Konata9

对中文文章进行深度润色，去除 AI 写作痕迹。分两层处理：(1) 调用 humanizer-zh 处理表层 AI 痕迹（用词选择、模板句式）；(2) 执行结构性去 AI 味检查（句子长度 方差、段落高度方差、过渡词多样性、AI 套话扫描、第二人称分布、口语插入、 结尾质量）。适用于所有中文内容创作项目的发布前润色环节。

对中文内容进行小红书和微信公众号的平台合规检查。扫描禁用词、灰色词汇、 最高级表述、外文专有名词格式、标题安全性等问题，输出违规报告和修改建议。 适用于所有需要在中文内容平台（小红书、公众号）发布内容的项目。

Predicts the next lottery numbers for Chinese lotteries like Double Color Ball (双色球) and Super Lotto (大乐透). Use this skill when user asks to predict lottery results in Chinese (e.g., "预测双色球", "大乐透推荐").

Comprehensive vulnerability analysis for npm packages across different versions. Use when Claude needs to: (1) Analyze security vulnerabilities for specific package versions, (2) Compare vulnerability counts across multiple versions of the same package, (3) Identify safe version ranges based on vulnerability thresholds, (4) Track vulnerability trends over version releases, (5) Work with npm, pnpm, or yarn package managers for audit analysis, or (6) Generate vulnerability reports and recommendations for dependency management.