Quiz

测验

Generate interactive quizzes about the current codebase to test understanding.

生成关于当前代码库的交互式测验，以测试理解程度。

Reference Files

参考文件

File	Read When
`references/question-templates.md`	Default: question types by difficulty with concrete examples
`references/difficulty-calibration.md`	Applying difficulty and quantity settings, exploration depth, question stems
`references/scoring-and-output.md`	Step 5: scoring rubric, result formatting, final output template

文件	读取时机
`references/question-templates.md`	默认：按难度划分的问题类型及具体示例
`references/difficulty-calibration.md`	应用难度与数量设置、探索深度、问题题干
`references/scoring-and-output.md`	步骤5：评分标准、结果格式、最终输出模板

Configuration

配置

Collect from the user (ask only what was not provided):

收集用户提供的信息（仅询问未提供的内容）：

Number of Cards

卡片数量

Option	Cards	Best for
Fewer	5	Quick check, focused review
Standard	10	Balanced coverage
More	15	Deep dive, comprehensive review

Default: Standard (10)

选项	卡片数	适用场景
较少	5	快速检查、重点回顾
标准	10	均衡覆盖
较多	15	深度探究、全面回顾

默认：标准（10张）

Difficulty

难度

Level	Format	Question style
Easy	Multiple choice	What does X do? Where is Y defined?
Medium	Multiple choice + explanation	How does X interact with Y? What pattern is used for Z?
Hard	Open-ended + explanation	What would break if X changed? How would you refactor Y?

Default: Medium

等级	题型	问题风格
简单	选择题	X的作用是什么？Y定义在何处？
中等	选择题+解析	X与Y如何交互？Z使用了什么模式？
困难	开放式问题+解析	如果X发生变化，哪些功能会受影响？你会如何重构Y？

默认：中等

Workflow

工作流

Copy this checklist to track progress:

text

Quiz progress:
- [ ] Step 1: Gather configuration
- [ ] Step 2: Explore the codebase
- [ ] Step 3: Generate questions
- [ ] Step 4: Present quiz interactively
- [ ] Step 5: Score and summarize

复制此清单以跟踪进度：

text

测验进度：
- [ ] 步骤1：收集配置信息
- [ ] 步骤2：探索代码库
- [ ] 步骤3：生成问题
- [ ] 步骤4：交互式呈现测验
- [ ] 步骤5：评分与总结

Step 1: Gather configuration

步骤1：收集配置信息

Ask the user for card count and difficulty. Use defaults if not specified. Accept informal phrasing ("give me a hard quiz", "just 5 questions").

If the user provides both values upfront, skip straight to Step 2.

询问用户卡片数量和难度。若未指定则使用默认值。接受非正式表述（如"给我一个困难的测验"、"只要5个问题"）。

如果用户预先提供了两个值，直接跳至步骤2。

Step 2: Explore the codebase

步骤2：探索代码库

Systematically scan the project to build a question pool:

Read the project structure (directories, key files, entry points)
Identify the primary language(s), framework(s), and tooling
Read key files: configuration, entry points, core modules, tests
Map dependencies and module boundaries
Note patterns: naming conventions, architecture style, error handling
Find non-obvious details: edge cases, workarounds, gotchas

Load

references/difficulty-calibration.md

for exploration depth and question strategy per level.

系统地扫描项目以构建问题库：

读取项目结构（目录、关键文件、入口点）
识别主要语言、框架及工具
读取关键文件：配置文件、入口点、核心模块、测试文件
梳理依赖关系与模块边界
记录模式：命名规范、架构风格、错误处理
发现非显而易见的细节：边缘情况、临时解决方案、易犯错误

加载

references/difficulty-calibration.md

以获取对应难度级别的探索深度和问题策略。

Step 3: Generate questions

步骤3：生成问题

Using

references/question-templates.md

, generate the configured number of questions at the selected difficulty. Apply calibration from

references/difficulty-calibration.md

.

Each question must:

Reference real code from the current codebase (file paths, function names, patterns)
Have one clear correct answer
Be answerable from the codebase alone (no external knowledge required)
Cover different parts of the codebase (avoid clustering)

For multiple-choice questions, provide 4 options (A, B, C, D) with plausible distractors drawn from real names in the project.

For medium and hard questions, prepare a brief explanation to show after the user answers.

Check every question against the quality checklist below. Remove or rewrite any that fail.

使用

references/question-templates.md

，生成符合配置数量和选定难度的问题。应用

references/difficulty-calibration.md

中的校准规则。

每个问题必须：

引用当前代码库中的真实代码（文件路径、函数名、模式）
有一个明确的正确答案
仅通过代码库即可解答（无需外部知识）
覆盖代码库的不同部分（避免集中在某一区域）

对于选择题，提供4个选项（A、B、C、D），干扰项需来自项目中的真实名称。

对于中等和困难难度的问题，准备一个简短的解析，在用户作答后展示。

对照下方的质量检查清单检查每个问题。移除或重写未通过的问题。

Step 4: Present quiz interactively

步骤4：交互式呈现测验

Present one question at a time. For each question:

Show the question number and total as a header (e.g., "Question 3/10")
For multiple choice (easy/medium): use
```
AskUserQuestion
```
with the question text and 4 options so the user can select an answer interactively
For open-ended (hard): show the question text and wait for a free-text response
After the user responds, show whether the answer was correct
Show the explanation with file:line references (medium and hard only)
Proceed to the next question

一次呈现一个问题。每个问题的处理流程：

显示问题序号和总数作为标题（例如："问题3/10"）
选择题（简单/中等难度）：使用
```
AskUserQuestion
```
工具，展示问题文本和4个选项，让用户可交互式选择答案
开放式问题（困难难度）：展示问题文本，等待用户输入自由文本答案
用户作答后，显示答案是否正确
展示解析并附带文件:行号引用（仅中等和困难难度）
进入下一个问题

Step 5: Score and summarize

步骤5：评分与总结

Load

references/scoring-and-output.md

for the result template.

After all questions are answered, present the final scorecard with score, rating, breakdown by area, and recommended next steps.

加载

references/scoring-and-output.md

获取结果模板。

所有问题作答完成后，呈现最终评分卡，包含分数、评级、各领域得分明细及后续建议。

Quality Checklist

质量检查清单

Every question must pass all of these:

Codebase-grounded — References a real file path, function, or pattern from the current project
Single focus — Tests one concept. If you need "and" to describe it, split it.
Unambiguous — Has exactly one correct answer. No trick questions.
Self-contained — Answerable from the codebase alone, no external knowledge required
Plausible distractors — Multiple-choice options use real names from the project, not random strings
Spread coverage — Questions cover different files and areas, no clustering
Difficulty-matched — Matches the cognitive level of the selected difficulty
No generated files — Never asks about lock files, node_modules, or build output
Explanation ready — Medium and hard questions have a prepared explanation with file:line references

每个问题必须全部满足以下要求：

基于代码库 — 引用当前项目中的真实文件路径、函数或模式
单一焦点 — 测试一个概念。如果需要用"和"来描述，拆分问题。
无歧义 — 仅有一个正确答案。无陷阱题。
自给自足 — 仅通过代码库即可解答，无需外部知识
合理干扰项 — 选择题选项使用项目中的真实名称，而非随机字符串
覆盖广泛 — 问题覆盖不同文件和区域，避免集中
难度匹配 — 符合选定难度的认知水平
排除生成文件 — 绝不询问锁文件、node_modules或构建输出相关问题
准备好解析 — 中等和困难难度的问题需附带包含文件:行号引用的解析

Anti-patterns

反模式

Do not ask questions about external libraries or frameworks (only the project's own code)
Do not ask questions that require running the code to answer
Do not reveal all questions at once (present one at a time, wait for response)
Do not skip the explanation on wrong answers (the quiz is for learning)
Do not ask trick questions or ambiguous questions with multiple valid answers
Do not repeat questions about the same file or function
Do not generate questions before exploring the codebase (Step 2 must complete first)

不要询问外部库或框架相关问题（仅针对项目自身代码）
不要询问需要运行代码才能解答的问题
不要一次性展示所有问题（一次一个，等待用户作答）
不要在用户答错时跳过解析（测验的目的是学习）
不要设置陷阱题或存在多个有效答案的歧义问题
不要重复询问同一文件或函数的问题
不要在探索代码库前生成问题（必须先完成步骤2）

quiz

Original

Translation