Identify and Humanize AI-Generated Prose
Modern LLMs have specific stylistic signatures—often called "AI slop"—that make content feel robotic, overly formal, or repetitive. The AI Tell Detector is a specialized diagnostic tool designed for developers, editors, and technical writers who need to audit drafts for these recognizable patterns before publication.
What it does
Using a combination of pattern-matching scripts and cadence analysis, the skill scans your Markdown or text files to identify specific linguistic "tells." It doesn't just give a generic "AI score"; it provides a line-level audit of structural and vocabulary issues that trigger human suspicion.
- Vocabulary Auditing: Flags overused AI-isms like "delve," "tapestry," "testament," and "comprehensive."
- Structural Analysis: Identifies uniform sentence lengths and repetitive antithesis constructions (e.g., "Not only X, but also Y").
- Punctuation & Syntax: Detects em-dash overuse and excessive hedging phrases that dilute your message.
- Actionable Feedback: Every finding includes a specific suggestion for how to revise the text for a more natural, human flow.
Why use this skill?
While standard AI detectors provide a "pass/fail" percentage, this skill acts as a mechanical editor. It shows you exactly why a piece of writing feels "off," allowing you to maintain your voice while removing the artifacts of LLM generation. It supports any text or Markdown-based workflow and is optimized for technical documentation and blog drafts.