zhiweio

对全书全部章节（含前言/致谢/附录）依次进行去 AI 写作痕迹处理。 逐章调用 humanizer-zh 进行深度检测和修复，全程不间断循环直到全书覆盖完毕。 Use when user says "全书去AI味", "humanize all chapters", "去除AI痕迹", "humanize全书".

对全书全部章节（不含前言/致谢/附录）依次进行 review + rewrite 的完整循环。 先调用 review-chapter 审查一章，若任何小节未达到阈值，立即调用 rewrite-section 重写， 重写完成后重新审查确认通过，然后进入下一章。全程不间断，直到全书覆盖完毕。 Use when user says "全量审查重写", "review and rewrite all", "全书review", "从头到尾检查", or uses loop-related terms with review/rewrite.

对书籍章节进行内容质量审查，按 Part → Chapter → Section 粒度逐节评分。 检测内容过于简单、图表表格罗列无深入分析、叙事逻辑薄弱、前后衔接不足等问题。 Use when user asks to "审查章节", "review chapters", "内容质量检查", "检查写得怎样".

对书籍中未通过质量审查的章节（粒度为 H3 小节）进行深度重写。 使用 MCP context7 和 deepwiki 查阅相关技术文档补充知识深度， 梳理整章上下文确保重写内容不突兀独立。Use when user says "重写章节", "rewrite section", "深度重写", "rewrite chapters", or after review-chapter identifies failures.

Generate a comprehensive Markdown interview preparation guide covering three interview types — Deep-Probing Technical Q&A, Breadth Probe Questions, and Behavioral & Cultural Fit. Each question includes quantifiable Scoring Points and a structured Reference Answer, grounded in resume + JD + company research. Use when the user provides a Resume, JD Analysis, and Company Business Analysis and asks for an interview guide, interview prep, technical Q&A bank, or "how do I prepare for this interview".

Generate a highly targeted YAML resume from a Job Description. Use when the user provides a JD (job description, job posting, job ad, role description) and asks for a tailored resume, an updated resume, a resume polish, or a resume that matches the role.

Polish raw work experience or project descriptions into structured YAML timeline entries with deep business-technology integration using enhanced STAR (work) or 3W (projects). Every achievement leads with business context and demonstrates transferable problem-solving ability. Use when the user pastes raw notes about a past job, internship, role, project, or deliverable and asks to polish, structure, format, expand, or convert them to YAML.