What problem does it solve? Teams and AI agents working on a Laravel application often guess at the project's conventions, producing inconsistent code across validation, models, architecture, testing, and frontend layers. This Skill systematically detects how the application is actually written and records those conventions as durable, path-scoped rules in .ai/rules so every agent and teammate follows the same patterns. ## Core Features & Use Cases - Systematic convention sweep: Evaluates roughly 49 Laravel convention dimensions across validation, controllers, authorization, Eloquent, architecture, frontend, database, testing, and 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 default filtering: Distinguishes genuine conventions from framework defaults, tooling-owned formats (Pint, Rector), and unresolved mixed patterns, reporting conflicts instead of guessing. - Path-scoped rule recording: Writes approved conventions via the Boost record-rule MCP tool with precise globs so rules surface only where relevant. - Use Case: After inheriting a mature Laravel app, run the sweep to discover it uses legacy magic-method accessors, Action classes invoked via handle, and inline validation, then record those as rules so future agent-generated code matches the existing style. ## Quick Start Analyze this Laravel application's conventions and record the confirmed patterns as rules in .ai/rules.
