ai-slop-cleaner

Plan and execute regression-tested code cleanup workflows on changed-file scopes.

1|Updated Mar 15, 2026
One-click install
npx skills add https://github.com/Linnanli/xClaw --skill ai-slop-cleaner-linnanli
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ai-slop-cleaner
Source: https://github.com/Linnanli/xClaw/tree/main/.codex/skills/ai-slop-cleaner
Command: npx skills add https://github.com/Linnanli/xClaw --skill ai-slop-cleaner-linnanli

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

AI-generated code tends to accumulate slop—bloated logic, dead branches, and weak boundaries. This skill provides a disciplined workflow to plan, scope, and execute targeted cleanups that preserve behavior.

Core Features & Use Cases

  • Regression-tested cleanup passes that target the most impactful smells first
  • Scope-bounded edits based on changed-files or explicit file lists
  • Plan-first approach with explicit risks, reversibility, and traceability

Quick Start

Bound the scope with a changed-files list and run a single-pass, regression-tested cleanup workflow with verification after each smell.

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, use a regression-tested workflow that targets dead code and duplication while enforcing lint and type checks to preserve behavior. Bound the scope to changed files for reversibility.

What is the best way to refactor dead code and code smells in a targeted scope?

The best way to refactor dead code and code smells is applying a plan-first approach that scopes edits to changed files, executes bounded refactors, and verifies each smell with regression tests to ensure reversibility.

Can I run a code cleanup pass on just the files changed in my current branch?

Yes, you can run a code cleanup pass on just the changed files. The workflow supports scope-bounded edits based on a changed-files list or explicit file lists, enabling targeted and reversible refactors without touching the entire codebase.

Why does AI-generated code accumulate bloat and weak boundaries?

AI-generated code accumulates bloat and weak boundaries because models often produce bloated logic, dead branches, and duplicated code. A structured cleanup pipeline with plan-before-edit execution is needed to resolve these specific code smells.

Do I need regression tests before removing dead branches and duplication?

Yes, you need regression tests before removing dead branches and duplication. The cleanup workflow enforces regression tests and lint/type checks after each smell is addressed to verify that the refactor preserves the original behavior.