Skills

AI Slop Cleaner

Post-implementation cleanup that removes AI-generated bloat while preserving...

Install

npx skills add vibeeval/vibecosystem --skill ai-slop-cleaner -g -a claude-code -y
Category
Testing
Updated
3mo ago
License
MIT
Context cost
Mediumabout 3,000 tokens
Runs scripts
No, instructions only

What it does

Post-implementation cleanup that removes AI-generated bloat while preserving functionality. Runs pass-by-pass with test verification after each pass. Activate after kraken/spark complete a feature, or when a codebase needs hygiene work.

AI Slop Cleaner

AI code generation produces working code. It also produces unnecessary code alongside it. This skill removes the unnecessary parts while keeping everything that matters.

What Is "AI Slop"?

AI slop is code that:

  • Works, but shouldn't exist
  • Adds complexity without adding value
  • Was clearly generated to pad a response rather than solve a problem
  • Suggests the author wasn't thinking, just generating

Common slop categories and their signals:

CategorySignal
Dead importsImported but never referenced in the file
Unused variablesDeclared, never read
Commented-out codeBlocks of // old code or /* removed */
Debug remnantsconsole.log, print(), debugger, fmt.Println
Obvious comments// increment counter above count++
Redundant JSDoc@param name - the name above name: string
Premature abstractionsA factory that creates exactly one thing
One-use helpersPrivate function called exactly once, trivially inlinable
Overly generic types<T extends object> when T is always User
Over-parameterizedfn(a, b, c, d, e) where 4 params never vary
Unreachable branchesif (false) or if (isLoggedIn && !isLoggedIn)
Speculative featuresCode paths for requirements that don't exist
Copy-paste duplicationTwo blocks identical except one variable name
Placeholder remnantsTODO: implement, lorem ipsum, example data in prod

The Prime Directive

Tests are sacred. Never clean test files.

Tests exist to protect behavior. Any cleanup that breaks a test reveals that the "slop" was actually load-bearing. That is good information. The test wins.

Regression-Safe Workflow (Non-Negotiable)

BEFORE ANYTHING: Run full test suite → all tests must pass (baseline)
Read the whole SKILL.md on GitHub

More in Testing