faq-generator

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

FAQ Generator

FAQ生成器

Generate comprehensive, categorized FAQs from textbook content and chatbot-ready JSON exports. Place the FAQs into the file docs/faq.md. Log the results of the session to

logs/faq.md

从教材内容生成分类完整的FAQ，并导出可直接用于聊天机器人的JSON文件。将FAQ保存到文件docs/faq.md中，并将会话结果记录到

logs/faq.md

。

Purpose

用途

This skill automates FAQ creation for intelligent textbooks by analyzing course content, learning graphs, and glossary terms to generate relevant questions and answers. The skill organizes questions by category and difficulty, ensures Bloom's Taxonomy distribution across cognitive levels, provides answers with links to source content, and exports structured JSON data ready for RAG system integration.

该Skill通过分析课程内容、学习图谱和术语表来生成相关的问题与答案，为智能教材自动创建FAQ。它会按类别和难度组织问题，确保Bloom's Taxonomy在各个认知层面的分布，提供带有源内容链接的答案，并导出可直接集成到RAG系统的结构化JSON数据。

When to Use This Skill

何时使用该Skill

Use this skill after the following artifacts exist:

Course description has been finalized with a quality score above 70
Learning graph has been created
Glossary has been generated
At least 30% of chapter content has been written

Having these prerequisites ensures the FAQ generator has sufficient context to create meaningful, relevant questions. Trigger this skill when:

Building initial FAQ for a new textbook
Updating FAQ after significant content additions
Preparing content for chatbot or AI assistant integration
Identifying knowledge gaps in existing content

请在以下素材均已准备好后使用该Skill：

课程描述已定稿且质量得分高于70分
已创建学习图谱
已生成术语表
至少完成30%的章节内容

具备这些前置条件可确保FAQ生成器拥有足够的上下文来创建有意义、相关的问题。在以下场景触发该Skill：

为新教材构建初始FAQ
大幅添加内容后更新FAQ
为聊天机器人或AI助手集成准备内容
识别现有内容中的知识缺口

Markdown Formatting

Markdown格式规范

Use markdown header level one (#) for the FAQ title
Use markdown header level two (##) for each category
Use markdown header level three (###) for each individual question
Place the answer in the body text

Use the faq-template.md in the skill references section as your template.

使用一级Markdown标题（#）作为FAQ标题
使用二级Markdown标题（##）作为每个类别的标题
使用三级Markdown标题（###）作为每个独立问题
答案放在正文文本中

请使用技能参考部分的faq-template.md作为模板。

Critical Rule: No Anchor Links

重要规则：禁止使用锚点链接

!!! warning "NEVER Use Anchor Links" All links must point to files only, never with
#
anchor fragments.

Anchor links (`file.md#section-name`) break frequently because:

- Section headers change during content editing
- Anchors are case-sensitive and whitespace-sensitive
- MkDocs anchor auto-generation is unpredictable
- Broken anchors cause build warnings and confuse users

✅ **Correct:** `[See Ohm's Law](chapters/02-ohms-law/index.md)`

❌ **Wrong:** `[See Ohm's Law](chapters/02-ohms-law/index.md#series-circuits)`

!!! warning "绝对不要使用锚点链接" 所有链接必须仅指向文件，绝对不能带有
#
锚点片段。

锚点链接（`file.md#section-name`）经常失效，原因如下：

- 章节标题在内容编辑过程中会发生变化
- 锚点区分大小写且对空格敏感
- MkDocs的锚点自动生成规则不可预测
- 失效的锚点会导致构建警告并使用户困惑

✅ **正确写法：** `[查看欧姆定律](chapters/02-ohms-law/index.md)`

❌ **错误写法：** `[查看欧姆定律](chapters/02-ohms-law/index.md#series-circuits)`

Workflow

工作流程

Step 1: Assess Content Completeness

步骤1：评估内容完整性

Calculate a content completeness score (1-100 scale) to determine FAQ generation feasibility:

Required Inputs:

Read
```
docs/course-description.md
```
- Check for: title, audience, prerequisites, learning outcomes
- Verify Bloom's Taxonomy outcomes present
- Score: 25 points if complete
Read
```
docs/learning-graph/03-concept-dependencies.csv
```
- Validate DAG structure (no cycles)
- Count concepts and dependencies
- Score: 25 points if valid DAG with good connectivity
Read
```
docs/glossary.md
```
- Count terms (50+ = good, 100+ = excellent)
- Score: 15 points for 100+, 10 for 50-99, 5 for <50
Scan all
```
docs/**/*.md
```
files
- Calculate total word count
- Target: 10,000+ words for comprehensive FAQ
- Score: 20 points for 10k+, 15 for 5k-10k, 10 for <5k
Calculate concept coverage
- What % of learning graph concepts have related chapter content?
- Score: 15 points for 80%+, 10 for 60-79%, 5 for <60%

Content Completeness Score Ranges:

90-100: All inputs present with high quality
70-89: Core inputs present, some content gaps
50-69: Missing optional inputs or low word count
Below 50: Critical inputs missing

User Dialog Triggers:

Score < 60: Ask "Limited content available for FAQ generation. Continue with basic FAQ or wait for more content?"
No glossary: Ask "No glossary found. Generate FAQ anyway (limited technical questions) or create glossary first?"
Low word count: Ask "Only [N] words of content found. FAQ quality may be limited. Proceed?"

If user agrees to proceed with score < 60, generate FAQ but include disclaimer in quality report about limited content.

计算内容完整性得分（1-100分）以确定FAQ生成的可行性：

所需输入：

读取
```
docs/course-description.md
```
- 检查是否包含：标题、受众、前置要求、学习目标
- 验证是否包含Bloom's Taxonomy目标
- 得分：内容完整得25分
读取
```
docs/learning-graph/03-concept-dependencies.csv
```
- 验证DAG结构（无循环）
- 统计概念和依赖关系的数量
- 得分：有效且连接良好的DAG得25分
读取
```
docs/glossary.md
```
- 统计术语数量（100+ = 优秀，50-99 = 良好，<50 = 一般）
- 得分：100+得15分，50-99得10分，<50得5分
扫描所有
```
docs/**/*.md
```
文件
- 计算总字数
- 目标：10,000+字以生成全面的FAQ
- 得分：10k+得20分，5k-10k得15分，<5k得10分
计算概念覆盖率
- 学习图谱中的概念有多少百分比拥有相关的章节内容？
- 得分：80%+得15分，60-79%得10分，<60%得5分

内容完整性得分范围：

90-100：所有输入均存在且质量高
70-89：核心输入存在，部分内容有缺口
50-69：缺少可选输入或字数较少
低于50：缺少关键输入

用户对话触发条件：

得分<60：询问"可用于FAQ生成的内容有限。是继续生成基础FAQ还是等待更多内容？"
无术语表：询问"未找到术语表。是继续生成FAQ（技术问题有限）还是先创建术语表？"
字数较少：询问"仅找到[N]字的内容。FAQ质量可能受限。是否继续？"

如果用户同意在得分<60的情况下继续生成FAQ，请在质量报告中添加关于内容有限的免责声明。

Step 2: Analyze Content for Question Opportunities

步骤2：分析内容以寻找问题生成机会

Read and analyze all content sources to identify common question patterns:

From Course Description:

"What is this course about?" (scope)
"Who is this course for?" (audience)
"What will I learn?" (outcomes)
"What do I need to know first?" (prerequisites)

From Learning Graph:

"What is [concept]?" (definition questions)
"How does [concept A] relate to [concept B]?" (relationship questions)
"What do I need to know before learning [concept]?" (prerequisite questions)
"What comes after [concept]?" (progression questions)

From Glossary:

"What does [term] mean?" (terminology questions)
"What's the difference between [term A] and [term B]?" (comparison questions)
"Can you give an example of [term]?" (application questions)

From Chapter Content:

Identify recurring themes or topics
Note areas where students might struggle (complex concepts)
Extract common misconceptions if mentioned
Find practical application examples

From Existing FAQ (if present):

Read
```
docs/faq.md
```
if it exists
Preserve manually curated questions
Merge with new generated questions
Remove duplicates, keeping manual version when conflict

读取并分析所有内容来源，识别常见的问题模式：

从课程描述中：

"本课程的内容是什么？"（范围）
"本课程面向哪些人群？"（受众）
"我能学到什么？"（目标）
"我需要先掌握什么知识？"（前置要求）

从学习图谱中：

"[概念]是什么？"（定义类问题）
"[概念A]与[概念B]有什么关系？"（关系类问题）
"学习[概念]之前我需要掌握什么？"（前置知识类问题）
"学习完[概念]之后接下来学什么？"（进阶类问题）

从术语表中：

"[术语]是什么意思？"（术语类问题）
"[术语A]和[术语B]有什么区别？"（对比类问题）
"能举一个[术语]的例子吗？"（应用类问题）

从章节内容中：

识别重复出现的主题或话题
标记学生可能难以理解的领域（复杂概念）
提取文中提到的常见误解
寻找实际应用示例

从现有FAQ中（如果存在）：

如果
```
docs/faq.md
```
存在则读取该文件
保留人工整理的问题
将新生成的问题与现有问题合并
去除重复内容，冲突时保留人工版本

Step 3: Generate Question Categories

步骤3：生成问题类别

Create 6 standard categories aligned with learning progression:

1. Getting Started Questions (10-15 questions)

Target Bloom's levels: 60% Remember, 40% Understand

Course overview and objectives
Prerequisites and preparation
How to use the textbook
Navigation and structure
Time commitment and difficulty

2. Core Concept Questions (20-30 questions)

Target Bloom's levels: 20% Remember, 40% Understand, 30% Apply, 10% Analyze

Key concepts from learning graph (prioritize high-centrality nodes)
Fundamental principles
Concept relationships and dependencies
How concepts build on each other

3. Technical Detail Questions (15-25 questions)

Target Bloom's levels: 30% Remember, 40% Understand, 20% Apply, 10% Analyze

Terminology from glossary
Definitions and explanations
Technical comparisons
Specification details

4. Common Challenges (10-15 questions)

Target Bloom's levels: 10% Remember, 30% Understand, 40% Apply, 20% Analyze

Difficult concepts requiring extra explanation
Common misconceptions
Troubleshooting scenarios
Error resolution

5. Best Practice Questions (10-15 questions)

Target Bloom's levels: 10% Understand, 40% Apply, 30% Analyze, 15% Evaluate, 5% Create

How to apply concepts effectively
Recommended approaches
When to use specific techniques
Real-world applications

6. Advanced Topics (5-10 questions)

Target Bloom's levels: 10% Apply, 30% Analyze, 30% Evaluate, 30% Create

Complex integrations
Edge cases
Performance optimization
Future directions

创建6个与学习进度对齐的标准类别：

1. 入门类问题（10-15个）

目标Bloom's Taxonomy层级：60% 记忆，40% 理解

课程概述与目标
前置要求与准备工作
教材使用方法
导航与结构
时间投入与难度

2. 核心概念类问题（20-30个）

目标Bloom's Taxonomy层级：20% 记忆，40% 理解，30% 应用，10% 分析

学习图谱中的关键概念（优先选择中心性高的节点）
基本原理
概念间的关系与依赖
概念如何相互构建

3. 技术细节类问题（15-25个）

目标Bloom's Taxonomy层级：30% 记忆，40% 理解，20% 应用，10% 分析

术语表中的术语
定义与解释
技术对比
规格细节

4. 常见挑战类问题（10-15个）

目标Bloom's Taxonomy层级：10% 记忆，30% 理解，40% 应用，20% 分析

需要额外解释的复杂概念
常见误解
故障排查场景
错误解决方法

5. 最佳实践类问题（10-15个）

目标Bloom's Taxonomy层级：10% 理解，40% 应用，30% 分析，15% 评估，5% 创造

如何有效应用概念
推荐方法
何时使用特定技术
实际应用场景

6. 高级主题类问题（5-10个）

目标Bloom's Taxonomy层级：10% 应用，30% 分析，30% 评估，30% 创造

复杂集成
边缘情况
性能优化
未来发展方向

Step 4: Generate Questions and Answers

步骤4：生成问题与答案

For each category, generate questions following these guidelines:

Question Format:

Use level-2 headers (##)
Write as actual questions (end with ?)
Make questions specific and searchable
Use terminology from glossary
Keep questions concise (5-15 words)

Answer Format:

Use a level 3 markdown header (###) for each question
Write complete, standalone answers
Include examples for 40% of answers
Link to relevant sections (target: 60%+ linked)
Target length: 100-300 words
Use clear, direct language
Address the question fully

Bloom's Taxonomy Guidelines:

Remember: Recall facts, terms, basic concepts

"What is [concept]?"
"What does [term] mean?"
"What are the components of [system]?"

Understand: Explain ideas or concepts

"How does [concept] work?"
"Why is [concept] important?"
"What is the difference between [A] and [B]?"

Apply: Use information in new situations

"How do I [perform task]?"
"When should I use [technique]?"
"What's an example of [concept] in practice?"

Analyze: Draw connections among ideas

"What is the relationship between [A] and [B]?"
"How does [concept] relate to [other concept]?"
"What are the underlying causes of [issue]?"

Evaluate: Justify a decision or stance

"Which approach is best for [scenario]?"
"What are the trade-offs of [technique]?"
"How do I choose between [A] and [B]?"

Create: Produce new or original work

"How would I design a [system] that [requirements]?"
"What's the best way to combine [concepts]?"
"How can I adapt [technique] for [new context]?"

Answer Quality Checklist:

Use correct markdown headers for title, categories and questions
Directly answers the question
Uses terminology from glossary consistently
Includes example if concept is abstract (40% target)
Links to relevant chapter file (60% target) - NO anchor fragments
Appropriate length (100-300 words)
Clear and understandable for target audience
Accurate based on textbook content
No jargon unless defined in glossary
Zero links with
#
anchors (hard requirement)

针对每个类别，遵循以下指南生成问题：

问题格式：

使用二级标题（##）
以真实问题的形式撰写（以问号结尾）
问题要具体且便于搜索
使用术语表中的术语
问题要简洁（5-15个单词）

答案格式：

每个问题使用三级Markdown标题（###）
撰写完整、独立的答案
40%的答案需包含示例
链接到相关章节（目标：60%+的答案带有链接）
目标长度：100-300字
使用清晰、直接的语言
完整回答问题

Bloom's Taxonomy指南：

记忆： 回忆事实、术语、基本概念

"[概念]是什么？"
"[术语]是什么意思？"
"[系统]的组成部分有哪些？"

理解： 解释想法或概念

"[概念]如何工作？"
"[概念]为什么重要？"
"[A]和[B]有什么区别？"

应用： 在新场景中使用信息

"我如何[执行任务]？"
"我应该何时使用[技术]？"
"[概念]在实际中的例子是什么？"

分析： 梳理想法之间的联系

"[A]和[B]之间的关系是什么？"
"[概念]与[其他概念]有什么关联？"
"[问题]的根本原因是什么？"

评估： 证明决策或立场的合理性

"哪种方法最适合[场景]？"
"[技术]的权衡是什么？"
"我如何在[A]和[B]之间做出选择？"

创造： 产出新的或原创的成果

"我如何设计一个满足[需求]的[系统]？"
"组合[概念]的最佳方式是什么？"
"我如何调整[技术]以适应[新场景]？"

答案质量检查清单：

标题、类别和问题使用正确的Markdown标题
直接回答问题
始终如一地使用术语表中的术语
如果概念抽象，包含示例（目标40%）
链接到相关章节文件（目标60%）- 绝对不要使用锚点片段
长度合适（100-300字）
目标受众易于理解
基于教材内容准确无误
除非在术语表中定义，否则不使用行话
绝对没有带
#
的链接（硬性要求）

Step 5: Create FAQ File

步骤5：创建FAQ文件

Generate

docs/faq.md

with proper structure:

markdown

undefined

生成结构规范的

docs/faq.md

：

markdown

undefined

[Course Name] FAQ

[课程名称] FAQ

Getting Started Questions

入门类问题

What is this course about?

本课程的内容是什么？

[Answer with overview, linking to course description]

[包含课程概述的答案，链接到课程描述]

Who is this course for?

本课程面向哪些人群？

[Answer describing target audience]

[Continue with 10-15 Getting Started questions...]

[描述目标受众的答案]

[继续添加10-15个入门类问题...]

Core Concepts

核心概念

What is a [Key Concept]?

[关键概念]是什么？

[Answer with definition and example, linking to chapter]

[Continue with 20-30 Core Concepts questions...]

[包含定义和示例的答案，链接到章节]

[继续添加20-30个核心概念类问题...]

Technical Detail Questions

技术细节类问题

[Continue with terminology and technical questions...]

[继续添加术语和技术类问题...]

Common Challenge Questions

常见挑战类问题

[Continue with troubleshooting questions...]

[继续添加故障排查类问题...]

Best Practice Questions

最佳实践类问题

[Continue with application questions...]

[继续添加应用类问题...]

Advanced Topic Questions

高级主题类问题

[Continue with advanced questions...]


**Formatting Requirements:**

- Use level-1 header for title
- Use level-2 headers for category names
- Use level-3 headers for questions
- Use body text for answers
- Use markdown links to chapter files: `[text](path.md)` - **NEVER use anchor links**
- Use bold for emphasis: `**important term**`
- Use code blocks for code: ` ```language ```
- Maintain consistent spacing

**CRITICAL: No Anchor Links**

NEVER add anchor fragments (`#section-name`) to links. Anchors break frequently because:
- Section headers change during editing
- Anchors are case-sensitive and whitespace-sensitive
- MkDocs anchor generation is unpredictable
- Broken anchors cause build warnings and confuse users

✅ **Correct:** `[Ohm's Law](chapters/02-ohms-law/index.md)`
❌ **Wrong:** `[Ohm's Law](chapters/02-ohms-law/index.md#series-circuits)`

Link to the chapter file only. Users can navigate within the page themselves.

[继续添加高级类问题...]


**格式要求：**

- 使用一级标题作为标题
- 使用二级标题作为类别名称
- 使用三级标题作为问题
- 使用正文文本作为答案
- 使用Markdown链接到章节文件：`[文本](path.md)` - **绝对不要使用锚点链接**
- 使用粗体强调：`**重要术语**`
- 使用代码块展示代码：` ```language ```
- 保持一致的间距

**重要提示：禁止使用锚点链接**

绝对不要在链接中添加锚点片段（`#section-name`）。锚点经常失效，原因如下：
- 章节标题在编辑过程中会发生变化
- 锚点区分大小写且对空格敏感
- MkDocs的锚点生成规则不可预测
- 失效的锚点会导致构建警告并使用户困惑

✅ **正确写法：** `[欧姆定律](chapters/02-ohms-law/index.md)`
❌ **错误写法：** `[欧姆定律](chapters/02-ohms-law/index.md#series-circuits)`

仅链接到章节/页面文件。用户可自行在页面内导航。

Step 6: Generate Chatbot Training JSON

步骤6：生成聊天机器人训练用JSON

Create

docs/learning-graph/faq-chatbot-training.json

for RAG integration:

json

{
  "faq_version": "1.0",
  "generated_date": "YYYY-MM-DD",
  "source_textbook": "Course Name",
  "total_questions": 87,
  "questions": [
    {
      "id": "faq-001",
      "category": "Getting Started",
      "question": "What is this course about?",
      "answer": "Full answer text here...",
      "bloom_level": "Understand",
      "difficulty": "easy",
      "concepts": ["Course Overview", "Learning Objectives"],
      "keywords": ["course", "overview", "objectives", "goals"],
      "source_links": [
        "docs/course-description.md",
        "docs/index.md"
      ],
      "has_example": false,
      "word_count": 142
    },
    {
      "id": "faq-002",
      "category": "Core Concepts",
      "question": "What is a Learning Graph?",
      "answer": "A Learning Graph is...",
      "bloom_level": "Understand",
      "difficulty": "medium",
      "concepts": ["Learning Graph", "Concept Dependency"],
      "keywords": ["learning graph", "dependencies", "prerequisites"],
      "source_links": [
        "docs/concepts/learning-graph.md",
        "docs/glossary.md"
      ],
      "has_example": true,
      "word_count": 218
    }
  ]
}

JSON Schema Requirements:

Each question has unique ID (faq-001, faq-002, etc.)
Category matches one of 6 standard categories
Bloom level from 6-level taxonomy
Difficulty: easy, medium, hard
Concepts list from learning graph
Keywords for search optimization
Source links to original content
Boolean flag for example presence
Word count for answer

创建

docs/learning-graph/faq-chatbot-training.json

以集成到RAG系统：

json

{
  "faq_version": "1.0",
  "generated_date": "YYYY-MM-DD",
  "source_textbook": "Course Name",
  "total_questions": 87,
  "questions": [
    {
      "id": "faq-001",
      "category": "Getting Started",
      "question": "What is this course about?",
      "answer": "Full answer text here...",
      "bloom_level": "Understand",
      "difficulty": "easy",
      "concepts": ["Course Overview", "Learning Objectives"],
      "keywords": ["course", "overview", "objectives", "goals"],
      "source_links": [
        "docs/course-description.md",
        "docs/index.md"
      ],
      "has_example": false,
      "word_count": 142
    },
    {
      "id": "faq-002",
      "category": "Core Concepts",
      "question": "What is a Learning Graph?",
      "answer": "A Learning Graph is...",
      "bloom_level": "Understand",
      "difficulty": "medium",
      "concepts": ["Learning Graph", "Concept Dependency"],
      "keywords": ["learning graph", "dependencies", "prerequisites"],
      "source_links": [
        "docs/concepts/learning-graph.md",
        "docs/glossary.md"
      ],
      "has_example": true,
      "word_count": 218
    }
  ]
}

JSON Schema要求：

每个问题有唯一ID（faq-001, faq-002等）
类别与6个标准类别之一匹配
Bloom层级来自6级分类法
难度：easy, medium, hard
概念列表来自学习图谱
用于搜索优化的关键词
指向原始内容的源链接
表示是否包含示例的布尔标志
答案的字数

Step 7: Generate Quality Report

步骤7：生成质量报告

Create

docs/learning-graph/faq-quality-report.md

markdown

undefined

创建

docs/learning-graph/faq-quality-report.md

：

markdown

undefined

FAQ Quality Report

FAQ质量报告

Generated: YYYY-MM-DD

生成日期：YYYY-MM-DD

Overall Statistics

总体统计

Total Questions: 87
Overall Quality Score: 82/100
Content Completeness Score: 78/100
Concept Coverage: 73% (145/198 concepts)

问题总数： 87
总体质量得分： 82/100
内容完整性得分： 78/100
概念覆盖率： 73% (145/198个概念)

Category Breakdown

类别细分

Getting Started

入门类

Questions: 12
Avg Bloom's Level: Remember/Understand
Avg Word Count: 156

[Continue for all categories...]

问题数量：12
平均Bloom层级：记忆/理解
平均字数：156

[继续所有类别的统计...]

Bloom's Taxonomy Distribution

Bloom's Taxonomy分布

Actual vs Target:

Level	Actual	Target	Deviation
Remember	18%	20%	-2% ✓
Understand	32%	30%	+2% ✓
Apply	24%	25%	-1% ✓
Analyze	16%	15%	+1% ✓
Evaluate	7%	7%	0% ✓
Create	3%	3%	0% ✓

Overall Bloom's Score: 25/25 (excellent distribution)

实际分布 vs 目标分布：

层级	实际	目标	偏差
记忆	18%	20%	-2% ✓
理解	32%	30%	+2% ✓
应用	24%	25%	-1% ✓
分析	16%	15%	+1% ✓
评估	7%	7%	0% ✓
创造	3%	3%	0% ✓

总体Bloom得分：25/25（分布优秀）

Answer Quality Analysis

答案质量分析

Examples: 38/87 (44%) - Target: 40%+ ✓
Links: 54/87 (62%) - Target: 60%+ ✓
Avg Length: 187 words - Target: 100-300 ✓
Complete Answers: 87/87 (100%) ✓

Answer Quality Score: 24/25

示例占比： 38/87 (44%) - 目标：40%+ ✓
链接占比： 54/87 (62%) - 目标：60%+ ✓
平均长度： 187字 - 目标：100-300 ✓
完整答案占比： 87/87 (100%) ✓

答案质量得分：24/25

Concept Coverage

概念覆盖率

Covered (145 concepts): [list]

Not Covered (53 concepts):

[Concept 1] - Priority: High (high centrality in learning graph)
[Concept 2] - Priority: Medium
[Concept 3] - Priority: Low

Coverage Score: 22/30 (73% coverage)

已覆盖（145个概念）： [列表]

未覆盖（53个概念）：

[概念1] - 优先级：高（在学习图谱中中心性高）
[概念2] - 优先级：中
[概念3] - 优先级：低

覆盖率得分：22/30 (73%覆盖率)

Organization Quality

组织质量

Logical categorization: ✓
Progressive difficulty: ✓
No duplicates: ✓
Clear questions: ✓

Organization Score: 20/20

逻辑分类：✓
难度递进：✓
无重复内容：✓
问题清晰：✓

组织质量得分：20/20

Overall Quality Score: 82/100

总体质量得分：82/100

Coverage: 22/30
Bloom's Distribution: 25/25
Answer Quality: 24/25
Organization: 20/20

覆盖率：22/30
Bloom分布：25/25
答案质量：24/25
组织质量：20/20

Recommendations

建议

High Priority

高优先级

Add questions for high-centrality concepts: [list top 10]
Slightly increase Remember-level questions (+2%)

为中心性高的概念添加问题：[前10个列表]
略微增加记忆层级的问题（+2%）

Medium Priority

中优先级

Add examples to 3 more answers (to reach 47%)
Link 5 more answers to source content

为3个更多答案添加示例（以达到47%）
为5个更多答案添加源内容链接

Low Priority

低优先级

Consider adding 2-3 more Advanced Topics questions
Review question phrasing for searchability

考虑添加2-3个更多高级主题类问题
检查问题措辞以优化搜索性

建议添加的额外问题

Based on concept gaps, consider adding:

"What is [Uncovered Concept 1]?" (Core Concepts)
"How does [Uncovered Concept 2] work?" (Technical Details) [Continue with top 10 suggestions...]

undefined

基于概念缺口，考虑添加：

"[未覆盖概念1]是什么？"（核心概念类）
"[未覆盖概念2]如何工作？"（技术细节类） [继续添加前10个建议...]

undefined

Step 8: Generate Coverage Gaps Report

步骤8：生成覆盖率缺口报告

Create

docs/learning-graph/faq-coverage-gaps.md

markdown

undefined

创建

docs/learning-graph/faq-coverage-gaps.md

：

markdown

undefined

FAQ Coverage Gaps

FAQ覆盖率缺口

Concepts from learning graph not covered in FAQ.

学习图谱中未被FAQ覆盖的概念。

Critical Gaps (High Priority)

关键缺口（高优先级）

High-centrality concepts (many dependencies) without FAQ coverage:

[Concept Name]
- Centrality: High (12 dependencies)
- Category: Core Concepts
- Suggested Question: "What is [Concept] and why is it important?"

[Continue for all high-priority gaps...]

中心性高的概念（有许多依赖关系）但未被FAQ覆盖：

[概念名称]
- 中心性：高（12个依赖关系）
- 类别：核心概念类
- 建议问题："[概念]是什么，为什么它很重要？"

[继续所有高优先级缺口...]

Medium Priority Gaps

中优先级缺口

Moderate-centrality concepts without FAQ coverage:

[Continue...]

中心性中等的概念但未被FAQ覆盖：

[继续...]

Low Priority Gaps

低优先级缺口

Leaf nodes or advanced concepts without FAQ coverage:

[Continue...]

叶节点或高级概念但未被FAQ覆盖：

[继续...]

Recommendations

建议

Add questions for all critical gaps (15 concepts)
Consider adding questions for medium priority (23 concepts)
Low priority can be addressed in future updates (15 concepts)

undefined

为所有关键缺口添加问题（15个概念）
考虑为中优先级缺口添加问题（23个概念）
低优先级缺口可在未来更新中处理（15个概念）

undefined

Step 9: Validate Output Quality

步骤9：验证输出质量

Perform comprehensive validation:

1. Uniqueness Check:

Scan all questions for duplicates
Check for near-duplicates (>80% similar)
Report any duplicates found

2. Link Validation:

Extract all markdown links from answers
REJECT any links containing
#
anchor fragments - these must be removed
Verify each link target file exists
Report broken links
Links should be to files only (e.g.,
```
chapters/01-intro/index.md
```
), never with anchors

3. Bloom's Distribution:

Calculate actual distribution across all questions
Compare to target distribution
Score based on deviation (±10% acceptable)

4. Reading Level:

Calculate Flesch-Kincaid grade level for answers
Verify appropriate for target audience
Flag answers that are too complex or too simple

5. Answer Completeness:

Check each answer addresses the question
Verify no partial or incomplete answers
Ensure proper context provided

6. Technical Accuracy:

Cross-reference terminology with glossary
Verify consistency with chapter content
Flag any contradictions or inaccuracies

Success Criteria:

Overall quality score > 75/100
Minimum 40 questions generated
At least 60% concept coverage
Balanced Bloom's Taxonomy distribution (within ±15%)
All answers include source references
Chatbot JSON validates against schema
Zero duplicate questions
All internal links valid (file exists)
Zero anchor links - no
```
#
```
fragments in any links

执行全面验证：

1. 唯一性检查：

扫描所有问题以查找重复内容
检查近似重复（相似度>80%）
报告任何发现的重复内容

2. 链接验证：

从答案中提取所有Markdown链接
拒绝任何包含
#
锚点片段的链接 - 必须移除这些锚点
验证每个链接的目标文件是否存在
报告失效链接
链接应仅指向文件（例如
```
chapters/01-intro/index.md
```
），绝对不能带锚点

3. Bloom分布检查：

计算所有问题的实际分布
与目标分布对比
根据偏差评分（±10%可接受）

4. 阅读水平检查：

计算答案的Flesch-Kincaid年级水平
验证是否适合目标受众
标记过于复杂或过于简单的答案

5. 答案完整性检查：

检查每个答案是否回答了问题
验证是否没有部分或不完整的答案
确保提供了适当的上下文

6. 技术准确性检查：

将术语与术语表交叉引用
验证与章节内容的一致性
标记任何矛盾或不准确的内容

成功标准：

总体质量得分>75/100
至少生成40个问题
至少60%的概念覆盖率
平衡的Bloom's Taxonomy分布（偏差在±15%以内）
所有答案包含源引用
聊天机器人JSON符合Schema规范
无重复问题
所有内部链接有效（文件存在）
绝对没有锚点链接 - 任何链接中都没有
```
#
```
片段

Step 10: Update Navigation Section in mkdocs.yml (Optional)

步骤10：更新mkdocs.yml中的导航部分（可选）

If FAQ not in

mkdocs.yml

Read
```
mkdocs.yml
```
Check if "FAQ: faq.md" exists in nav
If missing, add in appropriate location (typically near end of the nav structure)
Preserve existing structure

yml

nav:
...
  - FAQ: faq.md
  - Glossary: glossary.md
  - License: license.md
  - References: references.md
  - Contact: contact.md

If quality reports were created in the learning-graph directory also add these to the mkdocs.yml file in appropriate places.

yml

nav:
  ...
  - Learning Graph:
    ...
    - FAQ Quality Report: learning-graph/faq-quality-report.md
    - FAQ Coverage Gaps: learning-graph/faq-coverage-gaps.md

如果FAQ未在

mkdocs.yml

中：

读取
```
mkdocs.yml
```
检查导航中是否存在"FAQ: faq.md"
如果缺失，添加到适当位置（通常在导航结构的末尾）
保留现有结构

yml

nav:
...
  - FAQ: faq.md
  - 术语表: glossary.md
  - 许可证: license.md
  - 参考资料: references.md
  - 联系我们: contact.md

如果在learning-graph目录中创建了质量报告，也请将这些报告添加到mkdocs.yml文件的适当位置。

yml

nav:
  ...
  - 学习图谱:
    ...
    - FAQ质量报告: learning-graph/faq-quality-report.md
    - FAQ覆盖率缺口: learning-graph/faq-coverage-gaps.md

Quality Scoring Reference

质量评分参考

Use this rubric to calculate overall FAQ quality score (1-100):

Coverage (30 points):

80%+ concepts: 30 points
70-79%: 25 points
60-69%: 20 points
50-59%: 15 points
<50%: 10 points

Bloom's Taxonomy Distribution (25 points):

Calculate deviation from target for each level, sum absolute deviations:

Total deviation 0-10%: 25 points
Total deviation 11-20%: 20 points
Total deviation 21-30%: 15 points
Total deviation >30%: 10 points

Answer Quality (25 points):

Examples: 40%+ = 7 pts, 30-39% = 5 pts, <30% = 3 pts
Links: 60%+ = 7 pts, 50-59% = 5 pts, <50% = 3 pts
Length: 100-300 words avg = 6 pts, acceptable range = 4 pts
Completeness: 100% = 5 pts, 95-99% = 4 pts, <95% = 2 pts

Organization (20 points):

Logical categorization: 5 pts
Progressive difficulty: 5 pts
No duplicates: 5 pts
Clear questions: 5 pts

使用以下评分标准计算FAQ总体质量得分（1-100）：

覆盖率（30分）：

80%+概念：30分
70-79%：25分
60-69%：20分
50-59%：15分
<50%：10分

Bloom's Taxonomy分布（25分）：

计算每个层级与目标的偏差，求和绝对偏差：

总偏差0-10%：25分
总偏差11-20%：20分
总偏差21-30%：15分
总偏差>30%：10分

答案质量（25分）：

示例占比：40%+ = 7分，30-39% = 5分，<30% = 3分
链接占比：60%+ = 7分，50-59% = 5分，<50% = 3分
长度：平均100-300字 = 6分，可接受范围 = 4分
完整性：100% = 5分，95-99% = 4分，<95% = 2分

组织质量（20分）：

逻辑分类：5分
难度递进：5分
无重复内容：5分
问题清晰：5分

Common Pitfalls to Avoid

常见误区

Duplicate Questions:

Don't ask the same question in different categories
Vary phrasing for related concepts
Merge similar questions into one comprehensive answer

Incomplete Answers:

Don't leave questions partially answered
Don't use "See chapter X for details" without summary
Always provide standalone context

Missing Links:

Don't forget to link answers to source content
Link to chapter files only - NEVER use anchor fragments (
```
#section-name
```
)
Verify all links point to files that exist before finalizing

Broken Anchor Links:

NEVER use anchor links like
```
file.md#section-name
```
Anchors break when headers are edited, renamed, or restructured
Link to the chapter/page file only:
```
file.md
```
This is a hard rule - no exceptions

Poor Question Phrasing:

Avoid vague questions like "How does it work?"
Use specific terminology from glossary
Make questions searchable

Bloom's Imbalance:

Don't over-focus on Remember/Understand
Include higher-order thinking questions
Balance across all 6 levels

重复问题：

不要在不同类别中询问相同的问题
对相关概念使用不同的措辞
将相似问题合并为一个全面的答案

答案不完整：

不要留下部分回答的问题
不要只使用"详见第X章"而不提供摘要
始终提供独立的上下文

缺失链接：

不要忘记将答案链接到源内容
仅链接到章节文件 - 绝对不要使用锚点片段（
```
#section-name
```
）
最终确定前验证所有链接指向的文件都存在

失效的锚点链接：

绝对不要使用
```
file.md#section-name
```
这样的锚点链接
当标题被编辑、重命名或重构时，锚点会失效
仅链接到章节/页面文件：
```
file.md
```
这是硬性规则 - 无例外

问题措辞不佳：

避免使用"它如何工作？"这样模糊的问题
使用术语表中的特定术语
使问题便于搜索

Bloom分布失衡：

不要过度关注记忆/理解层级
包含更高阶思维的问题
在所有6个层级间保持平衡

Output Files Summary

输出文件汇总

Required:

```
docs/faq.md
```
- Complete FAQ with categorized questions and answers

Recommended:

docs/learning-graph/faq-quality-report.md

- Quality metrics and recommendations

docs/learning-graph/faq-chatbot-training.json

- Structured data for RAG systems

Optional:

docs/learning-graph/faq-coverage-gaps.md

- Concepts without FAQ coverage

Updates to
```
mkdocs.yml
```
navigation if FAQ link missing

必需文件：

```
docs/faq.md
```
- 包含分类问题和答案的完整FAQ

推荐文件：

docs/learning-graph/faq-quality-report.md

- 质量指标和建议

docs/learning-graph/faq-chatbot-training.json

- 用于RAG系统的结构化数据

可选文件：

docs/learning-graph/faq-coverage-gaps.md

- 未被FAQ覆盖的概念

如果缺失FAQ链接，更新
```
mkdocs.yml
```
导航

Example Session

会话示例

User: "Generate an FAQ for my textbook"

Claude (using this skill):

Assesses content completeness (score: 78/100)
Reads course description, learning graph, glossary, chapters
Identifies question opportunities
Generates 87 questions across 6 categories
Creates answers with 44% examples, 62% links
Exports chatbot training JSON
Generates quality report (score: 82/100)
Creates coverage gaps report (53 uncovered concepts)
Reports: "Created FAQ with 87 questions covering 73% of concepts. Overall quality: 82/100. Added 38 examples and 54 links. See quality report for recommendations."

用户： "为我的教材生成FAQ"

Claude（使用该Skill）：

评估内容完整性（得分：78/100）
读取课程描述、学习图谱、术语表、章节内容
识别问题生成机会
生成6个类别的87个问题
创建包含44%示例、62%链接的答案
导出聊天机器人训练用JSON
生成质量报告（得分：82/100）
创建覆盖率缺口报告（53个未覆盖概念）
回复："已创建包含87个问题的FAQ，覆盖73%的概念。总体质量：82/100。添加了38个示例和54个链接。详见质量报告获取建议。"

faq-generator

Original

Translation

FAQ Generator

FAQ生成器

Purpose

用途

When to Use This Skill

何时使用该Skill

Markdown Formatting

Markdown格式规范

Critical Rule: No Anchor Links

重要规则：禁止使用锚点链接

Workflow

工作流程

Step 1: Assess Content Completeness

步骤1：评估内容完整性

Step 2: Analyze Content for Question Opportunities

步骤2：分析内容以寻找问题生成机会

Step 3: Generate Question Categories

步骤3：生成问题类别

Step 4: Generate Questions and Answers

步骤4：生成问题与答案

Step 5: Create FAQ File

步骤5：创建FAQ文件

[Course Name] FAQ

[课程名称] FAQ

Getting Started Questions

入门类问题

What is this course about?

本课程的内容是什么？

Who is this course for?

本课程面向哪些人群？

Core Concepts

核心概念

What is a [Key Concept]?

[关键概念]是什么？

Technical Detail Questions

技术细节类问题

Common Challenge Questions

常见挑战类问题

Best Practice Questions

最佳实践类问题

Advanced Topic Questions

高级主题类问题

Step 6: Generate Chatbot Training JSON

步骤6：生成聊天机器人训练用JSON

Step 7: Generate Quality Report

步骤7：生成质量报告

FAQ Quality Report

FAQ质量报告

Overall Statistics

总体统计

Category Breakdown

类别细分

Getting Started

入门类

Bloom's Taxonomy Distribution

Bloom's Taxonomy分布

Answer Quality Analysis

答案质量分析

Concept Coverage

概念覆盖率

Organization Quality

组织质量

Overall Quality Score: 82/100

总体质量得分：82/100

Recommendations

建议

High Priority

高优先级

Medium Priority

中优先级

Low Priority

低优先级

Suggested Additional Questions

建议添加的额外问题

Step 8: Generate Coverage Gaps Report

步骤8：生成覆盖率缺口报告

FAQ Coverage Gaps