Universal de-AI writing skill. Catches and rewrites the tells that expose
AI-generated text — forbidden words ("delve", "crucial", "landscape", "tapestry",
"Additionally"), forbidden patterns (rule of three, negative parallelism,
em-dash overuse, Title Case headings, inline-header bullets, emoji headers,
knowledge-cutoff disclaimers), and AI structure (Despite-its-X formula,
"is/are" replaced by "serves as / represents"). Works on any medium: landing
page copy, emails, DMs, LinkedIn posts, proposals, documentation, microcopy,
CTAs, FAQ. The references in this folder are the canonical source — read them,
then use your own judgment for the rewrite.
TRIGGERS — Use this skill when the user says:
- "de-ai this" / "de-ai-ify" / "remove the AI tells"
- "make it sound human" / "humanize this copy" / "sound less AI"
- "is this AI slop?" / "does this read like AI?"
- "rewrite without AI words" / "scrub the AI from this"
- "anti-ai" / "anti-slop" / "no slop"
- "check this for AI tells" / "audit this copy"
- Before publ
2026-05-22