Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    ai Coding Guidelines

    1

    Standardized engineering guides for Clean Architecture, distributed systems, and human-centered UI/UX design.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    ai-coding-guidelines

    ai-coding-guidelines

    Example session with this skill installed

    Review my current Spring Boot service structure. I have ORM entities leaking into my REST controllers, and I need to move toward Clean Architecture with better TDD practices.

    • Read your context and instructions
    • Compiled the ai-coding-guidelines

    I have reviewed your Spring Boot service structure. The current tight coupling between your web layer and your persistence model violates the Dependency Rule. I will now provide a refactoring plan to establish proper architectural boundaries and an Outside-In TDD workflow.

    Clean Architecture Refactoring Plan

    ComponentCurrent StateTarget State
    EntitiesJPA @Entity annotations in domainPlain Java/Kotlin objects with no framework dependencies
    ControllersDirect injection of RepositoriesInjection of Use Case Input Boundaries (Interfaces)
    PersistenceLeaked SQL logic in servicesInterface-driven Repositories implemented in the outer layer
    Test StrategyUnit tests mocking HibernateWalking Skeleton (E2E) + Isolated Domain Unit Tests

    Refactored Directory Structure

    src/main/java/com/app/feature/
    ├── domain/                # Core business logic (Entities)
    │   └── Order.java
    ├── usecase/              # Application logic (Input/Output Boundaries)
    │   ├── PlaceOrderUseCase.java
    │   └── PlaceOrderInteractor.java
    ├── infrastructure/       # External tools (Frameworks/Drivers)
    │   ├── persistence/
    │   │   └── JpaOrderRepository.java
    │   └── web/
    │       └── OrderController.java
    

    Next steps

    1. Define the Domain Entities as pure objects to ensure they are independent of Jakarta Persistence.
    2. Implement a

    Walking Skeleton test that hits a /health endpoint and the database to verify the infrastructure slice.
    3. Extract the business logic from the OrderController into a PlaceOrderInteractor that implements a use-case interface.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    This dual-skill package provides specialized engineering standards for full-stack development, covering both backend architecture and UI/UX interaction design. It bridges the gap between clean code craftsmanship and human-centered design principles.

    What it does

    • Backend Architecture: Applies Clean Architecture, SOLID principles, and layered boundaries to keep business logic independent of frameworks.
    • Distributed Systems: Evaluates data storage trade-offs, replication strategies, and transaction isolation levels for scalable services.
    • TDD Implementation: Guides Outside-In TDD using walking skeletons to verify end-to-end functionality before feature implementation.
    • UI/UX Design: Establishes visual hierarchy, spacing systems, and typography scales based on cognitive psychology.
    • Interaction Posture: Optimizes interface layouts for sovereign workspaces or transient utilities to reduce cognitive friction.

    How it works

    1. Architectural Review: Invoke the backend skill to audit service boundaries or database schemas against the Dependency Rule.
    2. Design System Setup: Use the UI skill to define geometric spacing scales, type scales, and color palettes.
    3. Refactoring: Apply clean code guidelines to simplify complex functions or move to idiomatic OOP patterns like Builders.
    4. Interaction Audit: Evaluate existing frontend flows for Fitts' Law compliance and touch target ergonomics.

    Frameworks & tools

    Specific support for Java 21/25, Spring Boot 7.x, Jakarta EE 11, and distributed engines like PostgreSQL, MySQL, and Cassandra. Design guidelines align with WCAG AA accessibility and platform-specific ergonomics for iOS and Android.

    Why this beats prompting it yourself

    Generic prompts often mix business logic with infrastructure or ignore cognitive load in UI design. This skill enforces strict architectural boundaries and geometric design constraints that prevent technical and visual debt.

    Use cases

    • Designing a distributed system that requires specific transaction isolation levels and high write throughput.
    • Building a new design system from grayscale foundations with consistent spacing and typography.
    • Refactoring a legacy Java monolith into clean, testable layers using constructor dependency injection.
    • Auditing a mobile application for touch target compliance and accessibility standards.

    Known limitations

    Does not support pure frontend build configurations or project-specific CI/CD scripts. Visual design focuses on layout and hierarchy rather than branding or illustration.

    Focuses on architecture and UX principles, not CI/CD scripts or brand illustration. Requires Java 21+ for specific backend idioms.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 13 days ago

    Permissions

    Network Access
    Read Files
    Write Files
    Listed13 days ago

    What's inside

    Frequently Asked Questions

    This skill provides a standardized framework for building scalable backends using Clean Architecture and Spring Boot, alongside scientifically-backed UI/UX principles like Fitts' Law and cognitive psychology. It solves the problem of 'architectural drift' where code becomes messy and interfaces become unintuitive over time.

    The package includes two distinct specialized modules: a Backend Engineering Guide for system architecture and a UI/UX Interaction Design Guide for visual hierarchy and ergonomics. Both are delivered as optimized prompt instructions compatible with leading LLMs like GPT-4, Claude 3.5, and Gemini Pro.

    The guidelines are highly compatible with Java 21/25, Spring Boot 7.x, and Jakarta EE 11 environments. On the design side, it aligns with WCAG AA accessibility standards and is suitable for both iOS and Android platform development.

    Simply import the skill instructions into your AI agent's system prompt or specialized custom instruction field. Once active, you can invoke specific workflows like an 'Architectural Review' or a 'Design System Setup' to audit your current project files.

    Unlike generic prompts, this skill enforces strict 'Dependency Rules' and geometric spacing scales that prevent the AI from mixing business logic with infrastructure. It ensures your project remains maintainable by prioritizing SOLID principles and cognitive load reduction rather than just generating working code.

    New in Prompt & Skill Engineering