Audit text for AI writing tells
audit_textScan non-fiction for AI-writing tells (banned words, chatbot patterns, structural issues) and get a tiered score with findings and strengths to guide targeted fixes.
Instructions
Deterministically scan a piece of non-fiction text for common AI-writing tells: banned hype vocabulary, chatbot fingerprints, and structural patterns (uniform paragraph length, stacked transitions, em-dash overuse, rule-of-three compulsion, and more), plus this installer's own banned/custom word lists from add_banned_word/add_custom_word (the 'global' list, merged with a style's own list if styleId is given), plus a repo-local .etincelrc/.etincelrc.json/etincel.config.json if one exists at or above the current directory (dictionary as code, reviewable and versioned). Returns a tier (green/yellow/orange/red), a numeric score, specific findings with severity and location, and a strengths signal (specificity density, concrete-vs-abstract ratio, sentence-rhythm variation). Read strengths too, not just findings: it's the counter-signal against fixing every flagged word into flat, sterile prose. Never a silent rewrite. Use this to show the user what's flagged and why, so they stay in control of any change; only rewrite what they ask you to rewrite.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | The text to audit. | |
| styleId | No | Style id (from list_styles) whose own banned/custom word list should merge with the installer's global list. Omit to use only the global list. | |
| register | No | Register to calibrate strictness against. Defaults to 'general'. |