by weijt606 · Claude Skill · ★ 135
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
Featured in: Humanizer & Anti-Slop Skills
git clone https://github.com/weijt606/anti-vibe-writing.git
Taken from the project's README on GitHub.
None of the 44 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 44 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours.
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 | 135 |
| Forks | 11 |
| Language | Shell |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 60/100 |
| Last Updated | 2026-11-15 |
| Created | 2026-04-09 |
| Platforms | claude-code, cli, codex |
| Est. Tokens | ~12k |
anti-vibe-writing 本 README 提供中英文两个版本:中文(本页,默认)和 English。点上方徽章切换。 目标只有一个:让 AI 说话,倍儿地道。 一个用于去除文档"AI 生成感"的 agent 写作技能。同时支持中英文,并提供可选模式用于贴合特定作者的语言风格。 它最适合放在初稿之后做最终润色。Claude Code、Codex 等任何基于大模型的 agent 起完稿之后,由它收尾。目标不是把文字写得更花。目标是在不改原意的前提下,去掉那些明显的生成式痕迹:模板措辞、空泛抽象、咨询腔、过重的 Markdown 结构、过度分层的大纲,以及那种"什么都讲一点、什么都不下判断"的伪平衡。 如果默认的"干净模式"还不够,skill 还提供: 人味儿质感模式:在合适的位置注入倒装、语气词、残句、非标准标点等真人写作痕迹(可选)...
Looking for a anti-vibe-writing alternative? If you're comparing anti-vibe-writing 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.
Skill для AI-агентов (Claude Code, Codex, OpenClaw, Hermes): убирает 37 признаков AI-генерации из русского тек
AI-writing humanizer for KO/EN/ZH/JA
Делает русский текст после нейросети живым, сверяет числа, даты и цитаты, убирает скрытые символы и снижает ри
humanizer-ru: редактура русского текста для AI-агентов. Убирает канцелярит и шаблонные обороты, сверяет смысл
Email marketing skill for AI agents, by George Hartley (founded SmartrMail). Plans, writes, audits and sends e
Reusable project context and specialist workflows for the AI tools you already use. Agents, skills, rules and
Explore other popular claude skill tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 44 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: