diff --git a/README.md b/README.md index d1843da..0cbd2c2 100644 --- a/README.md +++ b/README.md @@ -1,10 +1,16 @@ -# Context Engineering Template + +> [!NOTE] +> 本文档由 WeHub 基于上游 README 翻译整理,属于社区翻译,非官方中文文档。 +> [English](./README.en.md) · [原始项目](https://github.com/coleam00/context-engineering-intro) · [上游 README](https://github.com/coleam00/context-engineering-intro/blob/HEAD/README.md) +> 原作者、版权与许可证归属以原始项目及本仓库 LICENSE 文件为准。 -A comprehensive template for getting started with Context Engineering - the discipline of engineering context for AI coding assistants so they have the information necessary to get the job done end to end. +# Context Engineering 模板 -> **Context Engineering is 10x better than prompt engineering and 100x better than vibe coding.** +这是一份用于入门 Context Engineering(上下文工程)的综合模板——这门学科致力于为大模型编程助手构建上下文,使其掌握端到端完成任务所需的信息。 -## 🚀 Quick Start +> **Context Engineering 比 prompt engineering(提示工程)好 10 倍,比 vibe coding(凭感觉写代码)好 100 倍。** + +## 🚀 快速开始 ```bash # 1. Clone this template @@ -29,40 +35,40 @@ cd Context-Engineering-Intro /execute-prp PRPs/your-feature-name.md ``` -## 📚 Table of Contents +## 📚 目录 -- [What is Context Engineering?](#what-is-context-engineering) -- [Template Structure](#template-structure) -- [Step-by-Step Guide](#step-by-step-guide) -- [Writing Effective INITIAL.md Files](#writing-effective-initialmd-files) -- [The PRP Workflow](#the-prp-workflow) -- [Using Examples Effectively](#using-examples-effectively) -- [Best Practices](#best-practices) +- [什么是 Context Engineering?](#what-is-context-engineering) +- [模板结构](#template-structure) +- [分步指南](#step-by-step-guide) +- [编写高效的 INITIAL.md 文件](#writing-effective-initialmd-files) +- [PRP 工作流](#the-prp-workflow) +- [有效使用示例](#using-examples-effectively) +- [最佳实践](#best-practices) -## What is Context Engineering? +## 什么是 Context Engineering? -Context Engineering represents a paradigm shift from traditional prompt engineering: +Context Engineering 代表了相对传统 prompt engineering 的范式转变: -### Prompt Engineering vs Context Engineering +### Prompt Engineering 与 Context Engineering 对比 -**Prompt Engineering:** -- Focuses on clever wording and specific phrasing -- Limited to how you phrase a task -- Like giving someone a sticky note +**Prompt Engineering:** +- 侧重于巧妙的措辞与具体表述 +- 仅限于你如何描述一项任务 +- 就像给别人一张便利贴 -**Context Engineering:** -- A complete system for providing comprehensive context -- Includes documentation, examples, rules, patterns, and validation -- Like writing a full screenplay with all the details +**Context Engineering:** +- 一套用于提供全面上下文的完整系统 +- 包含文档、示例、规则、模式和验证 +- 就像撰写一份细节齐全的完整剧本 -### Why Context Engineering Matters +### 为什么 Context Engineering 很重要 -1. **Reduces AI Failures**: Most agent failures aren't model failures - they're context failures -2. **Ensures Consistency**: AI follows your project patterns and conventions -3. **Enables Complex Features**: AI can handle multi-step implementations with proper context -4. **Self-Correcting**: Validation loops allow AI to fix its own mistakes +1. **减少 AI 失败**:大多数 agent 失败并非模型能力不足,而是上下文不足 +2. **确保一致性**:AI 会遵循你的项目模式与约定 +3. **支持复杂功能**:在充足上下文下,AI 可以处理多步骤实现 +4. **自我纠正**:验证循环让 AI 能够自行修复错误 -## Template Structure +## 模板结构 ``` context-engineering-intro/ @@ -82,25 +88,25 @@ context-engineering-intro/ └── README.md # This file ``` -This template doesn't focus on RAG and tools with context engineering because I have a LOT more in store for that soon. ;) +本模板暂不聚焦将 RAG 与工具纳入 context engineering,因为这方面我还有更多内容即将推出。;) -## Step-by-Step Guide +## 分步指南 -### 1. Set Up Global Rules (CLAUDE.md) +### 1. 设置全局规则(CLAUDE.md) -The `CLAUDE.md` file contains project-wide rules that the AI assistant will follow in every conversation. The template includes: +`CLAUDE.md` 文件包含 AI 助手在每次对话中都会遵循的项目级规则。模板包括: -- **Project awareness**: Reading planning docs, checking tasks -- **Code structure**: File size limits, module organization -- **Testing requirements**: Unit test patterns, coverage expectations -- **Style conventions**: Language preferences, formatting rules -- **Documentation standards**: Docstring formats, commenting practices +- **项目感知**:阅读规划文档、检查任务 +- **代码结构**:文件大小限制、模块组织 +- **测试要求**:单元测试模式、覆盖率期望 +- **风格约定**:语言偏好、格式化规则 +- **文档标准**:Docstring 格式、注释实践 -**You can use the provided template as-is or customize it for your project.** +**你可以直接使用提供的模板,也可以按项目自行定制。** -### 2. Create Your Initial Feature Request +### 2. 创建初始功能需求 -Edit `INITIAL.md` to describe what you want to build: +编辑 `INITIAL.md`,描述你想构建的内容: ```markdown ## FEATURE: @@ -116,139 +122,139 @@ Edit `INITIAL.md` to describe what you want to build: [Mention any gotchas, specific requirements, or things AI assistants commonly miss] ``` -**See `INITIAL_EXAMPLE.md` for a complete example.** +**完整示例见 `INITIAL_EXAMPLE.md`。** -### 3. Generate the PRP +### 3. 生成 PRP -PRPs (Product Requirements Prompts) are comprehensive implementation blueprints that include: +PRP(Product Requirements Prompts,产品需求提示)是包含以下内容的综合实现蓝图: -- Complete context and documentation -- Implementation steps with validation -- Error handling patterns -- Test requirements +- 完整上下文与文档 +- 带验证的实现步骤 +- 错误处理模式 +- 测试要求 -They are similar to PRDs (Product Requirements Documents) but are crafted more specifically to instruct an AI coding assistant. +它们与 PRD(Product Requirements Documents,产品需求文档)类似,但更为专门地用于指导 AI 编程助手。 -Run in Claude Code: +在 Claude Code 中运行: ```bash /generate-prp INITIAL.md ``` -**Note:** The slash commands are custom commands defined in `.claude/commands/`. You can view their implementation: -- `.claude/commands/generate-prp.md` - See how it researches and creates PRPs -- `.claude/commands/execute-prp.md` - See how it implements features from PRPs +**注意:** 这些斜杠命令是在 `.claude/commands/` 中定义的自定义命令。你可以查看其实现: +- `.claude/commands/generate-prp.md` —— 了解其如何调研并创建 PRP +- `.claude/commands/execute-prp.md` —— 了解其如何根据 PRP 实现功能 -The `$ARGUMENTS` variable in these commands receives whatever you pass after the command name (e.g., `INITIAL.md` or `PRPs/your-feature.md`). +这些命令中的 `$ARGUMENTS` 变量会接收你在命令名之后传入的参数(例如 `INITIAL.md` 或 `PRPs/your-feature.md`)。 -This command will: -1. Read your feature request -2. Research the codebase for patterns -3. Search for relevant documentation -4. Create a comprehensive PRP in `PRPs/your-feature-name.md` +该命令将: +1. 读取你的功能需求 +2. 调研代码库中的模式 +3. 搜索相关文档 +4. 在 `PRPs/your-feature-name.md` 中创建完整的 PRP -### 4. Execute the PRP +### 4. 执行 PRP -Once generated, execute the PRP to implement your feature: +生成后,执行 PRP 以实现你的功能: ```bash /execute-prp PRPs/your-feature-name.md ``` -The AI coding assistant will: -1. Read all context from the PRP -2. Create a detailed implementation plan -3. Execute each step with validation -4. Run tests and fix any issues -5. Ensure all success criteria are met +AI 编程助手将: +1. 读取 PRP 中的全部上下文 +2. 制定详细的实现计划 +3. 逐步执行并验证 +4. 运行测试并修复问题 +5. 确保满足所有成功标准 -## Writing Effective INITIAL.md Files +## 编写高效的 INITIAL.md 文件 -### Key Sections Explained +### 关键章节说明 -**FEATURE**: Be specific and comprehensive -- ❌ "Build a web scraper" -- ✅ "Build an async web scraper using BeautifulSoup that extracts product data from e-commerce sites, handles rate limiting, and stores results in PostgreSQL" +**FEATURE**:具体且全面 +- ❌ "构建一个网页爬虫" +- ✅ "构建一个使用 BeautifulSoup 的异步网页爬虫,从电商网站提取产品数据,处理速率限制,并将结果存入 PostgreSQL" -**EXAMPLES**: Leverage the examples/ folder -- Place relevant code patterns in `examples/` -- Reference specific files and patterns to follow -- Explain what aspects should be mimicked +**EXAMPLES**:善用 examples/ 文件夹 +- 将相关代码模式放入 `examples/` +- 引用应遵循的具体文件与模式 +- 说明应模仿哪些方面 -**DOCUMENTATION**: Include all relevant resources -- API documentation URLs -- Library guides -- MCP server documentation -- Database schemas +**DOCUMENTATION**:包含所有相关资源 +- API 文档 URL +- 库使用指南 +- MCP 服务器文档 +- 数据库 schema -**OTHER CONSIDERATIONS**: Capture important details -- Authentication requirements -- Rate limits or quotas -- Common pitfalls -- Performance requirements +**OTHER CONSIDERATIONS**:记录重要细节 +- 身份认证要求 +- 速率限制或配额 +- 常见陷阱 +- 性能要求 -## The PRP Workflow +## PRP 工作流 -### How /generate-prp Works +### /generate-prp 如何工作 -The command follows this process: +该命令遵循以下流程: -1. **Research Phase** - - Analyzes your codebase for patterns - - Searches for similar implementations - - Identifies conventions to follow +1. **调研阶段** + - 分析代码库中的模式 + - 搜索类似实现 + - 识别应遵循的约定 -2. **Documentation Gathering** - - Fetches relevant API docs - - Includes library documentation - - Adds gotchas and quirks +2. **文档收集** + - 获取相关 API 文档 + - 纳入库文档 + - 补充陷阱与注意事项 -3. **Blueprint Creation** - - Creates step-by-step implementation plan - - Includes validation gates - - Adds test requirements +3. **蓝图创建** + - 创建分步实现计划 + - 包含验证关卡 + - 添加测试要求 -4. **Quality Check** - - Scores confidence level (1-10) - - Ensures all context is included +4. **质量检查** + - 评估置信度(1-10) + - 确保包含全部上下文 -### How /execute-prp Works +### /execute-prp 如何工作 -1. **Load Context**: Reads the entire PRP -2. **Plan**: Creates detailed task list using TodoWrite -3. **Execute**: Implements each component -4. **Validate**: Runs tests and linting -5. **Iterate**: Fixes any issues found -6. **Complete**: Ensures all requirements met +1. **加载上下文**:读取完整 PRP +2. **规划**:使用 TodoWrite 创建详细任务列表 +3. **执行**:实现各个组件 +4. **验证**:运行测试与 lint +5. **迭代**:修复发现的问题 +6. **完成**:确保满足所有要求 -See `PRPs/EXAMPLE_multi_agent_prp.md` for a complete example of what gets generated. +生成内容的完整示例见 `PRPs/EXAMPLE_multi_agent_prp.md`。 -## Using Examples Effectively +## 有效使用示例 -The `examples/` folder is **critical** for success. AI coding assistants perform much better when they can see patterns to follow. +`examples/` 文件夹对成功**至关重要**。当 AI 编程助手能看到可遵循的模式时,表现会好得多。 -### What to Include in Examples +### 示例中应包含什么 -1. **Code Structure Patterns** - - How you organize modules - - Import conventions - - Class/function patterns +1. **代码结构模式** + - 模块组织方式 + - import 约定 + - 类/函数模式 -2. **Testing Patterns** - - Test file structure - - Mocking approaches - - Assertion styles +2. **测试模式** + - 测试文件结构 + - Mock 方法 + - 断言风格 -3. **Integration Patterns** - - API client implementations - - Database connections - - Authentication flows +3. **集成模式** + - API 客户端实现 + - 数据库连接 + - 身份认证流程 -4. **CLI Patterns** - - Argument parsing - - Output formatting - - Error handling +4. **CLI 模式** + - 参数解析 + - 输出格式化 + - 错误处理 -### Example Structure +### 示例结构 ``` examples/ @@ -263,34 +269,34 @@ examples/ └── conftest.py # Pytest configuration ``` -## Best Practices +## 最佳实践 -### 1. Be Explicit in INITIAL.md -- Don't assume the AI knows your preferences -- Include specific requirements and constraints -- Reference examples liberally +### 1. 在 INITIAL.md 中明确说明 +- 不要假设 AI 了解你的偏好 +- 包含具体的要求和约束 +- 大量引用示例 -### 2. Provide Comprehensive Examples -- More examples = better implementations -- Show both what to do AND what not to do -- Include error handling patterns +### 2. 提供全面的示例 +- 示例越多 = 实现越好 +- 同时展示该做什么和不该做什么 +- 包含错误处理模式 -### 3. Use Validation Gates -- PRPs include test commands that must pass -- AI will iterate until all validations succeed -- This ensures working code on first try +### 3. 使用验证关卡 +- PRP 包含必须通过测试命令 +- AI 会迭代直到所有验证通过 +- 这确保第一次就能得到可运行的代码 -### 4. Leverage Documentation -- Include official API docs -- Add MCP server resources -- Reference specific documentation sections +### 4. 利用文档 +- 包含官方 API 文档 +- 添加 MCP 服务器资源 +- 引用具体的文档章节 -### 5. Customize CLAUDE.md -- Add your conventions -- Include project-specific rules -- Define coding standards +### 5. 自定义 CLAUDE.md +- 添加你的约定 +- 包含项目特定规则 +- 定义编码标准 -## Resources +## 资源 -- [Claude Code Documentation](https://docs.anthropic.com/en/docs/claude-code) -- [Context Engineering Best Practices](https://www.philschmid.de/context-engineering) \ No newline at end of file +- [Claude Code 文档](https://docs.anthropic.com/en/docs/claude-code) +- [上下文工程(Context Engineering)最佳实践](https://www.philschmid.de/context-engineering)