Documentation
README
Unslop
A Claude skill that removes signs of AI writing from English text. Not just the word-level tells ("delve", "it's important to note") but the structural ones: over-explained conclusions, template paragraphs, invented specifics. Calibrates to your personal voice.
GitHub About line: "English text humanizer for Claude: typography, vocabulary, structure. Calibrates to your voice. Built on the UMD / Google DeepMind study and Wikipedia's Signs of AI writing."
Why word-swapping doesn't work
Every humanizer promises to make AI text "sound human", and most of them swap vocabulary: "delve" out, "explore" in. There are two problems with that.
This is the opening of the README. Read the full README on GitHub.