project-structure
关于
This skill provides comprehensive project structure guidelines and best practices for organizing codebases across various project types. It offers standardized directory patterns for monorepos, web frameworks, backend services, and libraries to ensure scalable, maintainable architecture. Use it when designing new project structures, organizing monorepo workspaces, or establishing code organization conventions for teams.
技能文档
Project Structure Guide
Monorepo
project-root/
├── src/ # All services/apps
├── infra/ # Shared infrastructure
├── docs/ # Documentation
├── .devcontainer/ # Dev Container configuration
├── .github/ # Workflows, templates
├── .vscode/ # VSCode settings
├── .claude/ # Claude settings
├── .gemini/ # Gemini settings
├── package.json # Root package.json. For releases, version management
├── go.work # Go workspace (when using Go)
├── justfile # Just task runner
├── .gitignore
├── .prettierrc
├── .prettierignore
└── README.md
NestJS
project-root/
├── src/
│ ├── domains/
│ ├── common/
│ ├── config/
│ ├── database/
│ ├── app.module.ts
│ └── main.ts
├── tests/
├── package.json
└── tsconfig.json
React
project-root/
├── src/
│ ├── pages/ # Page modules
│ ├── domains/ # Domain-shared code
│ ├── components/ # Common UI components
│ ├── layouts/ # Layout-related
│ ├── libs/ # Feature libraries (auth, api, theme)
│ ├── shared/ # Pure utilities
│ ├── app.tsx
│ └── main.tsx
├── public/
├── package.json
├── vite.config.ts
└── tsconfig.json
Next.js
project-root/
├── app/
│ ├── (routes)/ # Pages (route groups)
│ ├── actions/ # Server Actions (internal mutations)
│ └── api/ # API Routes (external integrations only)
├── components/ # Shared components
├── lib/ # Utilities and clients
├── public/ # Static assets
├── middleware.ts # Edge/Node.js middleware
├── next.config.js
├── package.json
└── tsconfig.json
Go
project-root/
├── cmd/ # Execution entry points (main.go)
├── internal/ # Private packages
├── pkg/ # Public packages
├── configs/ # Configuration files
├── scripts/ # Utility scripts
├── tests/ # Integration tests
├── docs/ # Documentation
├── go.mod
└── go.sum
NPM
project-root/
├── cli/ # CLI execution entry point
├── internal/ # Private packages
├── pkg/ # Public packages
├── configs/ # Configuration files
├── scripts/ # Utility scripts
├── tests/ # Integration tests
├── docs/ # Documentation
├── dist/ # Build artifacts
├── package.json
├── tsconfig.json
└── README.md
IDE Extension
project-root/
├── extension/ # Extension entry point (activate/deactivate)
├── internal/ # Private packages
├── pkg/ # Public packages
├── view/ # WebView (if applicable)
├── configs/ # Configuration files
├── scripts/ # Utility scripts
├── tests/ # Integration tests
├── public/ # Static resources (icons, etc.)
├── dist/ # Build artifacts
├── package.json
├── tsconfig.json
└── .vscodeignore
Chrome Extension
project-root/
├── background/ # Service Worker (Background Script)
├── content/ # Content Scripts
├── popup/ # Popup (Extension UI)
├── internal/ # Private packages
├── pkg/ # Public packages
├── configs/ # Configuration files
├── scripts/ # Utility scripts
├── tests/ # Integration tests
├── public/ # Static resources
├── dist/ # Build artifacts
├── package.json
└── tsconfig.json
快速安装
/plugin add https://github.com/KubrickCode/ai-config-toolkit/tree/main/project-structure在 Claude Code 中复制并粘贴此命令以安装该技能
GitHub 仓库
相关推荐技能
llamaguard
其他LlamaGuard是Meta推出的7-8B参数内容审核模型,专门用于过滤LLM的输入和输出内容。它能检测六大安全风险类别(暴力/仇恨、性内容、武器、违禁品、自残、犯罪计划),准确率达94-95%。开发者可通过HuggingFace、vLLM或Sagemaker快速部署,并能与NeMo Guardrails集成实现自动化安全防护。
sglang
元SGLang是一个专为LLM设计的高性能推理框架,特别适用于需要结构化输出的场景。它通过RadixAttention前缀缓存技术,在处理JSON、正则表达式、工具调用等具有重复前缀的复杂工作流时,能实现极速生成。如果你正在构建智能体或多轮对话系统,并追求远超vLLM的推理性能,SGLang是理想选择。
langchain
元LangChain是一个用于构建LLM应用程序的框架,支持智能体、链和RAG应用开发。它提供多模型提供商支持、500+工具集成、记忆管理和向量检索等核心功能。开发者可用它快速构建聊天机器人、问答系统和自主代理,适用于从原型验证到生产部署的全流程。
evaluating-llms-harness
测试该Skill通过60+个学术基准测试(如MMLU、GSM8K等)评估大语言模型质量,适用于模型对比、学术研究及训练进度追踪。它支持HuggingFace、vLLM和API接口,被EleutherAI等行业领先机构广泛采用。开发者可通过简单命令行快速对模型进行多任务批量评估。
