zh-humanizer-literary: 中文去 AI 味与文采增强 Codex Skill，汲取 Mengke / 好事风格，让中文草稿更像人写

How to install zh-humanizer-literary

git clone https://github.com/mengke-wang/zh-humanizer-literary.git

Taken from the project's README on GitHub. Check the security audit before running it.

Security audit verdict: SAFE · quality 56/100

None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.

Quick Facts

About zh-humanizer-literary

中文去 AI 味与文采增强 Skill 一个 Codex 中文写作 skill，用来把中文草稿改得更像人写。 出品与方法设计：王梦珂 Mengke｜好事发生 App 开发者｜好事引力创始人 它会帮你去掉 AI 味、模板感和通用营销腔，同时保留事实、作者声音和可读结构。适合公众号、小红书、即刻短帖、报告、提案、课程稿、产品文案和日常编辑改稿。 核心气质是：温暖平实，具体有判断；有文采，但不鸡汤；像一个摸过真实事情的人，在帮读者把事情看清楚。 它不是无出处的通用润色器。它汲取了王梦珂 Mengke（好事发生 App 开发者、好事引力创始人）的大量公开表达，以及好事引力和好事发生手册的内容风格，提炼成一套更普适的中文写作方法。 一句安装 把这句话发给你的 AI： 手动安装 如果你已经在仓库目录里，也可以直接： 一句使用 也可以这样用： 它会做什么...

Compatible Skills

These tools work well together with zh-humanizer-literary for enhanced workflows:

• academic-humanizer — semantic(0.57)+complementary+rare_topics+similar_pop+shared_platform (65%)
• humanizer-de — semantic(0.48)+complementary+rare_topics+similar_pop+shared_platform (61%)
• remove-ai-flavor-writing-skill — semantic(0.69)+rare_topics+similar_pop+shared_platform (58%)
• humanize — semantic(0.36)+complementary+rare_topics+similar_pop+shared_platform (57%)

zh-humanizer-literary alternative? Top 6 similar tools

Looking for a zh-humanizer-literary alternative? If you're comparing zh-humanizer-literary with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

• remove-ai-flavor-writing-skill by B1lli · ⭐ 197

  去AI味 skill for Codex: a compact Chinese AI writing humanizer for AI味清理, template sentence shells, and fake eng

• humanizer-de by marmbiz · ⭐ 171

  Deutscher Text-Humanizer für Claude Code & Codex. Redigiert KI-Floskeln, schützt deine Schreibstimme und prüft

• bushiershi by jinhanbuilds · ⭐ 62

  对抗模型输出不良表达习惯的 Agent Skill

• patina by devswha · ⭐ 378

  AI-writing humanizer for KO/EN/ZH/JA

• humanizer-skill by Aboudjem · ⭐ 218

  Free, open-source AI writing humanizer and detector. 55 patterns, 5 voices, a 0-100 AI-tell score, and nothing

• unslop by MohamedAbdallah-14 · ⭐ 160

  Make AI output sound human. Strips AI-isms (sycophancy, stock vocab, hedging stacks, em-dash pileups), preserv

More Codex Skill Tools

Explore other popular codex skill tools:

• superset ⭐ 15.5k
• humanizer ⭐ 57.5k
• refly ⭐ 7.5k
• nano-banana-pro-prompts-recommend-skill ⭐ 1.9k
• pi-skills ⭐ 2.5k
• skillkit ⭐ 1.5k
• ai-maestro ⭐ 831
• upskill ⭐ 762
• Claude-to-IM-skill ⭐ 2.9k
• learning-opportunities ⭐ 2.4k

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. 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:

• SlowMist agent-security taxonomy
• Liu et al., An Empirical Study of Agent Skill Security (2026)
• Our census dataset (DOI 10.5281/zenodo.21292799) · Hugging Face mirror
• How we grade: all 42 rules, the source tiers and known limits
• Full methodology & who runs this