Specialized Claude Code agents for software development. Provides architectural guidance, decision frameworks, and best practices. Helps developers make informed technology choices. Integrates with Claude.
git clone https://github.com/supatest-ai/awesome-claude-code-sub-agents.gitSpecialized Claude Code agents for software development. Provides architectural guidance, decision frameworks, and best practices. Helps developers make informed technology choices. Integrates with Claude.
1. **Define Your Project Context**: Start by filling in the placeholders in the prompt template with your specific project details (e.g., [PROJECT_TYPE], [TECHNOLOGY_STACK], [DEVELOPMENT_GOALS]). The more specific you are, the better the guidance will be. 2. **Select Your Focus Area**: Decide whether you need architectural guidance, a decision framework, best practices, or risk mitigation. You can combine these as needed. 3. **Run the Prompt in Claude**: Copy the customized prompt and paste it directly into Claude Code or ChatGPT. Use the `awesome-claude-code-sub-agents` tool if available in your environment to get specialized responses. 4. **Iterate and Refine**: Review the output and ask follow-up questions to dive deeper into specific areas. For example, ask for a detailed implementation plan for a particular service or a comparison of deployment strategies. 5. **Implement Incrementally**: Start with the highest-priority recommendations (e.g., security, performance) and implement them in phases. Use the provided best practices as a checklist during development. **Tips for Better Results**: - Include your team's current tech stack and skill levels in the prompt. - Specify any constraints (e.g., budget, timeline, compliance requirements). - Mention if you're working with legacy systems or need backward compatibility. - Ask for code snippets or architectural diagrams if you need concrete examples.
No install command available. Check the GitHub repository for manual installation instructions.
git clone https://github.com/supatest-ai/awesome-claude-code-sub-agentsCopy the install command above and run it in your terminal.
Launch Claude Code, Cursor, or your preferred AI coding agent.
Use the prompt template or examples below to test the skill.
Adapt the skill to your specific use case and workflow.
Act as an awesome-claude-code-sub-agent specializing in [PROJECT_TYPE]. Provide architectural guidance for [TECHNOLOGY_STACK] with a focus on [DEVELOPMENT_GOALS]. Suggest a decision framework for choosing between [OPTION_A] and [OPTION_B] based on [CRITERIA]. Include best practices for [SPECIFIC_TASK] and highlight potential pitfalls to avoid. Structure your response with clear sections: Architecture Overview, Decision Framework, Implementation Best Practices, and Risk Mitigation.
### Architecture Overview For a real-time analytics dashboard using React 18, Node.js, and PostgreSQL, I recommend a microservices architecture with the following components: 1. **Frontend Service**: React 18 with TypeScript, using Vite for bundling and Zustand for state management. Implement a modular component structure with atomic design principles. 2. **API Gateway**: Node.js with Express.js, handling authentication (JWT), rate limiting, and request routing. Use Helmet for security headers and Winston for structured logging. 3. **Analytics Service**: Python-based FastAPI microservice for data processing, using Pandas for transformations and NumPy for numerical operations. Deploy with Docker and Kubernetes for scalability. 4. **Database Layer**: PostgreSQL 15 with TimescaleDB extension for time-series data. Implement read replicas for analytics queries and connection pooling with PgBouncer. 5. **Message Broker**: Redis Streams for real-time event processing between services. ### Decision Framework: React vs Vue for Frontend When choosing between React and Vue for this project, evaluate based on: | Criteria | React | Vue | Recommendation | |------------------------|--------------------------------|--------------------------------|-------------------------| | Learning Curve | Steeper (JSX, hooks) | Gentler (template syntax) | Vue for junior team | | Performance | Virtual DOM, slightly faster | Virtual DOM, comparable | Tie | | Ecosystem | Larger (Next.js, Redux) | Smaller but cohesive | React for mature stack | | State Management | Requires external libraries | Built-in Composition API | Vue for simpler state | | Team Familiarity | 60% React, 40% Vue | 30% React, 70% Vue | Vue for team alignment | **Recommendation**: Choose Vue.js with the Composition API for this project due to the team's existing Vue expertise and the need for faster initial development. Implement Nuxt.js for server-side rendering and static site generation capabilities. ### Implementation Best Practices 1. **Frontend**: - Use Vite for development and production builds - Implement lazy loading for routes and components - Set up ESLint with Airbnb config and Prettier for consistent formatting - Configure Jest with React Testing Library for unit tests - Implement Storybook for component documentation 2. **Backend**: - Use TypeScript for type safety across the Node.js services - Implement request validation with Zod or Joi - Set up Docker multi-stage builds for production images - Configure CI/CD pipeline with GitHub Actions - Implement distributed tracing with OpenTelemetry 3. **Database**: - Use Prisma ORM for type-safe database access - Implement connection pooling with PgBouncer - Set up database migrations with Prisma Migrate - Configure automated backups with WAL-E ### Risk Mitigation 1. **Performance Bottlenecks**: - Implement caching with Redis for frequent queries - Use database indexing for time-series data - Set up query performance monitoring with pgBadger 2. **Scalability Issues**: - Design services to be stateless where possible - Implement horizontal scaling with Kubernetes HPA - Use message queues for decoupling services 3. **Security Concerns**: - Implement rate limiting with Redis - Use environment variables for secrets (never hardcode) - Set up regular dependency scanning with Snyk - Configure CSP headers with Helmet 4. **Team Knowledge Gaps**: - Schedule architecture review sessions - Create internal documentation with Notion - Implement pair programming for complex features - Set up a shared Slack channel for architecture questions
AI assistant built for thoughtful, nuanced conversation
IronCalc is a spreadsheet engine and ecosystem
Enterprise workflow automation and service management platform
Customer feedback management made simple
Complete help desk solution for growing teams
The AI automation platform built for everyone
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan