cd /news/ai-tools/show-hn-deslop-skill-based-on-corpus… · home › topics › ai-tools › article
[ARTICLE · art-170575] src=github.com ↗ pub= topic=ai-tools verified=true sentiment=· neutral

Show HN: Deslop skill based on corpus-linguistics and psycholinguistics research

A developer released a "deslop" skill on Show HN that rewrites LLM-generated prose using published corpus-linguistics and psycholinguistics research, including Reinhart et al.'s comparison of Biber's grammatical features in human and model writing, Terčon & Dobrovoljc's survey of 44 studies, Clark, Martin & Mahowald's work on why AI text is hard to read, and Graphite's "AI Tells" study, whose data covers tell lists for nine current models. The skill is benchmarked against three corpora in which humans and models answered identical prompts: 9,984 web-article topics from Graphite, 24,322 questions from HC3 and 3,027 advice prompts from ELEPHANT. It ships with a scanner that runs before and after each revision to show which problems were fixed or newly introduced, catch dropped facts, and flag tells from the reviser's own model family.

read1 min views1 publishedNov 16, 2026

I vibed this deslop skill because I was getting increasingly annoyed that deslop skills for prose relied either on fitting prose into an overly restrictive format (simple-english and iso-24495) or telling AI to rewrite something without providing any tools in the skill to measure the outcome (which more often than not resulted in one slop being replaced with another).

This skill is based on published measurements of how LLM text differs from human text: Reinhart et al.’s comparison of Biber’s grammatical features in human and model writing, Terčon & Dobrovoljc’s survey of 44 studies, Clark, Martin & Mahowald’s work on why AI text is hard to read, and Graphite’s “AI Tells” study, whose released data includes tell lists for nine current models. It’s benchmarked against three corpora in which humans and models answered the same prompts: 9,984 web-article topics from Graphite, 24,322 questions from HC3 and 3,027 advice prompts from ELEPHANT.

It also ships with a scanner that runs before and after each revision. It shows which problems the revision fixed or newly caused, and it catches dropped facts and any tells from the reviser’s own model family.

Comments URL: [https://news.ycombinator.com/item?id=50516995](https://news.ycombinator.com/item?id=50516995)

Points: 1

── more in #ai-tools 4 stories · sorted by recency
── more on @graphite 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/show-hn-deslop-skill…] indexed:0 read:1min 2026-11-16 · —