$ show redbaronyyyyy-eng/humanizer-zh-academic
This repository provides a Claude Code Skill for reducing AIGC detection rates in Chinese academic writing. The Skill is available in two versions: a compact SKILL.md (~414 lines) for efficient daily use and a full SKILL_full.md (~554 lines) with detailed examples for maximum effectiveness. It does not contain executable code but offers a comprehensive set of rewriting rules based on 16 identified AI writing patterns across content, language, and style layers. The core methodology involves pattern recognition, constrained rewriting (7 hard constraints), a 4-step SOP (risk scanning → rewriting → rhythm check → noise preservation), and a 6-dimension quality scoring system. The Skill transforms input text by breaking AI predictability while preserving academic meaning and injecting human-like variability through techniques like theoretical repositioning, asymmetric restructuring, and judicious noise retention.
The LLM identified 1 files worth highlighting for reuse:
The compact Skill file provides a self-contained, reusable framework for reducing AI detection in Chinese academic text. It isolates 16 detectable AI patterns (e.g., theoretical over-reliance at segment starts, symmetric triads, vague attributions) with concrete rewriting examples, enforces 7 hard constraints (like ≤2 AI high-frequency words per segment), and guides a 4-step rewriting workflow. The component demonstrates non-obvious skill in pattern-based text transformation, requires zero dependencies beyond Claude Code, and can be applied to any Chinese academic document with domain-appropriate adjustments (via its academic register adaptation table). Its efficiency-focused design (~414 lines) makes it ideal for batch processing while preserving core effectiveness.