ai-slop-cleaner

Remove duplicated and dead code while preserving behavior with regression tests.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/0xAndoroid/dotfiles --skill ai-slop-cleaner-0xandoroid
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ai-slop-cleaner
Source: https://github.com/0xAndoroid/dotfiles/tree/main/claude/skills/ai-slop-cleaner
Command: npx skills add https://github.com/0xAndoroid/dotfiles --skill ai-slop-cleaner-0xandoroid

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

AI-generated code slop can accumulate bloated patterns, duplicate logic, and weak test coverage, causing maintenance pain and drift from intent.

Core Features & Use Cases

  • Bounded, regression-safe cleanup passes that target bloated or duplicated code without changing behavior
  • Optional reviewer-only mode (--review) to perform anti-slop analysis before final delivery
  • Structured workflow: plan, identify slop categories (duplication, dead code, needless abstraction, boundary violations), execute minimally invasive edits, verify with regression checks

Quick Start

Provide the changed files list and run the ai-slop-cleaner in standard mode to begin a regression-safe deletion-first cleanup

Frequently Asked Questions about ai-slop-cleaner

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

FAQPage Schema
How do I clean up AI-generated code without breaking existing behavior?

To clean up AI-generated code safely, you must protect current behavior with regression tests, produce a cleanup plan, execute minimally invasive edits, and verify results with regression checks.

What is AI code slop and how does it affect software maintenance?

AI code slop is bloated, duplicated, or weakly tested generated logic that causes maintenance pain and drift from intent, typically categorized into duplication, dead code, needless abstraction, and boundary violations.

Can I review AI-generated code for slop without modifying the files?

Yes, you can use an optional reviewer-only mode to perform anti-slop analysis and categorize bloated patterns before final delivery, without applying any minimally invasive edits.

What's the best way to refactor duplicated AI logic in a post-review workflow?

The best way to refactor duplicated AI logic is using a bounded, deletion-first cleanup workflow that categorizes slop, executes targeted passes in order, and relies on regression tests to stay regression-safe.

Do I need regression tests to remove dead code and needless abstractions?

Yes, regression tests are required to protect current behavior before executing cleanup passes, ensuring that removing dead code and needless abstractions does not introduce regressions or alter functionality.