infer-conventions

Detect Laravel codebase conventions and record them as path-scoped rules.

Updated Aug 5, 2026
One-click install
npx skills add https://github.com/rizalord/livecode-ptbeon --skill infer-conventions-rizalord
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: infer-conventions
Source: https://github.com/rizalord/livecode-ptbeon/tree/main/src/backend/.grok/skills/infer-conventions
Command: npx skills add https://github.com/rizalord/livecode-ptbeon --skill infer-conventions-rizalord

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Laravel projects accumulate implicit coding conventions that new agents and teammates cannot discover without reading the entire codebase, leading to inconsistent code and conflicting patterns. ## Core Features & Use Cases - Systematic Convention Sweep: Evaluates roughly 49 Laravel convention dimensions covering validation, controllers, models, architecture, frontend, database, testing, and responses. - Architecture Discovery: Maps non-default app/ directories such as Actions, Services, DTOs, and domain modules, recording both structural patterns and deliberate absences. - Conflict Detection: Reports mixed patterns with counts and example files instead of silently picking a winner. - Rule Recording: Writes approved conventions as path-scoped rules via the Boost record-rule MCP tool so future agents follow them. - Use Case: When onboarding an AI agent to an existing Laravel app, run this skill to document that the project uses inline validation, Action classes invoked via handle(), and legacy attribute accessors, so generated code matches the house style. ## Quick Start Ask the agent to analyze this Laravel project's conventions and record them as rules in .ai/rules.

Frequently Asked Questions about infer-conventions

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I document coding conventions in a Laravel project?▼

Run a systematic sweep of the codebase across convention dimensions like validation style, model patterns, and architecture, then record each confirmed pattern as a path-scoped rule. This skill uses a 49-dimension checklist and the Boost record-rule tool to persist findings in .ai/rules.

How to detect conflicting code patterns in a Laravel codebase?▼

Grep for both sides of each fork, such as inline validation versus Form Requests, and count occurrences with example files. When both styles appear in meaningful numbers, report the split to the user rather than recording a preferred winner.

Does this work with modular or domain-driven Laravel layouts?▼

Yes, the open-ended pass maps non-default app/ directories like Domain, Modules, Actions, and Services, and adapts rule globs to the observed paths. The layout itself is captured as a high-value architectural convention.

What happens if the record-rule MCP tool is unavailable?▼

Detection steps still run read-only, and the skill falls back to reporting the full rule text so the user can enable BOOST_RULES_ENABLED or add rules to .ai/rules manually.

When should I not use convention inference?▼

Skip it for one-off code reviews, formatting already handled by Pint or Rector, and fresh apps with too little code to establish patterns. Framework defaults like anonymous migrations are also excluded since agents write them unprompted.