skills.rest
dropsyoon
dropsyoonCOMMUNITY
Explore all skills by this author →
GitHub

ai-slop-cleaner

Removes duplicated code and unnecessary abstractions while preserving behavior via selective file lists and Git-based tracking.

Updated Apr 17, 2026
Search Tags:#code review#refactoring#regression testing#duplication#dead code#code cleanup#boundary fixes
One-click install
npx skills add https://github.com/dropsyoon/oh-my-claudecode --skill ai-slop-cleaner-dropsyoon
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ai-slop-cleaner
Source: https://github.com/dropsyoon/oh-my-claudecode/tree/main/skills/ai-slop-cleaner
Command: npx skills add https://github.com/dropsyoon/oh-my-claudecode --skill ai-slop-cleaner-dropsyoon

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It solves the problem of AI-generated code that works but feels bloated, repetitive, weakly tested, or over-abstracted, without changing the intended behavior.

Core Features & Use Cases

  • Regression-safe de-sloping workflow: preserves behavior by locking down with narrow regression tests (or a concrete verification plan) before making cleanup edits.
  • Deletion-first simplification: removes dead code, duplicates, needless wrappers, and boundary leaks in small, smell-focused passes.
  • Optional reviewer-only mode: in --review, it inspects the cleanup plan and evidence without performing high-impact self-approved edits.
  • Scope control for safety: supports bounding to an explicit file list (e.g., changed files from a Ralph session) so cleanup stays within the agreed surface.

Quick Start

Use this command: /oh-my-claudecode:ai-slop-cleaner src/auth --review

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 bloated AI-generated code without breaking existing behavior?▼

To clean up AI-generated code safely, lock down behavior with narrow regression tests first, then remove duplication, dead code, and needless abstractions in small, smell-focused passes. This preserves the original intended behavior.

What is the best way to remove dead code and duplication from AI-generated modules?▼

The best way to remove dead code and duplication is a deletion-first workflow that applies small, smell-focused refactoring passes. Bound the cleanup scope using an explicit file list to keep changes within the agreed surface area.

Can I review a code cleanup plan before applying changes to my files?▼

Yes, you can inspect the cleanup plan and verification evidence without applying edits by using a reviewer-only mode. This validates the proposed refactoring while preventing high-impact self-approved changes.

How do I run regression tests during AI code refactoring?▼

Run regression tests as an evidence gate before making cleanup edits. The workflow enforces a tests-first approach, verifying that narrow regression tests pass before removing needless wrappers or fixing boundary leaks.

Does bounded scope refactoring work for incremental code cleanup?▼

Bounded scope refactoring works for incremental cleanup by limiting changes to an explicit file list, such as changed files from a session. This keeps the de-slopping process focused and prevents unintended modifications outside the specified modules.

Related Skills

Explore More Software Engineering Skills→
Haohao-endHaohao-end
779

diagnose

Diagnose bugs and performance regressions by reproducing failures and proving hypotheses with evidence.

Community
Intermediate
Goblin1024Goblin1024
6

ai-slop-cleaner

Identify and remove AI-generated slop in changed files using a regression-tests-first cleanup workflow.

Community
Intermediate
solitude6060solitude6060

ai-slop-cleaner

Remove dead code and duplicated logic from AI-generated modules.

Community
Intermediate
heliohqheliohq
88

refactor

Refactor code to remove structural, quality, and efficiency smells without changing behavior.

Official
Advanced