What problem does it solve?
Laravel projects accumulate implicit coding conventions that AI agents and new teammates cannot see, causing inconsistent code across validation styles, architecture patterns, and testing approaches. This Skill systematically analyzes how an application is actually written and records those conventions as durable, path-scoped rules in .ai/rules.
Core Features & Use Cases
- Systematic Convention Sweep: Evaluates roughly 49 Laravel convention dimensions across validation, controllers, Eloquent models, architecture, frontend, database, and testing using a structured checklist.
- 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 arbitrarily picking a winner, deferring to the user when the codebase is genuinely split.
- Rule Recording: Writes approved conventions via the Boost
record-rule MCP tool, scoped to precise globs like app/Models/** or tests/**.
- Use Case: When onboarding an AI agent to an existing Laravel app, run this Skill to document that the project uses legacy magic-method accessors, Action classes invoked via
handle(), and Pest tests with factories, so all future generated code matches the house style.
Quick Start
Analyze this Laravel project's coding conventions and record them as shared rules in .ai/rules.