F*ck Slop

Remove distracting stock phrasing and fit the requested genre. Treat the catalog as house-style heuristics, not proof of a text’s origin.

Why this is a loop, not a style guide

Use a repeatable scan followed by semantic review:

1. Scan for candidates. Regex surfaces phrases to inspect; meaning and genre decide whether each is a defect.
2. Rewriting reintroduces slop. Ask a model to remove "it's not just X, it's Y" and it produces "this is less about X than Y" — the same move in a wig. So every rewrite gets re-scanned, and the loop runs until the scan is clean.

Workflow: Scan → Diagnose → Rewrite by meaning → Re-scan → (repeat) → Register check.

Phase 0: Fix the target

Before touching the text, establish: