More screenshots
Works with the AI tools you already use
OptiTech Backend Developer (skill 1 of 6)
by Ilya Demidov
⚠️ Atention. This is 1 item of 6 skills that cover entire SDLC. Feel free to download other OptiTech skills to build your SDLC.
Secure checkout via Stripe
See it in action
You say
Read 2023-10-27-create-billing-module.md and implement the stable coins wallet backend.
Your agent does
I have implemented the stable coins wallet in backend/.
- Created WalletController and TransferController with Zod validation.
- Implemented WalletService and TransferServices for implementation Product Owner task.
- Added repository for persistence.
- Updated prisma/schema.prisma and generated migration.
- Registered module in src/index.ts.
POST-CODING CHECKLIST ... [x] Tests written; npm run test passes ... Invoking /optitech-backend-reviewer.
What you get
About this skill
The problem
Backend developers often struggle with architectural drift where business logic leaks into controllers, modules become tightly coupled, and the folder structure turns into a mess. Manually enforcing Domain-Driven Design and dependency injection rules across a growing team is time-consuming and error-prone.
What it does
- Enforces a strict modular monolith architecture (ready for microservices splitting) using a standardized folder structure for every feature.
- Implements business logic exclusively in service layers, keeping controllers thin and persistence-agnostic.
- Generates Prisma migrations and Zod validation schemas automatically based on feature requirements.
- Maintains API documentation by adding Swagger JSDoc to every new controller method.
- Prevents cross-module database access by forcing communication through public controller interfaces.
Frameworks & tools
Node.js, TypeScript, Express, Prisma, Zod, Vitest, and Swagger.
Why this beats prompting it yourself
Generic prompts often ignore project-specific DI containers and complex architectural constraints like bounded contexts. This skill follows a rigorous post-coding checklist and escalation protocol, ensuring code isn't just functional, but architecturally sound and production-ready according to your specific patterns.
Use cases
- Adding new RESTful endpoints that require strict request validation and auth.
- Implementing new business modules with dedicated persistence and service layers.
- Refactoring legacy backend logic into a clean, modular structure.
- Integrating third-party APIs through standardized integration clients.
Known limitations
Requires a CONTEXT.md file and an architect task file to function. It is restricted to the backend directory and will not modify frontend or end-to-end test files.
How to install
Drop the file into your AI Agent. Works with Claude, Cursor, ChatGPT, and 20+ more.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
Fresh listing
Recently published to Agensi
30-day refund
Not a fit? Get your money back
Trust & safety
Security scanned
Verified clean today
- 30-day refund guarantee
- One-time purchase, yours forever
- Secure checkout via Stripe
Creator
3 skills on Agensi
I'm an entrepreneur with a background in software engineering and solutions architecture. Over the years, I've built products across both enterprises and startups, learning how to combine technical excellence with business impact. I love transforming ideas into AI-powered solutions that people actually use. Curious by nature, I keep learning, experimenting, and focusing on what matters most: building products that solve real problems. 🚀
Frequently Asked Questions
Popular in AI Agents & LLM Ops
agentic-workflow
A risk-aware, evidence-based engineering lifecycle protocol for robust agentic task execution and safety.
designing-hybrid-context-layers
Architects the right retrieval strategy for every query — teaching your agent when to use RAG, a knowledge graph, or a temporal index instead of defaulting to vector search for everything.

prompt-engineer
Professional prompt engineering patterns for building robust, secure, and production-ready LLM applications.
codex-grade-coding
Turn your AI agent into a senior engineer with strict task classification and verification-driven coding protocols.