mcpField
A
ai-slop-cleaner

ai-slop-cleaner

github.com/zereightDevelopment2.1k57 installsUpdated today
Repository

About ai-slop-cleaner

AI Slop Cleaner is a coding skill for removing bloat and duplication from working code while preserving behavior. It suits focused cleanup, with tests used to check regressions after changes.

Key features

  1. 01Deletion-first code cleanup
  2. 02Duplicate and dead code removal
  3. 03Scope-bounded changes
  4. 04Tests before and after edits
  5. 05Reviewer-only findings mode

Use cases

  1. 01Remove unused code from a working project
  2. 02Simplify repeated or over-abstracted logic
  3. 03Review cleanup candidates without editing

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/zereight/gitlab-mcp --skill ai-slop-cleaner

After installing, type/ai-slop-cleanerin Claude Code to confirm it loaded.

Details

From the project README

AI Slop Cleaner

Clean AI-generated code slop without changing behavior. Deletion-first workflow with regression safety.

When to Use

  • Code that works but feels bloated, repetitive, or over-abstracted
  • Duplicate logic, dead code, wrapper layers, boundary leaks
  • --review for reviewer-only mode (no changes, just findings)

When NOT to Use

  • New feature build or product change
  • Broad redesign
  • Behavior is unclear and untestable

Principles

  • Preserve behavior unless explicitly asked for changes
  • Delete before refactoring — removal is safest
  • Scope-bounded: only clean what was specified
  • Regression-safe: verify tests pass after every change

Slop Signals

  • Unnecessary wrapper functions
  • Duplicated logic across files
  • Over-abstracted single-use helpers
  • Dead code / unreachable branches
  • Excessive comments restating obvious code
  • Premature abstractions (used only once)

Workflow

  1. Identify target files/scope
  2. Run existing tests (baseline)
  3. Apply deletions first (dead code, unused imports)
  4. Simplify remaining code (reduce nesting, merge duplicates)
  5. Re-run tests after each change
  6. Report what was cleaned and verification results

Comments

Markdown supported