Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Laravel Production Architect

    1

    Ship Laravel apps with clean architecture, hardened APIs, and production-ready performance patterns.

    Free

    2 usesSecurity scanned
    Laravel Production Architect

    Laravel Production Architect

    Example session with this skill installed

    Our order module's OrderController::checkout() is 380 lines, with inline validation and synchronous Stripe webhook calls. Prod is also showing N+1 warnings on /api/v1/orders. Refactor it into the standard lifecycle: a FormRequest for validation, an Action class for the checkout use case, an API Resource for the response, and move webhook delivery into a retry-safe queued job with backoff. Add a policy so users can only read their own orders, and audit the listing query for eager loading. Show me the resulting file structure, the key diffs, and which tests to add.

    • Read your context and instructions
    • Compiled the laravel production architect

    Summary

    Refactored OrderController@checkout from 380 lines into four focused classes plus a queued webhook job, fixed the N+1 on the orders listing, and added an OrderPolicy that blocks cross-user access.

    MetricBeforeAfter
    Lines in controller38042
    Queries on order index513
    Checkout p95 latency2.4s0.6s (webhook queued)
    Ownership enforcementscattered if checksPolicy + IDOR guard
    app/Domain/Orders/Actions/CheckoutOrder.php
    app/Http/Requests/CheckoutOrderRequest.php
    app/Http/Resources/OrderResource.php
    app/Jobs/DeliverStripeWebhook.php   # tries=5, backoff 5–120s
    

    Next steps

    • Run php artisan test --filter=Checkout and add feature tests for policy denials and the validation error shape.
    • Add an index on orders(user_id, status, placed_at) for the filtered listing query.
    • Run queue:work under supervisor so webhook retries survive deploys.

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

    About this skill

    Build and maintain Laravel applications that survive production traffic and technical audits. This skill enforces a senior engineering mindset, focusing on framework-native patterns, predictable structure, and security by default. It helps you move past messy controllers and unvalidated inputs toward a clean architecture that scales without over-engineering.

    What it does

    • Architectural Design Provides structured boundaries using Actions, Services, and Domain logic to keep codebases manageable.
    • Production Hardening Enforces secure defaults, including FormRequest validation, Policy-based authorization, and rate limiting.
    • Performance Optimization Identifies N+1 queries, suggests eager loading strategies, and implements robust caching with invalidation.
    • API Standardisation Generates stable JSON payloads using API Resources and consistent error shapes for mobile or SPA consumers.
    • Reliable Backgrounding Designs retry-safe Queue jobs with proper backoff, unique locks, and stateless execution.

    How it works

    1. Define the Scope Provide a feature requirement, a messy controller, or a database schema.
    2. Review & Audit The agent analyzes the input for security risks, performance bottlenecks, and framework anti-patterns.
    3. Refactor & Implement You receive framework-idiomatic code following the request lifecycle: Routes, Middleware, FormRequests, and Resources.

    Frameworks & tools

    Laravel 10/11+, Eloquent, Sanctum, Redis for caching/queues, and PHP 8.2+ type systems.

    Why this beats prompting it yourself

    Generic prompts often result in "helper-heavy" code or logic leaks into Blade views and controllers. This skill enforces strict architectural boundaries and production-ready security patterns that standard LLMs frequently overlook.

    Use cases

    • Refactoring a "God Controller" into discrete, testable Actions and Services.
    • Building a secure, versioned JSON API for a mobile application.
    • Troubleshooting database bottlenecks and implementing N+1 query fixes.
    • Designing a reliable background processing system for high-volume webhooks.

    Known limitations

    Does not support frontend-only tasks, non-Laravel PHP frameworks, or infrastructure-level database migrations unrelated to application design.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Code Quality & Review.

    Laravel-specific — pure PHP, Symfony, or other frameworks are out of scope. Examples target Laravel 10/11 conventions; newer majors may need small adjustments.

    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 buying a skill.

    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

    2 uses

    Times used to date

    Free to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 1 month ago

    • Free with an Agensi account

    Permissions

    Read Files
    Write Files

    File Scopes

    app/**
    routes/**
    database/**
    config/**
    tests/**

    Reads and edits Laravel project source and runs artisan/test commands locally, so no network access or secrets are required.

    Listed1 month ago

    What's inside

    Frequently Asked Questions

    This skill is compatible with LLMs that support system role prompts or custom instructions, such as GPT-4o, Claude 3.5 Sonnet, and specialized IDE agents like Cursor or GitHub Copilot.

    It specifically targets Laravel 10 and 11+, utilizing PHP 8.2+ type-hinting and modern framework features like Anonymous Migrations and Job Batching.

    Unlike generic prompts that often place logic in controllers, this skill enforces a strict separation of concerns using Actions, Services, and API Resources to ensure your code passes professional technical audits.

    You will receive a set of optimized instructions and constraints that you can plug into your favorite AI tool to instantly transform it into a senior-level Laravel consultant.

    The skill focuses on application-level architecture, Eloquent optimization, and secure API design; it does not handle frontend styling, DevOps/server provisioning, or legacy Laravel versions (pre-v9).

    Updates are provided periodically to reflect new Laravel releases and emerging best practices, ensuring your architecture remains modern as the ecosystem evolves.

    New in Code Quality & Review

    Free