What problem does it solve? AI agents and new teammates often write code that clashes with a project's established style because conventions live only in the codebase, not in documentation. This Skill systematically analyzes how a Laravel application is actually written and records those conventions as durable, path-scoped rules in .ai/rules that other agents read. ## Core Features & Use Cases - Systematic Convention Sweep: Evaluates roughly 49 Laravel convention dimensions across validation, controllers, Eloquent models, architecture, frontend, database, testing, and responses 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 and Default Filtering: Distinguishes genuine conventions from framework defaults, tooling-owned formats (Pint, Rector), and unresolved mixed patterns, requiring at least 3 consistent examples before recording. - Use Case: When onboarding an AI coding agent to an existing Laravel app, run this Skill to detect that the project uses legacy magic-method accessors and inline validation, then record those as rules so the agent matches the codebase instead of imposing modern defaults. ## Quick Start Analyze this Laravel project's coding conventions and record them as rules in .ai/rules using the record-rule tool.
