What problem does it solve? AI agents and new teammates often write code that clashes with how a Laravel application is actually built, because project conventions live only in the codebase itself. This Skill systematically analyzes the application and records its real conventions as durable, path-scoped rules in .ai/rules. ## Core Features & Use Cases - Systematic Convention Sweep: Evaluates roughly 49 Laravel convention dimensions covering validation, controllers, Eloquent models, architecture, frontend, database, and testing, using a structured checklist with grep hints. - Architecture Discovery: Maps non-default app/ directories (Actions, Services, DTOs, Queries, domain modules) and records structural patterns and deliberate absences like "no repository layer". - Conflict Detection: Reports mixed patterns with counts and example files instead of picking a winner, so rules always describe reality. - Rule Recording: Writes approved conventions via the Boost record-rule MCP tool, scoped to precise globs like app/Models/** or tests/**. - Use Case: After adopting Laravel Boost, run this Skill once to document that your app uses Form Requests, Action classes invoked via handle, and UUID primary keys, so every future agent session matches your house style. ## Quick Start Analyze this Laravel application's conventions and record them as rules in .ai/rules.
