“As an AI language model...”
caught red-handedThe AI slop linter
Your AI
has a tell.
SlopSift catches the canned structure, borrowed certainty, and suspiciously polished filler that spellcheck misses.
draft_07.md6 problems
In today’s rapidly evolving landscape,delete the canned opening clear writing is more important than ever.compared with what?
This revolutionary approachpromotional vocabulary seamlessly empowers teamssay what it does to unlock their full potential.
38Reads like a press release written by a toaster.
corrective-antithesisunsupported-certaintymechanical-outlinevague-attributionai-vocabulary
No account. No upload.
Paste the evidence.
The same compact parser used by the CLI runs in your browser. Your draft stays on your device.
Ready when you are.
Run the sample to load the local parser.
It reads structure,
not vibes.
- 01
Parse the sentence
A small owned model maps words, parts of speech, and grammatical relationships.
- 02
Run explainable rules
Each finding names the construction it matched. No mystery score. No remote judge.
- 03
Grade the suspicion
Errors are strong tells. Warnings need attention. Notes are candidates, not convictions.
Not every dash is a crime.
Three paragraphs use the same canned outline.
probably slopAn actorless passive may be hiding responsibility.
worth a lookMeet writers where they write.
$
CLI
Glob files, lint Markdown, inspect code comments, and emit ESLint-shaped JSON in CI.
bunx slopsift .VS
VS Code
Diagnostics appear beside the sentence, with the same severity and rule name as the terminal.
CR
Chrome
Review text boxes and editable pages before the draft escapes into the internet.
AI
Agent skill
Let coding agents lint their own prose before they hand it back to a human.
Yes, AI helped build this.
Built by AI.
Edited on purpose.
That is the point. SlopSift is not an AI detector and it does not pretend to know who typed a sentence. It catches habits that make writing vague, inflated, repetitive, or weirdly certain. Human beings do those things too.
One command.
Several opinions.
Use --format json for machines, --level info for the full suspicious pile.