Help us improve
Share bugs, ideas, or general feedback.
From harlan-agent-kit
Strip AI tells from prose so it reads as human-written. Use when user says "humanize this", "remove AI tells", "does this sound AI", "make this sound human", "de-slop", "sounds like ChatGPT", or before publishing any prose (blog, release notes, tweet, docs, email).
npx claudepluginhub harlan-zw/harlan-agent-kit --plugin harlan-agent-kitHow this skill is triggered — by the user, by Claude, or both
Slash command
/harlan-agent-kit:humanize-writing [text or file path to humanize][text or file path to humanize]The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Detect and remove the patterns that make text recognizably AI-written. The premise (from StoryScope, arXiv:2604.03136): AI prose stays detectable even after surface cleanup, because the *structural* choices give it away. Fixing em-dashes and "delve" is necessary but not sufficient.
Guides technical evaluation of code review feedback: read fully, restate for understanding, verify against codebase, respond with reasoning or pushback before implementing.
Share bugs, ideas, or general feedback.
Detect and remove the patterns that make text recognizably AI-written. The premise (from StoryScope, arXiv:2604.03136): AI prose stays detectable even after surface cleanup, because the structural choices give it away. Fixing em-dashes and "delve" is necessary but not sufficient.
Given text (in $ARGUMENTS or a file path), run both passes below, report what you flagged, then rewrite. Don't silently rewrite, show the user which tells you found so they learn to avoid them.
These are the well-known signatures. Fix them, but know they are the easy half.
This is what actually separates human from AI prose. Editing these requires real rewrites, not find-and-replace.
Not every tell applies everywhere. Weight by genre: