“As an AI language model...”
caught red-handedNatural-language processing. Local first.
Your AI
has a
tell.
SlopSift maps the grammatical structure beneath a draft—not just words or parts of speech—to catch canned arguments, borrowed certainty, and suspiciously polished filler.
Starting the local parser…
Loading the on-device NLP model…
never uploaded corrective-antithesisunsupported-certaintymechanical-outlinevague-attributionai-vocabulary
More than a word list
It reads structure,
not vibes.
Many writing tools stop at word matching and basic parts of speech. SlopSift follows the relationships between words, so rules can recognize how a sentence makes its claim—not only which vocabulary it uses.
- 01
Build a dependency graph
A compact local model maps tokens, parts of speech, and the grammatical relationships holding the sentence together.
- 02
Match the construction
Authorable rules inspect the graph for structural tells. Every finding names what matched and the exact text that triggered it.
- 03
Keep judgment with the writer
Errors are strong tells. Warnings need attention. Notes are candidates—not a machine pretending to know who wrote the sentence.
Not every em dash is slop.
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.