ai-slop-cleaner

Refactor AI-generated outputs by removing duplication, dead code, boundary violations, and missing tests with regression-first workflow.

Updated Apr 24, 2026
One-click install
npx skills add https://github.com/RJJJJ/project2 --skill ai-slop-cleaner-rjjjj
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ai-slop-cleaner
Source: https://github.com/RJJJJ/project2/tree/main/.codex/skills/ai-slop-cleaner
Command: npx skills add https://github.com/RJJJJ/project2 --skill ai-slop-cleaner-rjjjj

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Remove AI-generated slop and over-abstracted patterns from code and docs by applying a disciplined, regression-tested cleanup workflow that preserves behavior while improving clarity and maintainability.

Core Features & Use Cases

  • Regression-tests-first: lock-in behavior by adding/running targeted tests before edits.
  • Scope-bounded cleanup: limit changes to the provided set of files or modules to prevent broad rewrites.
  • Structured passes: categorize issues (Duplication, Dead code, Boundary violations, Missing tests) and apply fixes in a safe, ordered sequence.
  • Audit-ready reporting: produce an evidence-dense summary of changes, tests, and residual risks for review.

Quick Start

Initiate a bounded cleanup pass on the provided changed files using a regression-tests-first approach.

Frequently Asked Questions about ai-slop-cleaner

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

FAQPage Schema
How do I refactor AI-generated code to remove slop without breaking existing behavior?

AI slop cleanup works by categorizing issues like duplication, dead code, and boundary violations, then applying fixes in a structured, ordered sequence. This process ensures maintainability improvements are auditable and do not introduce unintended regressions.

Can I limit AI code cleanup to specific files and modules to prevent broad rewrites?

After AI slop cleanup, you generate an audit-ready report summarizing applied changes, test results, and residual risks. This evidence-dense output provides a clear record for review, ensuring all modifications are fully traceable and verified.

What is the best way to clean up over-abstracted patterns introduced by AI code generators?

AI slop cleanup requires a caller-provided scope defining the files or modules to process. Providing this bounded scope ensures the cleanup workflow targets the correct code sections and prevents unintended modifications outside the specified boundaries.

Do I need regression tests before cleaning up AI-generated outputs?

For AI slop cleanup, scope-bounded limitations ensure the workflow only processes the caller-provided files or modules. This targeted approach prevents broad rewrites, but you must define explicit boundaries to avoid unintended modifications to external dependencies.