AI Slop Checker
Paste a draft and get every AI-sounding pattern flagged with the exact line it appears in. No scores, no guessing about authorship — just named patterns you can check and fix.
Runs entirely in your browser. Your text is never uploaded or stored.
Named patterns are evidence you can check — not proof that AI wrote this.
Want the fixes done for you?
The detection rules on this page are adapted fromNo AI Slop, an MIT-licensed editing skill by Peter Yang. Install it into Claude Code or Codex and it will rewrite your draft to remove these patterns while preserving your voice — not just flag them.
Frequently asked questions
What is AI slop?
AI slop is the set of stock patterns that make writing feel machine-generated: binary contrasts ("It's not X. It's Y."), importance puffery ("marks a pivotal moment"), weasel attribution ("experts agree"), colon reveals, banned buzzwords like "delve" and "leverage", and endings that restate the whole piece. The patterns show up constantly in unedited AI drafts.
Does this tool detect whether AI wrote my text?
No, and that is deliberate. AI detectors guess and are often wrong. This checker names specific slop patterns and quotes the exact line for each one, so every finding is evidence you can verify yourself. Human writers produce these patterns too — the point is to remove them, whoever wrote them.
Is my text uploaded or stored anywhere?
No. The checker runs entirely in your browser with plain JavaScript. Your text never leaves your device, and nothing is logged or stored.
How do I fix the patterns it finds?
Each finding comes with a short fix. For a full rewrite that removes the patterns while keeping your voice, install the open-source No AI Slop skill by Peter Yang into Claude Code or Codex — the same rule set this checker is adapted from.