- 新增文档模板和导航结构 - 实现服务器基础API路由和控制器 - 添加扩展插件配置和前端框架 - 引入多租户和权限管理模块 - 集成日志和数据库配置 - 添加核心业务模型和类型定义
12 KiB
我先给你一份比较完整的模板,然后再告诉你 还有哪些文件能进一步优化 AI 编程体验。
PROJECT_MAP.md
Project Map
This document provides a high-level map of the entire repository.
It is intended for both developers and AI systems to quickly understand the project structure.
1. Project Overview
Project Name: <PROJECT_NAME>
Purpose:
Describe the main goal of this project.
Example:
- Web backend service
- AI processing pipeline
- SaaS platform
Primary technologies:
- Language: <Python / Node / Go / etc>
- Framework: <FastAPI / Express / Spring / etc>
- Database: <PostgreSQL / MongoDB>
2. Repository Structure
Top-level structure:
project
├─ api
├─ service
├─ repository
├─ models
├─ utils
├─ config
├─ tests
└─ scripts
3. Key Modules
api
Handles external requests.
Responsibilities:
- routing
- validation
- response formatting
service
Contains core business logic.
Responsibilities:
- orchestration
- domain rules
- transaction control
repository
Handles data persistence.
Responsibilities:
- database queries
- ORM interactions
- caching layer
models
Defines domain entities.
Examples:
- User
- Order
- Session
utils
Shared helper functions.
Examples:
- date helpers
- logging
- validation utilities
4. Request Flow
Typical request lifecycle:
Client
↓
API Layer
↓
Service Layer
↓
Repository Layer
↓
Database
5. Important Entry Points
Main entry points:
main.py
app.ts
server.go
Startup flow:
- load configuration
- initialize services
- register routes
- start server
6. Configuration
Configuration files are located in:
config/
Types:
- environment variables
- database configuration
- feature flags
7. Testing Strategy
Tests are located in:
tests/
Structure mirrors source code.
Example:
service/user_service.py
tests/service/test_user_service.py
8. Coding Rules
See:
project_rules.md
9. Dependency Rules
See:
DEPENDENCY_MAP.md
10. AI Notes
Guidelines for AI tools:
- Keep files under 2000 lines
- Avoid circular dependencies
- Follow modular architecture
- Prefer small reusable functions
除了这些文件,还有哪些 AI 项目文件?
完整的 AI-native 项目结构通常会有这些:
AI_CONTEXT.md
PROJECT_MAP.md
MODULE_INDEX.md
DEPENDENCY_MAP.md
project_rules.md
但实际上还可以再加几个更高级的。
1️⃣ CODE_STYLE.md
专门给 AI 的代码风格。
例如:
indent: 4 spaces
naming: snake_case
class naming: PascalCase
error handling: explicit
AI生成代码会更一致。
2️⃣ API_MAP.md
如果项目有 API。
例如:
GET /users
POST /login
DELETE /session
AI可以直接知道接口结构。
3️⃣ DATA_SCHEMA.md
数据库结构说明。
例如:
User
- id
- email
- password_hash
AI生成 SQL / ORM 会更准。
4️⃣ WORKFLOW.md
业务流程。
例如:
user register
↓
email verification
↓
account activation
AI理解业务逻辑会更快。
最完整的 AI 项目结构(推荐)
project
├─ api
├─ service
├─ repository
├─ models
├─ utils
├─ tests
├─ project_rules.md
├─ PROJECT_MAP.md
├─ AI_CONTEXT.md
├─ MODULE_INDEX.md
├─ DEPENDENCY_MAP.md
├─ CODE_STYLE.md
├─ API_MAP.md
└─ DATA_SCHEMA.md
一个很多人不知道的关键点
真正提升 AI 理解能力最大的文件其实不是这些,而是:
REPO_PROMPT.md
这是 专门给 AI 的系统提示词,告诉 AI:
- 如何修改代码
- 如何写模块
- 如何重构项目
下面是一套 “AI 时代项目模板仓库结构(2026版)”。 目标:让 AI IDE、代码助手和人类开发者都能快速理解、导航和重构项目。
一、完整仓库结构(推荐模板)
project
├─ api/ # 外部接口层(HTTP / RPC / CLI)
│
├─ service/ # 核心业务逻辑
│
├─ repository/ # 数据访问层
│
├─ models/ # 数据模型 / schema
│
├─ components/ # 可复用组件(前端或服务模块)
│
├─ utils/ # 工具函数
│
├─ config/ # 配置文件
│
├─ scripts/ # 自动化脚本
│
├─ tests/ # 单元测试
│
├─ docs/ # 人类文档
│
├─ prompts/ # AI Prompt 模板
│
├─ embeddings/ # 向量索引配置
│
├─ project_rules.md
├─ AI_CONTEXT.md
├─ PROJECT_MAP.md
├─ MODULE_INDEX.md
├─ DEPENDENCY_MAP.md
├─ CODE_STYLE.md
├─ API_MAP.md
├─ DATA_SCHEMA.md
├─ WORKFLOW.md
├─ REPO_PROMPT.md
├─ README.md
└─ CHANGELOG.md
二、AI核心文件(最关键)
这些是 AI理解项目的核心入口。
1️⃣ AI_CONTEXT.md
作用:
- 项目总体介绍
- 技术栈
- 架构思想
AI第一时间读取。
2️⃣ PROJECT_MAP.md
作用:
- 仓库结构地图
- 入口文件
- 模块概览
让AI快速定位代码。
3️⃣ MODULE_INDEX.md
作用:
说明每个模块职责:
api → 接口
service → 业务逻辑
repository → 数据访问
4️⃣ DEPENDENCY_MAP.md
定义 依赖规则:
api → service
service → repository
repository → models
避免循环依赖。
5️⃣ project_rules.md
代码规范:
- 文件大小
- 模块拆分
- 命名规则
三、AI增强文件(提升 AI 代码能力)
CODE_STYLE.md
代码风格:
indent: 4 spaces
naming: snake_case
classes: PascalCase
comments: concise
AI生成代码更统一。
REPO_PROMPT.md
最重要的 AI 提示词文件。
告诉 AI:
如何修改代码
如何重构
如何写模块
例如:
When modifying code:
- preserve architecture layers
- avoid circular dependencies
- keep files under 2000 lines
prompts/
存放 AI prompt 模板:
prompts/
refactor.md
bugfix.md
feature.md
四、业务理解文件
这些帮助 AI 理解业务逻辑。
API_MAP.md
GET /users
POST /login
DELETE /session
DATA_SCHEMA.md
数据库结构:
User
- id
- email
- password_hash
WORKFLOW.md
业务流程:
register
↓
email verification
↓
account activation
五、代码目录规范
推荐代码目录:
api/
user_controller
auth_controller
service/
user_service
auth_service
repository/
user_repository
调用链:
API
↓
Service
↓
Repository
↓
Database
六、AI检索优化目录
为了让 AI IDE 更好检索代码:
embeddings/
存储:
- 向量索引
- 代码摘要
一些 AI 工具会自动生成。
七、docs目录
给人类开发者:
docs/
architecture.md
deployment.md
dev_setup.md
八、文件大小建议
AI-friendly 项目规则:
单文件 ≤ 2000 行
函数 ≤ 100 行
模块 ≤ 10 文件
九、典型调用链
Client
↓
API
↓
Service
↓
Repository
↓
Database
AI最容易理解这种结构。
十、为什么这个结构重要
这种仓库结构可以:
- 降低 AI 上下文需求
- 提升代码生成质量
- 提升自动重构能力
- 提升项目可维护性
很多开发者用这种结构后:
7B–13B 模型
就能处理 大型项目重构。
十一、最关键的三个文件
如果只选三个:
AI_CONTEXT.md
PROJECT_MAP.md
REPO_PROMPT.md
这三个可以让 AI 30 秒理解项目。
下面是一份 增强版 REPO_PROMPT.md 模板。它的定位是:为 AI 助手(如 Cursor、Windsurf、GitHub Copilot)提供仓库级系统提示,统一其改代码、加功能、重构时的行为准则。把它放在仓库根目录即可。
REPO_PROMPT.md
Purpose
This file defines how AI assistants should interact with this repository. Follow these rules when reading, modifying, or generating code.
1. Architectural Principles
-
Respect the layered architecture:
- api → service → repository → models
-
Never introduce circular dependencies.
-
Keep modules loosely coupled and cohesive.
-
Prefer composition over inheritance.
2. File and Function Limits
- Single file ≤ 2000 lines.
- Function ≤ 100 lines.
- Prefer splitting large logic into smaller modules.
If modifying a file that exceeds limits, propose a refactor.
3. Code Style
- Use descriptive variable and function names.
- Follow language conventions (snake_case or camelCase).
- Avoid abbreviations unless common (id, url, api).
- Add short comments only when logic is non-obvious.
Example:
Good:
createUserAccount
validateToken
fetchUserProfile
Bad:
handle
doTask
runLogic
4. Dependency Rules
Allowed:
api → service
service → repository
service → models
repository → models
utils → used by all
Forbidden:
repository → service
models → repository
api → repository
If a change would break these rules, refactor instead.
5. Refactoring Guidelines
When refactoring:
- Preserve existing public interfaces.
- Avoid unnecessary changes across unrelated modules.
- Extract shared logic into utils if reused.
- Ensure unit tests remain valid.
Prefer incremental refactoring over large rewrites.
6. Feature Development
When implementing a new feature:
- Determine affected modules.
- Add or modify models if needed.
- Implement business logic in service layer.
- Expose endpoints in api layer.
Never place business logic directly in api controllers.
7. Bug Fixing
When fixing bugs:
- Identify root cause.
- Modify the minimal number of files.
- Avoid introducing new dependencies.
- Add tests if possible.
8. Code Generation Behavior
When generating code:
- Follow existing project patterns.
- Reuse existing utilities and helpers.
- Avoid duplicating functionality.
- Maintain consistent naming conventions.
9. AI Context Strategy
To understand the project:
- Read PROJECT_MAP.md.
- Read MODULE_INDEX.md.
- Check DEPENDENCY_MAP.md.
- Then inspect relevant modules.
Do not assume knowledge of the entire repository.
10. Documentation Updates
If architectural changes occur:
Update the following files:
- PROJECT_MAP.md
- MODULE_INDEX.md
- DEPENDENCY_MAP.md
11. Testing Expectations
When adding new logic:
- Add unit tests in the tests directory.
- Mirror source directory structure.
- Ensure test coverage for critical paths.
12. Safety Rules
Do NOT:
- rewrite large parts of the codebase unnecessarily
- introduce breaking API changes
- add new external dependencies without justification
Prefer minimal, safe modifications.
13. AI Interaction Summary
AI assistants should:
- understand the architecture first
- make minimal targeted changes
- keep code modular and readable
- follow project conventions
使用建议
- 将
REPO_PROMPT.md放在仓库根目录,与PROJECT_MAP.md、AI_CONTEXT.md同级。 - 在 IDE 的 AI 设置中,如果支持 repo rules / system prompt,可指向此文件。
- 当项目架构变化时,及时同步更新。
搭配文件(推荐最小组合)
最实用的一组是:
AI_CONTEXT.md
PROJECT_MAP.md
MODULE_INDEX.md
DEPENDENCY_MAP.md
project_rules.md
REPO_PROMPT.md
这 6 个文件通常就足以让 AI 在中大型仓库里保持较稳定的改动质量。