”“领域建模”“分层架构设计”“Repository 查询设计”“类图评审”时使用;优先产出 UML 文件,禁止臆造与无落点关系。

How do I install eliteforge-java-uml?

Run npx skills add https://github.com/cloudsen/eliteforge-skills --skill eliteforge-java-uml in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/eliteforge-java-uml/ (personal) or .claude/skills/eliteforge-java-uml/ (project).

Which AI agents can use eliteforge-java-uml?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is eliteforge-java-uml safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains eliteforge-java-uml?

It is published by cloudsen in cloudsen/eliteforge-skills. It has 47 recorded installs.

More from cloudsen/eliteforge-skills

View all →

wechat-message-sender

cloudsen/eliteforge-skills

在 macOS 上通过微信桌面版向指定联系人发送文本消息。用户提供联系人名称和消息内容时使用,例如“给张三发微信:xxx”“打开微信给某人发送一句话”“用微信发送指定文本”。运行前必须已安装微信桌面版,并给当前终端或 Codex 辅助功能权限。执行时只做精确匹配:先搜索联系人,再校验当前会话标题与目标完全一致;匹配失败就停止,避免误发。

585 installs

eliteforge-framework-specification

cloudsen/eliteforge-skills

约束 Java 开发优先复用璀璨工坊统一框架能力,避免重复造轮子。基于《璀璨工坊统一框架-使用手册-nightly》提供统一框架接入、升级、配置、Starter 选型与排障指引。命中框架能力时必须使用框架内 Starter 和对应抽象 API,禁止回退到 Spring 官方 starter 或绕过框架抽象层(如缓存场景绕过 CacheService 直接用 StringRedisTemplate)。用户提到“统一框架”“starter清单”“接入步骤”“升级步骤”“系统要求”“Web MVC/服务间调用/Mybatis-Plus/加解密/缓存/多数据源/代码生成器/资源抽象层”或需要判断“该功能是否应直接使用某个 starter(如 cache-starter)”时使用。

Backend & APIs51 installs

eliteforge-task-progress-tracker

cloudsen/eliteforge-skills

Open the skill to read its SKILL.md instructions.

eliteforge-java-service-generator

cloudsen/eliteforge-skills

Generate an EliteForge Java service project via Maven archetype wrapper script. Use when users ask to scaffold a new EliteForge service, provide companyName/productName/serviceName (kebab-case), need Maven archetype generation execution, or want tech stack to enableXXX mapping.

Backend & APIs46 installs

eliteforge-frontend-generator

cloudsen/eliteforge-skills

Generate EliteForge frontend projects with the same logic as cisdigital-generator-app. Reuse the exact project type to template mapping for frontendapp/frontendui/frontendsdk, naming rules for company/product/service, and onebase-cli command assembly. Use when users ask to scaffold EliteForge frontend app projects, Vue3 component monorepo projects, JS SDK/lib projects, or request a dry-run command preview aligned with this generator. Always require user-provided required parameters and never infer missing required fields.

eliteforge-sonar-pmd-generator

cloudsen/eliteforge-skills

Transform user-provided coding specification files into a layered governance plan and validated SonarQube plugin workflow. Automatically classify each requirement into L1/L2/L3/L4, implement L1-L2 as PMD rules for supported languages, route L3 to automation tooling, route L4 to human or AI review, package rules into a custom sonar-pmd plugin, and verify with Docker Sonar + real project scans.

Popular backend & apis skills

View category →

find-skills

vercel-labs/skills

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

OfficialBackend & APIs4.1M installs

entra-app-registration

microsoft/azure-skills

Guides Microsoft Entra ID app registration, OAuth 2.0 authentication, and MSAL integration. USE FOR: create app registration, register Azure AD app, configure OAuth, set up authentication, add API permissions, generate service principal, MSAL example, console app auth, Entra ID setup, Azure AD authentication. DO NOT USE FOR: Key Vault secrets (use azure-keyvault-expiration-audit), general Azure resource security guidance.

OfficialBackend & APIs566.7K installs

This skill should be used when the user wants to "write agent code", "build an agent with ADK", "add a tool", "create a callback", "define an agent", "use state management" — in a project that needs ADK (Agent Development Kit) API patterns and code examples. It provides a quick reference for agent types, tool definitions, orchestration patterns, callbacks, state management, the graph Workflow API, and reference recipes to study. Do NOT use for scaffolding (use google-agents-cli-scaffold) or deployment (use google-agents-cli-deploy).

Backend & APIs514.8K installs

embedded-captions

heygen-com/hyperframes

Add captions or subtitles to an existing single-subject talking-head video without editing the footage. Use for plain verbatim captions, cinematic captions embedded behind the subject, VFX captions, “炸/特效/酷炫字幕,” or a named identity from the 35-style catalog. Route by visual identity, not by backend engine. The quiet anchor rail is the default; embed every word only when the user explicitly wants a fully cinematic treatment. The workflow runs locally end to end, including transcription and subject matting; split multi-shot footage before applying it.

Backend & APIs453.3K installs

entra-agent-id

microsoft/azure-skills

Provision Microsoft Entra Agent Identity Blueprints, BlueprintPrincipals, and per-instance Agent Identities via Microsoft Graph, and configure OAuth 2.0 token exchange (fmipath, OBO, cross-tenant) including the Microsoft Entra SDK for AgentID sidecar. USE FOR: Agent Identity Blueprint, BlueprintPrincipal, agent OAuth, fmipath token exchange, agent OBO, Workload Identity Federation for agents, polyglot agent auth, Microsoft.Identity.Web.AgentIdentities. DO NOT USE FOR: standard Entra app registration (use entra-app-registration), Microsoft Foundry agent authoring (use microsoft-foundry).

OfficialBackend & APIs336.6K installs

neon

neondatabase/agent-skills

Overview of Neon, a complete set of cloud backend primitives around Lakebase Postgres: Auth, Object Storage, Functions, the AI Gateway, and Realtime. Start here to choose Neon for undecided login, files, APIs, and LLM calls, set up the CLI or MCP server, and follow the branch-first workflow. Use when building an app or backend on Neon, or when "Neon" or "Lakebase Postgres" is mentioned. Child skill neon-postgres wins for an existing DATABASEURL, SQL, schema, inspect, or search. Child skill neon-auth wins for login, users, sessions, identity routing, and Managed Better Auth setup. Child skill neon-realtime wins for live queries in reactive apps and agents. Also use for object storage, S3, buckets, serverless functions, function triggers, cron, AI gateway, LLM calls, realtime, logs, Loki, Grafana, observability, postgres, database, backend, Claimable Neon, neon.new, or a no-signup database.

Backend & APIs237.1K installs