by Hyacehila · Agent Tool · ★ 80
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
去除中文文本中 AI 写作痕迹的 Agent Skill（基于 blader/humanizer 与 op7418/humanizer-zh）
| Stars | 80 |
| Forks | 2 |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 54.3143882402646/100 |
| Open Issues | 1 |
| Last Updated | 2026-09-04 |
| Created | 2026-07-13 |
| Platforms | claude-code |
| Est. Tokens | ~5k |
Looking for a humanizer-zh-next alternative? If you're comparing humanizer-zh-next 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.
Stop your AI from writing like AI. A universal system prompt eliminating every known LLM style tell — works wi
免费本地 AI 文本去痕迹工具 | Chinese AI text detection & humanization. N-gram perplexity analysis, 20+ detection patterns
Проверяемая гигиена вставки из чата для русского текста
Dynamic-memory-first collaborative AI framework for long-form story generation, chapter planning, and coherent
humanizer-ru: очеловечить русский AI-текст для Claude Code, Cursor, Codex и других AI-агентов. 64 признака ней
AI-writing humanizer for KO/EN/ZH/JA
Explore other popular agent tool tools:
humanizer-zh-next is 去除中文文本中 AI 写作痕迹的 Agent Skill（基于 blader/humanizer 与 op7418/humanizer-zh）. It is categorized as a Agent Tool with 80 GitHub stars.
You can find installation instructions and usage details in the humanizer-zh-next GitHub repository at github.com/Hyacehila/humanizer-zh-next. The project has 80 stars and 2 forks, indicating an active community.
humanizer-zh-next is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to humanizer-zh-next on Agent Skills Hub include anti-slop-writing, humanize-chinese, humanizer-ru. 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: