What problem does it solve? AI agents and new teammates often write Laravel code that clashes with how a project actually does things, because conventions live only in the codebase and in people's heads. This Skill systematically analyzes a Laravel application and records its real conventions as durable, path-scoped rules in .ai/rules that agents read automatically. ## Core Features & Use Cases - Systematic convention sweep: Evaluates roughly 49 Laravel convention dimensions across validation, controllers, authorization, Eloquent models, architecture, frontend, database, testing, and API responses using a structured checklist. - Architecture discovery: Maps non-default app/ directories (Actions, Services, DTOs, Queries, domain modules) and records structural patterns and deliberate absences, such as "no repository layer". - Conflict and noise filtering: Distinguishes genuine conventions from framework defaults, tool-owned formatting (Pint/Rector), and mixed-style conflicts, requiring at least 3 consistent examples before proposing a rule. - Use Case: An agent keeps generating Form Request classes while the app validates inline everywhere. Run this Skill to detect the inline-validation convention, confirm it, and record a rule scoped to app/Http/** so every future agent matches the house style. ## Quick Start Analyze this Laravel project's conventions and record them as rules in .ai/rules using the infer-conventions skill.
