by baibanbao · Claude Skill · ★ 68
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
git clone https://github.com/baibanbao/qu-ai-wei.git ~/.claude/skills/qu-ai-weiTaken from the project's README on GitHub. Check the security audit before running it.
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.
| Stars | 68 |
| Forks | 13 |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 59/100 |
| Last Updated | 2026-09-23 |
| Created | 2026-09-23 |
| Platforms | claude-code |
| Est. Tokens | ~2k |
去 AI 味 · qu-ai-wei 一个 Claude skill，清理中文稿子里的 AI 痕迹。合并三家规则，并把它们互相矛盾的地方一条条裁掉。 为什么又做一个 去 AI 味的规则集已经有几份，问题是它们互相打架。 一家说「AI 爱把段落写得一样长，真文章有毛边」；另一家拿 300 篇 AI 样本、117.9 万汉字、5 个模型实测，句长段长的离散度人机无差别。照前者改，你会为了制造参差去乱调句长；照后者改，你又会放过那些确实该删的东西。 类似的顶牛有七处：排比、被动句、破折号、抽象换具体、段首评论语、句首「其实」、毛边。这个 skill 做的事是把三家合到一起，冲突处给出裁决和依据，再按「稿子是谁的」分成两种模式。 三家来源 第一家是作者自用的写作系统，靠经验。另两家是开源项目，MIT。lieflat 靠语料实测——本 skill...
These tools work well together with qu-ai-wei for enhanced workflows:
Looking for a qu-ai-wei alternative? If you're comparing qu-ai-wei with other claude skill 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
免费本地 AI 文本去痕迹工具 | Chinese AI text detection & humanization. N-gram perplexity analysis, 20+ detection patterns
Deutscher Text-Humanizer für Claude Code & Codex. Redigiert KI-Floskeln, schützt deine Schreibstimme und prüft
Make AI output sound human. Strips AI-isms (sycophancy, stock vocab, hedging stacks, em-dash pileups), preserv
In today's rapidly evolving landscape, vale-ai-tells is a comprehensive, cutting-edge Vale style package that
Claude Code skill for building modern Android apps following best practices.
Explore other popular claude skill tools:
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: