by voidborne-d · Agent Tool · ★ 305
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
免费本地 AI 文本去痕迹工具 | Chinese AI text detection & humanization. N-gram perplexity analysis, 20+ detection patterns, academic AIGC reduction (知网/维普/万方), 7 style transforms. Zero dependencies, runs locally.
| Stars | 305 |
| Forks | 27 |
| Language | Python |
| Category | Agent Tool |
| Quality Score | 54.4046403357471/100 |
| Open Issues | 9 |
| Last Updated | 2026-05-10 |
| Created | 2026-02-23 |
| Platforms | claude-code, python |
| Est. Tokens | ~117k |
Looking for a humanize-chinese alternative? If you're comparing humanize-chinese with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Free, open-source AI writing humanizer and detector. 55 patterns, 5 voices, a 0-100 AI-tell score, and nothing
AIGC 检测论文 AI 降率工具 - Claude Code Skill for academic paper AI detection and rewriting
AI-writing humanizer for KO/EN/ZH/JA
Pure instruction-pack skill wrapping Ai2's Asta MCP server (Semantic Scholar). Intent-to-tool routing, safe de
DOI → PDF resolver with 7-source fallback (Unpaywall, S2, arXiv, PMC, bioRxiv, publisher, Sci-Hub). Multi-agen
Semantic Scholar API wrapper for agents — search 200M+ papers, traverse citations, find authors. Python, rate-
Explore other popular agent tool tools:
humanize-chinese is 免费本地 AI 文本去痕迹工具 | Chinese AI text detection & humanization. N-gram perplexity analysis, 20+ detection patterns, academic AIGC reduction (知网/维普/万方), 7 style transforms. Zero dependencies, runs locally.. It is categorized as a Agent Tool with 305 GitHub stars.
humanize-chinese is primarily written in Python. It covers topics such as academic, agent-skill, ai-detection.
You can find installation instructions and usage details in the humanize-chinese GitHub repository at github.com/voidborne-d/humanize-chinese. The project has 305 stars and 27 forks, indicating an active community.
The top alternatives to humanize-chinese on Agent Skills Hub include humanizer-skill, AIGC-Detector-Pro, patina. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: