Skip to main content

​
No-slop academic writing

“AI slop” is fluent text that says less than it seems to: delves into the intricate tapestry, plays a pivotal role, it is important to note that, three stacked hedges, and every sentence the same length. Reviewers recognize it immediately and trust the paper less. The unslop-academic-writing skill fixes this with a linter and an editing playbook.

​
How it works

  1. Measure. python scripts/slop_check.py draft.tex ignores math, citations and code, then reports each problem with a line number and rewrite hint, plus a slop index (under 5 is clean, over 30 is severe).
  2. Fix content before words. Replace vague claims with numbers, tie claims to evidence, and cut paragraphs that restate the field.
  3. Fix the words. Delete framing phrases, replace stock vocabulary, keep one hedge sized to the evidence, and use normal punctuation.
  4. Keep your voice. The skill calibrates to a sample of your own writing and your discipline’s norms.
  5. Re-measure and read aloud.

​
What it detects

​
Does it work?

See the slop benchmark on the benchmarks page. In short: with the skill in context, model-written abstracts had a much lower slop index and more of them scored “clean”. The linter is a checklist for recognizable slop, not an AI detector, and it cannot tell careful modern model output from human writing. !!! note “Integrity” This skill improves clarity and authorship. It is not a tool for hiding AI use. Follow your venue’s disclosure policy.