agent-creator
Use when creating expert agents. Generates agent.md with frontmatter, hooks, required sections, and skill references.
Use when structuring a Laravel project, creating services/repositories/actions, implementing dependency injection, or organizing code layers.
$ npx -y skills add fusengine/agents --skill laravel-architecture --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/laravel-architectureContext preview
The summary Claude sees to decide when to auto-load this skill.
Use when structuring a Laravel project, creating services/repositories/actions, implementing dependency injection, or organizing code layers.
name: laravel-architecture description: Use when structuring a Laravel project, creating services/repositories/actions, implementing dependency injection, or organizing code layers. versions: laravel: "13.0" php: "8.3" user-invocable: true references: references/container.md, references/providers.md, references/facades.md, references/contracts.md, references/structure.md, references/lifecycle.md, references/configuration.md, references/installation.md, references/upgrade.md, references/releases.md, references/sail.md, references/valet.md, references/homestead.md, references/octane.md, references/artisan.md, references/helpers.md, references/filesystem.md, references/processes.md, references/context.md, references/pennant.md, references/mcp.md, references/concurrency.md, references/deployment.md, references/envoy.md, references/logging.md, references/errors.md, references/packages.md related-skills: solid-php, laravel-api, laravel-eloquent
<objective> Covers Laravel application architecture end to end: project structure (Actions, Contracts, DTOs, Services, Repositories layout), the service container and dependency injection, service providers and facades, environment/configuration, development environments (Sail, Valet, Homestead, Octane), Artisan CLI, filesystem/processes/context, feature flags (Pennant), MCP servers, concurrency, and production deployment (including Envoy, logging, error handling, and package authoring). </objective>
Before ANY implementation, spawn 3 agents in parallel, one `Agent` call each with a `name`:
1. **fuse-ai-pilot:explore-codebase** - Analyze existing architecture 2. **fuse-ai-pilot:research-expert** - Verify Laravel patterns via Context7 3. **mcp__context7__query-docs** - Check service container and DI patterns
After implementation, run **fuse-ai-pilot:sniper** for validation.
---
Laravel architecture focuses on clean separation of concerns, dependency injection, and maintainable code organization. This skill covers everything from project structure to production deployment.
---
1. **Thin controllers** - Delegate business logic to services 2. **Interfaces in app/Contracts/** - Never alongside implementations 3. **DI over facades** - Constructor injection for testability 4. **Files < 100 lines** - Split larger files per SOLID 5. **Environment separation** - .env never committed
---
app/ ├── Actions/ # Single-purpose action classes ├── Contracts/ # Interfaces (DI) ├── DTOs/ # Data transfer objects ├── Enums/ # PHP 8.1+ enums ├── Events/ # Domain events ├── Http/ │ ├── Controllers/ # Thin controllers │ ├── Middleware/ # Request filters │ ├── Requests/ # Form validation │ └── Resources/ # API transformations ├── Jobs/ # Queued jobs ├── Listeners/ # Event handlers ├── Models/ # Eloquent models only ├── Policies/ # Authorization ├── Providers/ # Service registration ├── Repositories/ # Data access layer └── Services/ # Business logic
---
| Reference | When to Use | |-----------|-------------| | [container.md](references/container.md) | Dependency injection, binding, resolution | | [providers.md](references/providers.md) | Service registration, bootstrapping | | [facades.md](references/facades.md) | Static proxies, real-time facades | | [contracts.md](references/contracts.md) | Interfaces, loose coupling | | [structure.md](references/structure.md) | Directory organization | | [lifecycle.md](references/lifecycle.md) | Request handling flow |
| Reference | When to Use | |-----------|-------------| | [configuration.md](references/configuration.md) | Environment, config files | | [installation.md](references/installation.md) | New project setup | | [upgrade.md](references/upgrade.md) | Version upgrades, breaking changes | | [releases.md](references/releases.md) | Release notes, versioning |
| Reference | When to Use | |-----------|-------------| | [sail.md](references/sail.md) | Docker development | | [valet.md](references/valet.md) | macOS native development | | [homestead.md](references/homestead.md) | Vagrant (legacy) | | [octane.md](references/octane.md) | High-performance servers |
| Reference | When to Use | |-----------|-------------| | [artisan.md](references/artisan.md) | CLI commands, custom commands | | [helpers.md](references/helpers.md) | Global helper functions | | [filesystem.md](references/filesystem.md) | File storage, S3, local | | [processes.md](references/processes.md) | Shell command execution | | [context.md](references/context.md) | Request-scoped data sharing |
| Reference | When to Use | |-----------|-------------| | [pennant.md](references/pennant.md) | Feature flags | | [mcp.md](references/mcp.md) | Model Context Protocol | | [concurrency.md](references/concurrency.md) | Parallel execution |
| Reference | When to Use | |-----------|-------------| | [deployment.md](references/deployment.md) | Production deployment | | [envoy.md](references/envoy.md) | SSH task automation | | [logging.md](references/logging.md) | Log channels, formatting | | [errors.md](references/errors.md) | Exception handling | | [packages.md](references/packages.md) | Creating packages |
---
| Template | Purpose | |----------|---------| | [UserService.php.md](references/templates/UserService.php.md) | Service + repository pattern | | [AppServiceProvider.php.md](referen
A plugin ecosystem that turns Claude Code into a supervised, multi-agent development environment.
Repo: fusengine/agents
Use when creating expert agents. Generates agent.md with frontmatter, hooks, required sections, and skill references.
Use when starting ANY development task -- feature, bug fix, refactor, hotfix (triggers: implement, create, build, fix, add feature, refactor, develop).
Use when creating a feature/component or adding functionality. Fires BEFORE APEX Analyze to refine requirements via structured questioning.
Use before a root-cause, done/verified claim, irreversible action, or 2nd-time fix reaches the owner (APEX or plain conversation); also fires at every…
Use when validating code quality after modifications -- SOLID compliance, DRY duplication, linter errors, architecture violations. Do NOT use for functional…
Use when an expert agent self-reviews and self-corrects code after the Execute phase, before sniper validation (BMAD-METHOD elicitation techniques).