Menu
把整本书提炼成结构化精华内容——按阅读目的决定保留什么，AI 逐章提取关键知识点，构建知识图谱串联概念，多角色答辩式校验摘要。
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Use when users ask to design a logo, create a wordmark, generate typographic logo, make text-based brand identity, or request AI image prompts for logo design where the text itself forms the graphic. Triggers: "logo", "wordmark", "字标", "文字logo", "创意logo", "LOGO设计", "AI生图生成logo", "文字图形logo".
📋 GESP试卷处理：从官网下载PDF→提取全文→检查流程图→创建标准化文件(.md/.json/答案.md) | 触发：GESP、真题、试卷处理、gesp真题
Use this skill only for scheduled or recurring tasks. Manage jobs with qwenpaw cron list/create/get/state/pause/resume/delete/run, and always pass --agent-id explicitly.
Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of "Word doc", "word document", ".docx", or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a "report", "memo", "letter", "template", or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.
Generate AI-implementable product requirement documents (PRDs) from one-line product ideas, vague app/site/tool requests, or feature concepts. Use when the user asks for PRD, 产品需求文档, 需求文档, AI 可执行 PRD, 产品规格, MVP 方案, app/site/tool planning, or developer handoff docs for AI coding assistants.
为GESP等级考试生成作业卷子，包含选择/判断/编程题。知识点定制，答案随机分布防猜测。
| name | AI读书 |
| description | 把整本书提炼成结构化精华内容——按阅读目的决定保留什么，AI 逐章提取关键知识点，构建知识图谱串联概念，多角色答辩式校验摘要。 |
| metadata | {"slug":"ai-reader","trigger":"读书、阅读、提炼、摘要、知识图谱、书摘、拆书"} |
读书, 提炼, 知识图谱, 电子书, 结构化笔记
用户提供图书文件（EPUB/MD/TXT/PDF），AI 逐章提取关键知识单元，构建跨章节概念关联知识图谱，输出结构化摘要。无需额外配置 LLM 供应商。
pdftotext（poppler-utils）：
sudo apt install poppler-utils # Ubuntu/Debian
brew install poppler # macOS
# 提取章节
python3 modules/extract_book.py 图书.pdf --pretty
# 按 modules/02-chunk.md → 03-graph.md → 04-review.md → 05-output.md 依次执行
输入：算法启蒙.pdf，阅读目的 = "关注教育方法"
执行流程：
① extract_book.py → 7 章节（前言 + ch1-ch6）
② 逐章精读 → 每章提取 4-6 个知识单元 + 反直觉点
③ 概念串联 → 14 条概念连线 + 3 条贯穿线索（"蛇"）
④ 多角校验 → AI 撰写摘要 → 用户提问 → AI 答辩补充
⑤ 输出笔记 → 《算法启蒙书》读书笔记.md
输出片段（知识图谱）：
| 二分策略 | → 实例 → | Wordle 猜词 | ch1 |
| 递归调用栈 | = 天然决策树 | 回溯法数据管理 | ch2 |
| 剪枝 | → 效果 → | 同等时间看得更远 | ch6 |
详细步骤见 modules/ 中各文件：
| 阶段 | 文件 | 说明 |
|---|---|---|
| Phase 1 文本提取 | modules/extract_book.py | 解析图书为章节 JSON |
| Phase 2 逐章精读 | modules/02-chunk.md | 每章提取知识单元 |
| Phase 3 概念串联 | modules/03-graph.md | 跨章节构建知识图谱 |
| Phase 4 多角校验 | modules/04-review.md | 答辩式审查摘要 |
| Phase 5 成果输出 | modules/05-output.md | 结构化读书笔记 |
| — 用户确认节点 | 各阶段开始前 | 询问用户是否满意当前结果 |
贯穿原则：每阶段完成后暂停，询问用户是否满意当前结果，确认后再进入下一阶段。