migration-skill

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Migration Skill: Cursor → Claude Code

Overview

将使用 Cursor 开发的项目平滑迁移到 Claude Code 开发模式，提取标杆项目的最佳实践，建立高度抽象的、脱离语言和框架的开发规范体系。本技能采用主控 Agent + SubAgent 的协作模式，确保迁移过程的系统性和可验证性。

核心原则：

抽象优先：提取通用的工程实践，而非具体技术栈的规范
渐进式迁移：分阶段迁移，每步都可验证
Compounding Engineering：让每次改进都成为系统永久知识
主控模式：主控 Agent 思考方案，SubAgent 执行细节，独立 Task 验证结果

Smoothly migrate projects developed with Cursor to Claude Code development mode, extract best practices from benchmark projects, and establish a highly abstract development specification system independent of languages and frameworks. This skill adopts a collaborative mode of Main Agent + SubAgent to ensure the systematicness and verifiability of the migration process.

Core Principles:

Abstraction First: Extract general engineering practices rather than specifications for specific tech stacks
Progressive Migration: Migrate in phases with verifiable results at each step
Compounding Engineering: Make every improvement a permanent part of the system's knowledge
Main Agent Mode: Main Agent designs solutions, SubAgents execute details, and independent Tasks verify results

何时使用本技能

When to Use This Skill

从 Cursor IDE 迁移到 Claude Code CLI
建立 AI Agent 友好的项目配置体系
优化现有项目的上下文工程实践
为老项目补充 AI 开发规范文档
建立项目知识库和经验沉淀机制

Migrate from Cursor IDE to Claude Code CLI
Establish an AI Agent-friendly project configuration system
Optimize context engineering practices for existing projects
Supplement AI development specification documents for legacy projects
Build a project knowledge base and experience accumulation mechanism

核心概念映射

Core Concept Mapping

Cursor 模式	Claude Code 模式	说明
`.cursorrules`	`CLAUDE.md`	Agent 配置文件
`.cursor/`	`.claude/`	配置目录
内联规则	渐进式披露	配置文件指向详细文档
单一规则文件	层次化文档体系	配置 + 规则 + 文档
隐式知识	显式知识库	AGENTS.md 经验沉淀

Cursor Mode	Claude Code Mode	Description
`.cursorrules`	`CLAUDE.md`	Agent configuration file
`.cursor/`	`.claude/`	Configuration directory
Inline Rules	Progressive Disclosure	Configuration files point to detailed documents
Single Rule File	Hierarchical Document System	Configuration + Rules + Documentation
Implicit Knowledge	Explicit Knowledge Base	Experience accumulation in AGENTS.md

迁移流程

Migration Process

Phase 1: 现状分析 (主控 Agent)

Phase 1: Current State Analysis (Main Agent)

目标：理解当前项目状态，识别迁移范围和优先级

SubAgent 任务清单：

探索项目结构

bash

Task: Explore subagent_type=Explore
探索当前项目：
- 技术栈和框架类型
- 目录结构和模块划分
- 现有的配置文件（.cursorrules, .cursor/ 等）
- 文档体系完整性
返回：项目结构报告和现有配置清单

分析现有规范

bash

Task: Explore subagent_type=Explore
分析现有开发规范：
- 代码风格规则
- 架构模式和约定
- 测试策略
- Git 工作流
返回：现有规范摘要和改进建议

识别知识孤岛

bash

Task: Grep pattern="TODO|FIXME|HACK|NOTE"
搜索代码中的隐性知识：
- 注释中的临时方案
- 需要文档化的陷阱
- 团队约定（命名、模式等）
返回：隐性知识清单和分类

主控决策点：

确定迁移优先级（配置 → 规则 → 文档）
识别必须保留的领域知识
规划文档层次结构

Objective: Understand the current project status, identify migration scope and priorities

SubAgent Task List:

Explore Project Structure

bash

Task: Explore subagent_type=Explore
Explore the current project:
- Tech stack and framework types
- Directory structure and module division
- Existing configuration files (.cursorrules, .cursor/, etc.)
- Completeness of documentation system
Return: Project structure report and existing configuration list

Analyze Existing Specifications

bash

Task: Explore subagent_type=Explore
Analyze existing development specifications:
- Code style rules
- Architecture patterns and conventions
- Testing strategies
- Git workflows
Return: Summary of existing specifications and improvement suggestions

Identify Knowledge Silos

bash

Task: Grep pattern="TODO|FIXME|HACK|NOTE"
Extract implicit knowledge from code:
- Temporary solutions in comments
- Pitfalls requiring documentation
- Team conventions (naming, patterns, etc.)
Return: Implicit knowledge list and classification

Main Agent Decision Points:

Determine migration priorities (Configuration → Rules → Documentation)
Identify domain knowledge that must be retained
Plan document hierarchy

Phase 2: 配置文件迁移 (主控 Agent + SubAgent)

Phase 2: Configuration File Migration (Main Agent + SubAgent)

目标：建立 AI Agent 配置文件体系（WHAT/WHY/HOW）

SubAgent 任务清单：

创建 CLAUDE.md（索引文件，< 500 行）

Task: Write file CLAUDE.md
内容结构：
## 项目概述 (WHAT)
- 技术栈：[框架] + [语言] + [数据库] + [其他关键依赖]
- 关键目录：src/, tests/, docs/ 等的职责说明

## 核心架构决策 (WHY)
- 为什么选择这个架构？
- 哪些是历史债务？
- 哪些设计决策需要 Agent 遵守？

## 开发工作流 (HOW)
- 如何运行项目？
- 如何测试？
- 如何验证改动？

## 核心约束 (5-10 条)
- 最关键的规则（带 CRITICAL 标记）
- 每条规则指向详细文档

## 详细文档索引
- 按主题分类的文档链接

迁移现有规则

Task: Edit/Migrate
将 .cursorrules 内容迁移到：
- CLAUDE.md（简述）
- rules/（详细文档）
- agent_docs/（技术文档）
遵循渐进式披露原则

创建规则文档

Task: Write files in rules/
为每条核心规则创建独立文档：
- 规则名称.md
- 问题描述和重要性
- 正反例对比
- 常见错误
- 参考代码（使用 file:line 引用）

验证任务：

bash

Task: General-purpose
验证配置迁移质量：
- CLAUDE.md 行数 < 500
- 所有规则都有详细文档
- 文档间引用正确
- 运行时无配置错误

Objective: Establish an AI Agent configuration file system (WHAT/WHY/HOW)

SubAgent Task List:

Create CLAUDE.md (Index file, < 500 lines)

Task: Write file CLAUDE.md
Content structure:
## Project Overview (WHAT)
- Tech stack: [Framework] + [Language] + [Database] + [Other key dependencies]
- Key directories: Responsibilities of src/, tests/, docs/, etc.

## Core Architecture Decisions (WHY)
- Why was this architecture chosen?
- What are the technical debts?
- Which design decisions must Agents follow?

## Development Workflow (HOW)
- How to run the project?
- How to test?
- How to verify changes?

## Core Constraints (5-10 items)
- Most critical rules (marked with CRITICAL)
- Each rule links to detailed documentation

## Detailed Document Index
- Themed document links

Migrate Existing Rules

Task: Edit/Migrate
Migrate .cursorrules content to:
- CLAUDE.md (brief description)
- rules/ (detailed documentation)
- agent_docs/ (technical documentation)
Follow the principle of progressive disclosure

Create Rule Documents

Task: Write files in rules/
Create independent documents for each core rule:
- rule-name.md
- Problem description and importance
- Comparison of correct and incorrect examples
- Common mistakes
- Reference code (using file:line references)

Verification Task:

bash

Task: General-purpose
Verify configuration migration quality:
- CLAUDE.md has < 500 lines
- All rules have detailed documentation
- Cross-document references are correct
- No configuration errors during runtime

Phase 3: 经验沉淀系统 (主控 Agent + SubAgent)

Phase 3: Experience Accumulation System (Main Agent + SubAgent)

目标：建立 AGENTS.md，实现 Compounding Engineering

SubAgent 任务清单：

创建 AGENTS.md

Task: Write file AGENTS.md
内容结构：
## 代码风格
- 命名约定
- 导入顺序
- 语言特性偏好

## 已知陷阱
- 常见错误模式
- 必须避免的做法
- 框架特定陷阱

## 成功模式
- 标准工作流
- 可复用模板
- 最佳实践示例

## 复利效应实践
- Bug 修复后的改进清单
- 代码审查后的规范更新

挖掘隐性知识

Task: Grep + Read
从代码历史和注释中提取：
- Git commit 历史中的修复记录
- 代码审查中的常见问题
- 注释中的"为什么"
- 团队约定和模式
分类整理到 AGENTS.md

验证任务：

bash

Task: General-purpose
验证经验沉淀质量：
- AGENTS.md 覆盖主要陷阱
- 每个陷阱有具体代码示例
- 成功模式可操作
- 复利效应清单完整

Objective: Establish AGENTS.md to implement Compounding Engineering

SubAgent Task List:

Create AGENTS.md

Task: Write file AGENTS.md
Content structure:
## Code Style
- Naming conventions
- Import order
- Language feature preferences

## Known Pitfalls
- Common error patterns
- Practices to avoid
- Framework-specific pitfalls

## Success Patterns
- Standard workflows
- Reusable templates
- Best practice examples

## Compounding Engineering Practices
- Improvement checklist after bug fixes
- Specification updates after code reviews

Mine Implicit Knowledge

Task: Grep + Read
Extract from code history and comments:
- Fix records in Git commit history
- Common issues in code reviews
- "Why" explanations in comments
- Team conventions and patterns
Classify and organize into AGENTS.md

Verification Task:

bash

Task: General-purpose
Verify experience accumulation quality:
- AGENTS.md covers major pitfalls
- Each pitfall has specific code examples
- Success patterns are actionable
- Compounding engineering checklist is complete

Phase 4: 文档体系完善 (主控 Agent + SubAgent)

Phase 4: Documentation System Improvement (Main Agent + SubAgent)

目标：建立层次化、渐进式披露的文档体系

文档结构：

agent_docs/
├── architecture/          # 架构文档
│   ├── overview.md        # 系统架构概览
│   ├── modules.md         # 模块划分和职责
│   └── decisions.md       # 架构决策记录 (ADR)
├── workflows/             # 工作流程
│   ├── development.md     # 开发流程
│   ├── testing.md         # 测试流程
│   └── deployment.md      # 部署流程
├── troubleshooting.md     # 故障排除
└── api/                   # API 文档（如需要）
    └── README.md

rules/
├── rule-1.md              # 核心规则详细说明
├── rule-2.md
└── ...

SubAgent 任务清单：

创建架构文档

Task: Write + Explore
生成架构文档：
- 系统层次结构
- 模块依赖关系
- 数据流图
- 技术选型理由

创建工作流文档

Task: Write
标准化工作流程：
- 添加新功能流程
- Bug 修复流程
- 代码审查流程
- 发布流程

创建故障排除指南

Task: Write
常见问题解决：
- 环境配置问题
- 依赖问题
- 性能问题
- 调试技巧

Objective: Build a hierarchical, progressive disclosure documentation system

Document Structure:

agent_docs/
├── architecture/          # Architecture documentation
│   ├── overview.md        # System architecture overview
│   ├── modules.md         # Module division and responsibilities
│   └── decisions.md       # Architecture decision records (ADR)
├── workflows/             # Workflows
│   ├── development.md     # Development process
│   ├── testing.md         # Testing process
│   └── deployment.md      # Deployment process
├── troubleshooting.md     # Troubleshooting guide
└── api/                   # API documentation (if needed)
    └── README.md

rules/
├── rule-1.md              # Detailed explanation of core rules
├── rule-2.md
└── ...

SubAgent Task List:

Create Architecture Documentation

Task: Write + Explore
Generate architecture documentation:
- System hierarchy
- Module dependencies
- Data flow diagrams
- Reasons for technology selection

Create Workflow Documentation

Task: Write
Standardize workflows:
- New feature addition process
- Bug fix process
- Code review process
- Release process

Create Troubleshooting Guide

Task: Write
Resolve common issues:
- Environment configuration problems
- Dependency issues
- Performance issues
- Debugging techniques

Phase 5: 上下文工程优化 (主控 Agent + SubAgent)

Phase 5: Context Engineering Optimization (Main Agent + SubAgent)

目标：应用最佳实践，优化上下文管理

核心原则（来自上下文工程最佳实践）：

配置文件精简原则

Task: Edit CLAUDE.md
确保配置文件：
- 行数 < 500（越短越好）
- 只包含普遍适用的内容
- 详细内容指向独立文档
- 避免代码风格指南（交给 linter）

渐进式披露

Task: Reorganize docs/
实现三级加载：
1. CLAUDE.md（元数据，自动加载）
2. rules/（规则详细说明，按需加载）
3. agent_docs/（技术文档，深度查阅）

指针优于副本

Task: Edit all .md files
统一使用 file:line 引用：
- 不复制代码片段
- 使用 "详见 src/module/file.ts:123"
- 保持文档与代码同步

200K Token 足够了

主控 Agent 策略：
- 单对话 < 100K token 时继续
- 完成子任务后开新对话
- Agent 出现"醉酒"症状时重置
- 把"开新对话"视为正常工作流

Objective: Apply best practices to optimize context management

Core Principles (from Context Engineering Best Practices):

Configuration File Simplification Principle

Task: Edit CLAUDE.md
Ensure configuration files:
- Have < 500 lines (the shorter the better)
- Only contain universally applicable content
- Detailed content links to independent documents
- Avoid code style guidelines (leave to linters)

Progressive Disclosure

Task: Reorganize docs/
Implement three-level loading:
1. CLAUDE.md (metadata, automatically loaded)
2. rules/ (detailed rule explanations, loaded on demand)
3. agent_docs/ (technical documentation, for in-depth reference)

Pointers Over Copies

Task: Edit all .md files
Uniformly use file:line references:
- Do not copy code snippets
- Use "See src/module/file.ts:123"
- Keep documentation synchronized with code

200K Tokens Are Sufficient

Main Agent Strategy:
- Continue when single conversation < 100K tokens
- Start new conversations after completing subtasks
- Reset when Agent shows "drunk" symptoms
- Treat "starting new conversations" as normal workflow

Phase 6: 复利工程机制 (主控 Agent + SubAgent)

Phase 6: Compounding Engineering Mechanism (Main Agent + SubAgent)

目标：建立持续改进的知识系统

SubAgent 任务清单：

建立 Git Hooks 集成

Task: Write scripts/
创建自动化脚本：
- pre-commit: 检查文档更新
- commit-msg: 验证提交格式
- post-merge: 提醒更新文档

创建改进模板

Task: Write templates/
标准化改进流程：
- Bug 修复报告模板
- 代码审查反馈模板
- 新规范提案模板

文档更新检查清单

Task: Write CHECKLIST.md
每次改动后检查：
- [ ] 是否发现新陷阱？
- [ ] 是否总结新模式？
- [ ] 是否需要更新规范？
- [ ] 是否添加测试防止回归？

Objective: Build a continuous improvement knowledge system

SubAgent Task List:

Establish Git Hooks Integration

Task: Write scripts/
Create automation scripts:
- pre-commit: Check document updates
- commit-msg: Verify commit message format
- post-merge: Remind to update documents

Create Improvement Templates

Task: Write templates/
Standardize improvement processes:
- Bug fix report template
- Code review feedback template
- New specification proposal template

Document Update Checklist

Task: Write CHECKLIST.md
Check after each change:
- [ ] Have new pitfalls been discovered?
- [ ] Have new patterns been summarized?
- [ ] Do specifications need to be updated?
- [ ] Have tests been added to prevent regression?

通用最佳实践（脱离技术栈）

Universal Best Practices (Tech Stack Independent)

1. 文档编写原则

1. Documentation Writing Principles

WHAT（是什么）：

技术栈和工具
目录结构和职责
核心概念和术语

WHY（为什么）：

架构决策背景
历史债务说明
设计权衡考量

HOW（怎么做）：

运行和测试命令
开发工作流程
问题排查方法

WHAT (What it is):

Tech stack and tools
Directory structure and responsibilities
Core concepts and terminology

WHY (Why it matters):

Background of architecture decisions
Explanation of technical debts
Design tradeoff considerations

HOW (How to implement):

Run and test commands
Development workflows
Troubleshooting methods

2. 规则定义模式

2. Rule Definition Pattern

每条规则包含：

undefined

Each rule includes:

undefined

规则 N: [规则名称] [优先级]

Rule N: [Rule Name] [Priority]

问题描述：为什么需要这条规则？

正确做法 (✅)： [代码示例]

错误做法 (❌)： [代码示例]

常见错误：

[错误1]
[错误2]

参考文档：

详细说明：rules/rule-name.md
示例代码：src/module/file.ts:123

undefined

Problem Description: Why is this rule needed?

Correct Practice (✅): [Code Example]

Incorrect Practice (❌): [Code Example]

Common Mistakes:

[Mistake 1]
[Mistake 2]

Reference Documentation:

Detailed explanation: rules/rule-name.md
Example code: src/module/file.ts:123

undefined

3. 经验沉淀结构

3. Experience Accumulation Structure

undefined

undefined

代码风格

Code Style

语言特性偏好
命名和格式约定

Language feature preferences
Naming and formatting conventions

已知陷阱

Known Pitfalls

框架特定陷阱
常见错误模式
必须避免的做法

Framework-specific pitfalls
Common error patterns
Practices to avoid

成功模式

Success Patterns

标准工作流
可复用模板
最佳实践示例

Standard workflows
Reusable templates
Best practice examples

复利效应

Compounding Engineering

Bug 修复 → 规范更新
代码审查 → 模式提取
经验 → 永久知识

undefined

Bug fixes → Specification updates
Code reviews → Pattern extraction
Experience → Permanent knowledge

undefined

4. 上下文管理策略

4. Context Management Strategy

配置文件（CLAUDE.md）：

索引性质，< 500 行
只包含普遍适用的约束
详细内容指向文档
避免：代码风格、过度规范

规则文档（rules/）：

每条规则独立文档
正反例对比
常见错误和解决方案
指向代码实现

技术文档（agent_docs/）：

架构和设计文档
工作流程指南
故障排除手册
API 参考手册

Configuration File (CLAUDE.md):

Index nature, < 500 lines
Only contains universally applicable constraints
Detailed content links to documents
Avoid: Code style, over-specification

Rule Documents (rules/):

Independent document for each rule
Comparison of correct and incorrect examples
Common mistakes and solutions
Links to code implementations

Technical Documentation (agent_docs/):

Architecture and design documents
Workflow guides
Troubleshooting manuals
API reference manuals

主控 Agent 工作模式

Main Agent Working Mode

角色定义

Role Definitions

主控 Agent（你）：

思考需求和落地方案
拆分任务并指挥 SubAgent
不执行细节操作
开启独立 Task 验证结果

SubAgent（Task 工具）：

执行具体操作
搜集信息和分析
按指令完成任务
返回结果报告

验证 Task（独立 General-purpose Agent）：

检查实现质量
发现异常并更正
确保符合规范
提供改进建议

Main Agent (You):

Think about requirements and implementation plans
Split tasks and direct SubAgents
Do not perform detailed operations
Initiate independent Tasks to verify results

SubAgent (Task Tool):

Execute specific operations
Collect information and analyze
Complete tasks as instructed
Return result reports

Verification Task (Independent General-purpose Agent):

Check implementation quality
Discover anomalies and correct them
Ensure compliance with specifications
Provide improvement suggestions

工作流程

Workflow

1. 主控 Agent 思考需求
   ↓
2. 拆分为 SubAgent 任务
   ↓
3. 并行执行多个 Task
   ↓
4. 汇总结果并分析
   ↓
5. 开启验证 Task 检查
   ↓
6. 根据反馈调整
   ↓
7. 继续下一阶段

1. Main Agent analyzes requirements
   ↓
2. Split into SubAgent tasks
   ↓
3. Execute multiple Tasks in parallel
   ↓
4. Summarize and analyze results
   ↓
5. Initiate Verification Task for inspection
   ↓
6. Adjust based on feedback
   ↓
7. Proceed to the next phase

执行原则

Execution Principles

主控 Agent：

✅ 思考"为什么"和"怎么做"
✅ 规划迁移路径
✅ 识别风险和依赖
✅ 评估优先级
❌ 不直接编辑文件
❌ 不执行细节任务
❌ 不运行命令

SubAgent：

✅ 执行具体操作
✅ 搜集和分析信息
✅ 按指令完成任务
❌ 不做决策
❌ 不改变计划

验证 Task：

✅ 独立验证结果
✅ 发现潜在问题
✅ 提供改进建议
✅ 确保质量标准

Main Agent:

✅ Think about "why" and "how"
✅ Plan migration paths
✅ Identify risks and dependencies
✅ Evaluate priorities
❌ Do not directly edit files
❌ Do not perform detailed tasks
❌ Do not run commands

SubAgent:

✅ Execute specific operations
✅ Collect and analyze information
✅ Complete tasks as instructed
❌ Do not make decisions
❌ Do not change plans

Verification Task:

✅ Independently verify results
✅ Discover potential issues
✅ Provide improvement suggestions
✅ Ensure quality standards

验证和测试

Verification and Testing

每阶段验证清单

Per-phase Verification Checklist

整体验证

Overall Verification

bash

Task: General-purpose
最终验证：
1. 文档结构完整性
   - CLAUDE.md, AGENTS.md 存在
   - rules/ 和 agent_docs/ 组织合理
   - 所有引用可访问

2. 内容质量检查
   - 规则有正反例
   - 陷阱有具体代码
   - 工作流可操作

3. 实用性验证
   - 新开发者能快速上手
   - Agent 能理解规范
   - 知识可复用

4. 复利效应验证
   - Bug 修复流程包含文档更新
   - 代码审查包含规范提取
   - 经验有沉淀机制

bash

Task: General-purpose
Final Verification:
1. Documentation structure completeness
   - CLAUDE.md and AGENTS.md exist
   - rules/ and agent_docs/ are well-organized
   - All references are accessible

2. Content quality check
   - Rules have correct and incorrect examples
   - Pitfalls have specific code examples
   - Workflows are actionable

3. Practicality verification
   - New developers can get started quickly
   - Agents can understand specifications
   - Knowledge is reusable

4. Compounding engineering verification
   - Bug fix process includes document updates
   - Code reviews include specification extraction
   - Experience accumulation mechanism exists

常见问题

Frequently Asked Questions

Q1: 配置文件应该多长？

Q1: How long should configuration files be?

A: CLAUDE.md 应控制在 500 行以内，越短越好。只保留普遍适用的内容，详细说明放在 rules/ 和 agent_docs/。

A: CLAUDE.md should be kept under 500 lines, the shorter the better. Only retain universally applicable content, with detailed explanations in rules/ and agent_docs/.

Q2: 如何平衡详细和简洁？

Q2: How to balance detail and conciseness?

A: 使用渐进式披露：

CLAUDE.md：索引和摘要
rules/：规则详细说明
agent_docs/：深度技术文档

A: Use progressive disclosure:

CLAUDE.md: Index and summary
rules/: Detailed rule explanations
agent_docs/: In-depth technical documentation

Q3: 是否需要代码风格指南？

Q3: Are code style guidelines needed?

A: 不建议。交给 linter 和 formatter（ESLint, Prettier, Biome）。LLM 做格式检查既慢又贵，而且会降低对其他指令的遵循能力。

A: Not recommended. Leave this to linters and formatters (ESLint, Prettier, Biome). LLMs are slow and expensive for format checks, and it reduces their ability to follow other instructions.

Q4: 如何防止文档过时？

Q4: How to prevent documentation from becoming outdated?

使用 file:line 引用而非代码副本
建立 Git Hooks 提醒更新
代码审查时检查文档一致性
定期运行验证脚本

Use file:line references instead of code copies
Set up Git Hooks to remind document updates
Check document consistency during code reviews
Run verification scripts regularly

Q5: 如何处理技术栈特定内容？

Q5: How to handle tech stack-specific content?

A: 保持抽象原则，提取通用实践：

❌ "如何使用 Prisma"
✅ "ORM 使用规范：单例模式、事务边界、连接管理"

A: Adhere to the abstraction principle and extract general practices:

❌ "How to use Prisma"
✅ "ORM Usage Specifications: Singleton Pattern, Transaction Boundaries, Connection Management"

Q6: 迁移需要多长时间？

Q6: How long does migration take?

A: 分阶段进行：

Phase 1-2（配置迁移）：2-4 小时
Phase 3-4（文档完善）：1-2 天
Phase 5-6（优化机制）：持续进行

建议先完成 Phase 1-2，让 Agent 开始工作，再逐步完善。

A: Conduct in phases:

Phase 1-2 (Configuration Migration): 2-4 hours
Phase 3-4 (Documentation Improvement): 1-2 days
Phase 5-6 (Optimization Mechanism): Ongoing

It is recommended to complete Phase 1-2 first to enable Agents to start working, then gradually improve the rest.

Resources

可复用的配置模板

Reusable Configuration Templates

assets/ 目录包含：

```
CLAUDE.md.template
```
- 配置文件模板
```
AGENTS.md.template
```
- 经验沉淀模板
```
rules/
```
- 规则文档模板
```
agent_docs/
```
- 技术文档模板

The assets/ directory contains:

```
CLAUDE.md.template
```
- Configuration file template
```
AGENTS.md.template
```
- Experience accumulation template
```
rules/
```
- Rule document templates
```
agent_docs/
```
- Technical document templates

参考文档

Reference Documentation

references/ 目录包含：

```
context-engineering-best-practices.md
```
- 上下文工程最佳实践
```
compounding-engineering.md
```
- 复利工程指南
```
documentation-structure.md
```
- 文档结构规范

The references/ directory contains:

```
context-engineering-best-practices.md
```
- Context Engineering Best Practices
```
compounding-engineering.md
```
- Compounding Engineering Guide
```
documentation-structure.md
```
- Documentation Structure Specifications

执行脚本

Execution Scripts

scripts/ 目录包含：

```
analyze_project.py
```
- 项目分析脚本
```
validate_migration.py
```
- 迁移验证脚本
```
check_docs_consistency.py
```
- 文档一致性检查

The scripts/ directory contains:

```
analyze_project.py
```
- Project analysis script
```
validate_migration.py
```
- Migration verification script
```
check_docs_consistency.py
```
- Document consistency check script