shared/tech-stack-detection

Tech Stack Detection Method

Use Cases

Before technology selection, architecture design, or code generation, you need to first understand the tech stack currently used by the project, in order to:

• Follow the project's existing technology choices
• Generate code that conforms to project standards
• Avoid introducing incompatible technologies

Detection Methods

1. Detect configuration files

Use Read or Glob tools to detect configuration files in the project root directory:

JavaScript/TypeScript Ecosystem

File	Description	Detection Content
package.json	Node.js project configuration	dependencies, devDependencies, scripts
tsconfig.json	TypeScript configuration	Confirm TypeScript is used
next.config.js	Next.js configuration	Confirm Next.js is used
vite.config.js	Vite configuration	Confirm Vite is used
nuxt.config.js	Nuxt configuration	Confirm Nuxt is used

Detection Command：

# 检测是否存在
ls package.json tsconfig.json next.config.js vite.config.js 2>/dev/null

# 读取 package.json
Read(file_path: "package.json")

Key Dependency Identification：

• react: React project
• vue: Vue project
• next: Next.js project
• @angular/core: Angular project
• express: Express backend
• fastify: Fastify backend
• prisma: Prisma ORM
• typeorm: TypeORM

Python Ecosystem

File	Description	Detection Content
requirements.txt	pip dependencies	Dependency list
pyproject.toml	Poetry/PDM configuration	Dependencies and project configuration
Pipfile	Pipenv configuration	Dependencies
setup.py	Package configuration	Project metadata

Key Dependency Identification：

• django: Django project
• flask: Flask project
• fastapi: FastAPI project
• sqlalchemy: SQLAlchemy ORM
• pytest: Uses pytest for testing

Go Ecosystem

File	Description	Detection Content
go.mod	Go module configuration	Dependencies and Go version
go.sum	Dependency checksums	Confirm dependencies are locked

Key Dependency Identification：

• github.com/gin-gonic/gin: Gin framework
• github.com/gofiber/fiber: Fiber framework
• gorm.io/gorm: GORM ORM

Rust Ecosystem

File	Description	Detection Content
Cargo.toml	Cargo configuration	Dependencies and project configuration
Cargo.lock	Dependency locking	Confirm dependency versions

Key Dependency Identification：

• actix-web: Actix Web framework
• axum: Axum framework
• tokio: Async runtime

Java/Kotlin Ecosystem

File	Description	Detection Content
pom.xml	Maven configuration	Dependencies and plugins
build.gradle	Gradle configuration	Dependencies and tasks

Key Dependency Identification：

• spring-boot-starter: Spring Boot project
• quarkus: Quarkus project
• micronaut: Micronaut project

Ruby Ecosystem

File	Description	Detection Content
Gemfile	Bundler configuration	Dependencies
Gemfile.lock	Dependency locking	Confirm dependency versions

Key dependency identification：

• rails: Ruby on Rails project
• sinatra: Sinatra project

2. Detect database configuration

File/Directory	Description
prisma/schema.prisma	Prisma database configuration
drizzle.config.ts	Drizzle ORM configuration
ormconfig.json	TypeORM configuration
alembic/	Python Alembic migrations
migrations/	Database migration directory

Database type identification：

• postgresql://: PostgreSQL
• mysql://: MySQL
• mongodb://: MongoDB
• sqlite:: SQLite
• redis://: Redis

3. Detect deployment configuration

File	Description
Dockerfile	Docker containerization
docker-compose.yml	Docker Compose multi-container
vercel.json	Vercel deployment
.github/workflows/	GitHub Actions CI/CD
netlify.toml	Netlify deployment
railway.json	Railway deployment

4. Detect testing framework

JavaScript/TypeScript

File/Dependency	Framework
jest.config.js	Jest
vitest.config.js	Vitest
playwright.config.js	Playwright
cypress.json	Cypress

Python

Dependency	Framework
pytest	pytest
unittest	unittest (built-in)

Go

File	Framework
*_test.go	Go built-in testing

Detection process

Step 1: Detect project type

# 使用 Glob 查找配置文件
Glob(pattern: "{package.json,go.mod,Cargo.toml,pom.xml,requirements.txt,Gemfile}")

Step 2: Read configuration files

# 读取主配置文件
Read(file_path: "package.json")  # 或其他检测到的文件

Step 3: Analyze dependencies

Extract from configuration files:

• Language and version: e.g. Node.js 18, Python 3.11, Go 1.21
• Main framework: e.g. Next.js 14, Django 5.0, Gin
• Database: e.g. PostgreSQL, MongoDB
• ORM: e.g. Prisma, SQLAlchemy, GORM
• Testing framework: e.g. Jest, pytest
• Build tool: e.g. Vite, Webpack, esbuild

Step 4: Output detection results

Output in a structured format:

## 技术栈检测结果

### 语言和运行时
- **语言**：TypeScript
- **运行时**：Node.js 20.x
- **包管理器**：pnpm

### 前端框架
- **框架**：Next.js 14 (App Router)
- **UI 库**：React 18
- **样式**：Tailwind CSS
- **状态管理**：Zustand

### 后端框架
- **框架**：Next.js API Routes
- **ORM**：Prisma
- **数据库**：PostgreSQL

### 测试
- **单元测试**：Vitest
- **E2E 测试**：Playwright

### 部署
- **容器化**：Docker
- **CI/CD**：GitHub Actions
- **托管**：Vercel

Usage examples

Example 1: Detect a Next.js project

# 1. 检测配置文件
Glob(pattern: "package.json")

# 2. 读取 package.json
Read(file_path: "package.json")

# 3. 分析依赖
# 发现: "next": "14.0.0", "react": "18.2.0", "prisma": "5.0.0"

# 4. 输出结果
技术栈：Next.js 14 + React 18 + Prisma + PostgreSQL

Example 2: Detect a Python project

# 1. 检测配置文件
Glob(pattern: "{requirements.txt,pyproject.toml}")

# 2. 读取配置
Read(file_path: "pyproject.toml")

# 3. 分析依赖
# 发现: fastapi, sqlalchemy, pytest

# 4. 输出结果
技术栈：FastAPI + SQLAlchemy + PostgreSQL + pytest

Notes

1. Prioritize detecting existing projects: If the project already has configuration files, the existing tech stack must be followed
2. Only choose a stack for new projects: Only perform technology selection when there are no configuration files
3. Version compatibility: Pay attention to version compatibility between dependencies
4. Ecosystem consistency: Do not mix tools from different ecosystems (such as npm + poetry)

Common mistakes

❌ Assuming without detecting: Directly assuming a project uses a certain technology without detecting configuration files ❌ Ignoring versions: Only detecting framework names, not version numbers ❌ Mixing ecosystems: Recommending Python tools in a Node.js project ❌ Duplicate detection: Detecting the same configuration files multiple times in the same task