Recommend technology stacks based on project requirements, team expertise, and constraints. Use when selecting frameworks, languages, databases, and infrastructure for new projects.
The Tech Stack Recommender is a comprehensive Claude skill designed to assist developers, architects, and stakeholders in selecting the optimal technology stack for their software projects. By analyzing specific project requirements, team expertise, and business constraints, it provides data-driven recommendations across frameworks, languages, databases, and infrastructure to ensure scalability, performance, and cost-efficiency.
Use Cases
1. Startup MVP Selection: Identifying the most efficient and rapid-development stacks (e.g., Next.js + Supabase) to minimize time-to-market for new products.
2. Enterprise Architecture Planning: Evaluating robust, long-term solutions like Java/Spring Boot or .NET for high-stability and transaction-heavy enterprise systems.
3. Specialized Use Case Optimization: Choosing tailored stacks for specific domains such as ML-powered applications (FastAPI + Vector DBs) or real-time collaboration tools (Node.js + WebSockets).
4. Team Skill Alignment: Assessing the learning curve and hiring market for various technologies to ensure the chosen stack matches the current team's capabilities.
5. Technology Migration & Modernization: Providing risk assessments and strategic frameworks for transitioning from legacy monoliths to modern cloud-native or microservices architectures.
name
tech-stack-recommender
description
Recommend technology stacks based on project requirements, team expertise, and constraints. Use when selecting frameworks, languages, databases, and infrastructure for new projects.
Tech Stack Recommender
Provides structured recommendations for technology stack selection based on project requirements, team constraints, and business goals.
When to Use
Starting a new project and need stack recommendations
Evaluating technology options for specific use cases
❌ "Let's use microservices from day one"
→ Start monolith, extract later
❌ "We need Kubernetes for our 3-person startup"
→ Use managed platforms (Vercel, Railway)
❌ "MongoDB because NoSQL is modern"
→ PostgreSQL handles 95% of use cases better
❌ "GraphQL for everything"
→ REST is simpler for most APIs
❌ "Let's build our own auth"
→ Use Auth0, Clerk, or established solutions
Migration Considerations
When to Consider Migration
Trigger
Action
Performance bottlenecks
Profile first, then consider
Team expertise mismatch
Train or hire before migrating
End of life/support
Plan 6-12 months ahead
Scale limitations
Validate limits with benchmarks
Security vulnerabilities
Patch if possible, migrate if not
Migration Risk Assessment
LOW RISK:
- Library/package updates
- Minor version upgrades
- Adding new services
MEDIUM RISK:
- Database version upgrades
- Framework major versions
- New deployment platform
HIGH RISK:
- Language/framework rewrites
- Database technology changes
- Monolith to microservices