Scaffold and Analyze Fullstack Projects

The skill provides three automated scripts for fullstack work: scripts/fullstack_scaffolder.py <project-path> [options] for scaffolding a fullstack project, scripts/project_scaffolder.py <target-path> [--verbose] for comprehensive project analysis and optimization recommendations, and scripts/code_quality_analyzer.py [arguments] [options] for code-quality analysis. It ships three reference documents: references/tech_stack_guide.md for patterns, code examples, and anti-patterns; references/architecture_patterns.md for step-by-step workflows, optimization strategies, and tool integrations; and references/development_workflows.md for technology-stack details, configuration examples, and security/scalability guidance - the same file it points to for troubleshooting.

The named tech stack spans TypeScript, JavaScript, Python, Go, Swift, and Kotlin for languages; React, Next.js, React Native, and Flutter on the frontend; Node.js, Express, GraphQL, and REST APIs on the backend; PostgreSQL, Prisma, NeonDB, and Supabase for data; Docker, Kubernetes, Terraform, GitHub Actions, and CircleCI for DevOps; and AWS, GCP, and Azure for cloud. The development workflow is: install dependencies and configure the environment, run project_scaffolder.py to get recommendations and apply fixes, then implement the patterns documented in the three reference files. Best practices are grouped into code quality (established patterns, comprehensive tests, documented decisions), performance (measure before optimizing, appropriate caching, monitor in production), security (validate inputs, parameterized queries, proper authentication, updated dependencies), and maintainability (clear code, consistent naming, simplicity).

Common commands cover both development and analysis: npm run dev, npm run build, npm run test, and npm run lint for the app; python scripts/project_scaffolder.py . and python scripts/code_quality_analyzer.py --analyze for analysis; and docker build -t app:latest ., docker-compose up -d, and kubectl apply -f k8s/ for deployment. For troubleshooting it points to the comprehensive troubleshooting section inside references/development_workflows.md, and for further help it directs the agent to review the reference documentation, check script output messages, consult the tech-stack documentation, and review error logs.

Setup, quoted verbatim from the source:

### Install dependencies
npm install
### or
pip install -r requirements.txt

### Configure environment
cp .env.example .env

Use it when scaffolding or reviewing a fullstack project and needing project scaffolding, structural analysis, or code-quality review backed by documented patterns and a defined tech stack. It is not a substitute for environment-specific validation, testing, or expert review, and it stops for clarification when required inputs, permissions, safety boundaries, or success criteria are missing.

Input is a project or target path passed to one of the three scripts. Output is a scaffolded fullstack project, a project analysis with performance metrics and recommendations, or a code-quality analysis report, plus the reference documentation to act on the findings.

Fullstack developers who need project scaffolding, structural analysis, and code-quality review as scripted, repeatable tools rather than manual, one-off setup and review.