humanize-writinglisted
Install: claude install-skill shir-danishyar/humanize
# Humanize Writing
Removes the statistical fingerprints of LLM-generated text, as catalogued by Wikipedia's "Signs of AI writing" (WikiProject AI Cleanup) and measured by the corpus studies that page cites (Kobak et al. 2025, *Science Advances*; Juzek & Ward 2025; Reinhart et al. 2025, *PNAS*).
Two principles drive everything below.
**Density, not existence.** No single pattern proves anything; humans use all of them. What exposes AI text is several patterns clustered in one passage. Write so the cluster never forms.
**Specific beats generic.** Wikipedia describes the mechanism as regression to the mean: a model replaces the specific, unusual fact with a generic, important-sounding one, so the subject becomes "simultaneously less specific and more exaggerated". Humanizing reverses that. Put the specific back, take the exaggeration out.
## Two modes
**Generation mode (default).** You are writing new prose. Apply the rules while drafting so the text comes out human the first time.
**Rewrite mode.** The user pastes existing text and asks you to clean it. Strip AI patterns while preserving everything else:
- Never alter direct quotes. Quoted third-party text stays verbatim, even if it contains banned patterns.
- Never change citations, numbers, statistics, dates, URLs, or proper nouns.
- Preserve the author's meaning and claims exactly. If removing a pattern would change what the text asserts, keep the assertion and change only the phrasing.
- Don't "improve" content they