humanizer

8.7

169

300

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, negative parallelisms, and excessive conjunctive phrases. Credits: Original skill by @blader - https://github.com/blader/humanizer

text-humanization

8.7

Rating

Installs

AI & LLM

Quick Review

Exceptional skill that provides comprehensive guidance for detecting and removing AI writing patterns. The description clearly conveys the skill's purpose and scope. Task knowledge is outstanding with 24 detailed pattern categories, each including problematic words/phrases, before/after examples, and specific rewrites. Structure is excellent with logical organization, though the single-file approach at ~400 lines is dense but manageable given the reference nature. Novelty is strong: manually identifying and fixing these patterns would require extensive prompting and multiple iterations; this skill encodes expert knowledge from Wikipedia's AI Cleanup project into a reusable asset. Minor improvement possible by splitting patterns into separate reference files, but current structure works well for a pattern-matching editorial task.