clean-code-guard

Audits code diffs for Clean Code, SOLID, and AI-specific failure patterns.

Updated Jun 9, 2026
One-click install
npx skills add https://github.com/Asharf30/Brainwave --skill clean-code-guard-asharf30
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: clean-code-guard
Source: https://github.com/Asharf30/Brainwave/tree/main/.agents/skills/clean-code-guard
Command: npx skills add https://github.com/Asharf30/Brainwave --skill clean-code-guard-asharf30

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill addresses the systematic failure modes of LLM-generated code, such as swallowed exceptions, premature abstractions, and hardcoded mock data, ensuring code quality before it reaches production.

Core Features & Use Cases

  • Guard-pass Mode: Automatically audits code diffs for Clean Code, SOLID, and AI-specific failure patterns before you commit or merge.
  • Review Mode: Provides a structured, evidence-based audit of existing codebases against industry-standard principles like DRY, KISS, and YAGNI.
  • Live Mode: Acts as a real-time coding assistant that applies rigorous quality imperatives while you write, preventing technical debt from being introduced in the first place.

Quick Start

Invoke the clean-code-guard skill to review the current pull request for potential bugs and maintainability issues.

Frequently Asked Questions about clean-code-guard

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

FAQPage Schema
How do I review LLM-generated code for swallowed exceptions and premature abstractions?

You can review LLM-generated code for swallowed exceptions and premature abstractions by applying rigorous code quality guardrails and AI-specific failure mode checks to enforce SOLID, DRY, KISS, and YAGNI principles.

What is the best way to enforce clean code principles during a code review?

The best way to enforce clean code principles during a code review is to use a structured audit mode that checks existing codebases against DRY, KISS, and YAGNI principles to ensure production-grade reliability.

How do I prevent hardcoded mock data and AI failure modes from reaching production?

Prevent hardcoded mock data and AI failure modes from reaching production by applying automated guardrails that audit code diffs for clean code and AI-specific failure patterns before merging.

Can I apply real-time coding guardrails to enforce SOLID principles while writing code?

Yes, you can apply real-time coding guardrails using a live mode assistant that enforces SOLID principles and documented imperatives for function sizing, error handling, and naming conventions while you write.

Does this code quality guard work across diverse programming languages?

Yes, this code quality guard operates across diverse programming languages to enforce clean code, SOLID, DRY, KISS, and YAGNI principles during code review or implementation tasks.

How do I check my pull request for maintainability issues and potential bugs?

Check your pull request for maintainability issues and potential bugs by invoking an automated guard-pass mode that audits code diffs against documented imperative rules for error handling and naming conventions.