humanize
FeaturedDetects and removes AI-generated writing patterns while preserving meaning and facts. Triggers on: "humanize text", "make this sound human", "remove AI patterns", "rewrite to sound natural", "make this less AI", "de-slop this", "not sound like ChatGPT", "human pass".
Install
Quality Score: 93/100
Skill Content
Details
- Author
- Mathews-Tom
- Repository
- Mathews-Tom/armory
- Created
- 5 months ago
- Last Updated
- 4 days ago
- Language
- Python
- License
- MIT
Integrates with
Bundled in these plugins
Similar Skills
Semantically similar based on skill content — not just same category
humanizer-en
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, passive voice, negative parallelisms, filler phrases, and the statistical signatures AI detectors measure (burstiness, lexical density and diversity, part-of-speech distribution, emotional range).
humanizer
Humanize text: strip AI-isms and add real voice. Improves genuine writing quality; does NOT reliably evade trained neural detectors (see Threat Model). TRIGGER when: user invokes "/humanize" or asks to "humanize", "remove AI writing patterns", "de-slop", "strip AI-isms", or make prose that reads as AI-generated sound natural and human. DO NOT TRIGGER when: user wants voice calibration in a specific author's style (use writing-voice skill), is writing code, generating commit messages, or producing technical documentation where voice is irrelevant.
humanizer
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, passive voice, negative parallelisms, and filler phrases.