No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by LifelongLazyLearner · Codex Skill · ★ 547
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is qu-ai-wei safe to install? View the security audit →
去 AI 味（qu-ai-wei） 语言: 简体中文 Español ⚠️ 0.x 开发版（当前 v0.7.1）: qu-ai-wei 仍在迭代，规则、分类、API 都可能变动。欢迎提 issue / discussion / PR 反馈。 只支持简体中文。 繁體有自己的 AI 腔特征、用字偏好、排版规范，规则需要单独维护，留给后续版本。 扫掉简体中文里 AI 写作的痕迹，让稿子读着像人写的。当前原生支持 8 个 agent：Cursor、Claude Code、OpenAI Codex CLI、OpenCode、Kiro、Factory Droid、Slate、Hermes。 https://github.com/user-attachments/assets/24513c20-968d-437b-8ceb-1ac1f77f6ad6 ⚠️ 此 skill 能做什么，不能做什么 这是扫地机 + 打磨工,仍然不是雕刻刀。 当前 v0.7.1 的行为仍是「扫地机 + 打磨工」,但所有冲突统一按 的「冲突仲裁顺序」六级处理: ① 扫地机 —— 清除显眼 AI 污染（赋能 / 助力 / 让我们一起 / 璀璨画卷 / 🚀 emoji 列点 / 机械加粗 / 希望对您有帮助），让稿子从「一眼像 AI」变成「不像 AI 了」。 ② 打磨工（v0.6.0 新增） —— 在不虚构的前提下主动打磨：动词强化（ → ）、节奏重塑（打断机关枪节奏）、filler 切除（）、抽象换具体（仅限原文已有细节）、语序归位、语体匹配。合格线从"不像 AI 了"抬到"干净且精准"。
| Stars | 547 |
| Forks | 42 |
| Language | Shell |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 58.029914512492/100 |
| Open Issues | 2 |
| Last Updated | 2026-09-10 |
| Created | 2026-04-21 |
| Platforms | claude-code, cli, codex |
| Est. Tokens | ~15k |
Looking for a qu-ai-wei alternative? If you're comparing qu-ai-wei 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.
说人话｜中文优先的去 AI 味改写 skill：保事实、分场景、改完可直接发。Chinese-first rewrite skill for Codex / Claude Code / Cursor / ChatGPT
Local-first macOS app to browse, search, analyze, and resume supported AI coding-agent session history across
Convert AI coding agent sessions (Claude Code, Cursor, Codex, Gemini, OpenCode, Kimi Code, Hermes) into self-c
AI-writing humanizer for KO/EN/ZH/JA
humanizer-ru: очеловечить русский AI-текст для Claude Code, Cursor, Codex и других AI-агентов. 64 признака ней
Deutscher Text-Humanizer für Claude Code & Codex. Redigiert KI-Floskeln, schützt deine Schreibstimme und prüft
Explore other popular codex skill tools:
qu-ai-wei is 去 AI 味：去除简体中文 AI 写作痕迹 / Chinese humanizer skill. It is categorized as a Codex Skill with 547 GitHub stars.
qu-ai-wei is primarily written in Shell. It covers topics such as agent-skills, ai-writing, chinese.
You can find installation instructions and usage details in the qu-ai-wei GitHub repository at github.com/LifelongLazyLearner/qu-ai-wei. The project has 547 stars and 42 forks, indicating an active community.
qu-ai-wei is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to qu-ai-wei on Agent Skills Hub include shuorenhua, agent-sessions, claude-replay. 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: