writing-anti-ai

Detect and rewrite AI writing patterns in English and Chinese prose.

Updated Oct 7, 2022
One-click install
npx skills add https://github.com/tamagusko/linux-cfg --skill writing-anti-ai-tamagusko
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: writing-anti-ai
Source: https://github.com/tamagusko/linux-cfg/tree/main/dotfiles/claude/skills/writing-anti-ai
Command: npx skills add https://github.com/tamagusko/linux-cfg --skill writing-anti-ai-tamagusko

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? AI-generated text contains predictable patterns—inflated symbolism, promotional language, vague attributions, and formulaic structures—that make prose sound robotic and generic. This Skill identifies those patterns and rewrites the text to sound natural and human-written. ## Core Features & Use Cases - Pattern Detection: Identifies 20+ AI writing patterns based on Wikipedia's "Signs of AI writing" guide, including AI vocabulary, negative parallelisms, rule-of-three structures, and superficial -ing analyses. - Bilingual Support: Handles both English and Chinese text with language-specific pattern references and examples. - Voice Injection: Goes beyond pattern removal to add personality, opinions, and varied rhythm so text doesn't become sterile. - Quality Scoring: Rates text on a 50-point scale across directness, rhythm, trust, authenticity, and density. - Use Case: Paste an AI-drafted product announcement and receive a rewritten version with specific facts, varied sentence lengths, and no filler phrases like "serves as a testament to" or "值得注意的是". ## Quick Start Ask the AI to humanize this text and remove AI writing patterns, then paste your draft.

Frequently Asked Questions about writing-anti-ai

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I remove AI writing patterns from text?

Scan the text for common AI patterns like inflated symbolism, vague attributions, and filler phrases, then rewrite each flagged section with direct statements and specific details. This Skill provides checklists and before/after examples for both English and Chinese.

What are the most common signs of AI-generated writing?

Common signs include words like "Moreover", "crucial", and "landscape", phrases like "serves as a testament to", negative parallelisms ("It's not just X, it's Y"), rule-of-three structures, em dash overuse, and vague attributions like "experts believe".

Does this AI text humanizer support Chinese writing?

Yes, it includes a complete Chinese pattern reference covering AI vocabulary like 此外 and 至关重要, copula avoidance with 作为/代表, and filler phrases like 值得注意的是. Examples show before/after rewrites for Chinese prose.

Can removing AI patterns make writing sound worse?

Yes, stripping patterns without adding voice produces sterile, soulless text. The Skill addresses this by injecting personality: varied sentence rhythm, first-person perspective where appropriate, opinions, and acknowledgment of mixed feelings.

How is humanized text quality scored?

Text is rated 1-10 on five dimensions: directness, rhythm, trust, authenticity, and density, for a 50-point total. Scores of 45-50 indicate AI patterns are removed, while below 35 means the text needs revision.