ai-slop-remover
Strips AI-generated code smells while preserving functionality. Removes verbose comments, redundant error handling, over-engineered patterns, generic phrasing.
ai-slop-remover cleans up the artifacts agents leave behind: defensive try/except: pass, three-paragraph comments restating the obvious, IUserServiceFactoryBuilder abstractions for a 30-line script, generic AI phrasing like "let's dive into" or "in this comprehensive guide."
Triggers
"remove AI slop", "de-AI", "humanize".
What it removes
- Verbose comments that just narrate code.
- Redundant error handling for impossible failures.
- Over-engineered abstractions for one-off code.
- Generic AI phrasing.
- "Helpful" docstrings that say nothing.
What it preserves
- Functionality — strict equivalence.
- Comments that explain a why, hidden constraint, or workaround.
- Validation at trust boundaries (user input, external APIs).
Source Notes
Aligned with upstream docs/reference/features.md#built-in-skills. Related: Configuration → comment-checker hook which runs the same kind of check at PostToolUse time.