Practice Quiz logo

Practice Quiz

Community
mingchen666
practice-quiz

This skill should be used when the user asks to "出题", "做练习", "生成测验", "刷题", "给我出几道题", "做几道题练练", "出一套练习", "按章节出题", "按题型出题", "选择题", "填空题", "计算题", "简答题", "测测我", "考考我对这章的掌握", "出几道巩固题", "帮我做课后练习", or when the user wants practice questions generated by chapter, type, or difficulty, with answers, explanations, and study-focused assessment.

Overview

Publishermingchen666
RepositoryReviva
Skill namepractice-quiz
Stars
293
Forks
31
Bundled files
9
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 9 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by mingchen666 on GitHub. Read the source before you install it.

Installation

Install the Practice Quiz AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/mingchen666/Reviva/tree/main/electron/builtin-assets/skills/practice-quiz
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/mingchen666/Reviva.git /tmp/Reviva
mkdir -p .claude/skills
cp -r /tmp/Reviva/electron/builtin-assets/skills/practice-quiz .claude/skills/practice-quiz
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Practice Quiz in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Practice Quiz on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Practice Quiz is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

练习与测验

按章节、题型、难度灵活生成练习题,附带答案与详细解析。

Purpose

帮助用户通过做题巩固知识、检测掌握程度、发现薄弱环节。不仅仅是出题,更重要的是通过练习促进学习。

可生成:

  • 选择题(单选 / 多选)
  • 填空题
  • 判断题
  • 简答题
  • 计算题
  • 分析题
  • 编程题
  • 综合混合题型

支持:

  • 即时答案 + 解析
  • 先做后批改模式
  • 难度分级
  • 按知识点出题
  • 干扰项设计

When to Use

Use this skill when the user asks to:

  • 生成练习题或测验
  • 按章节出题
  • 按题型出题
  • 刷题或做题巩固
  • 检测对某知识点的掌握
  • 做课后练习
  • 生成答案和解析
  • 生成干扰项或陷阱题
  • 按难度出题(基础/中等/拔高)

示例:

  • "给我出 10 道高数选择题。"
  • "按第三章内容出一套练习。"
  • "出几道微积分的计算题,中等难度。"
  • "帮我做这章的课后练习。"
  • "出 5 道填空题测测我对线性代数的掌握。"

When Not to Use

Do not use this skill when:

  • 用户只想理解某个概念,不想做题(→ 使用知识梳理或概念解释)
  • 用户想分析已有的错题(→ 使用错题与薄弱点)
  • 用户想要完整的模拟考试卷(→ 使用模拟考试与批改)
  • 用户想制定复习计划(→ 使用复习计划)
  • 用户想要考前速记材料(→ 使用考前输出)
  • 没有任何科目、章节或材料作为出题范围

如果用户说"出一套期末模拟卷",那是模拟考试的场景,应使用模拟考试与批改。 如果用户说"这几道题我做错了,帮我分析",那是错题分析的场景,应使用错题与薄弱点。

Inputs

用户可能提供:

  • 科目 / 章节 / 知识点范围
  • 教材、讲义、笔记等材料文件
  • 题型要求(选择/填空/判断/简答/计算/分析/编程)
  • 数量要求(默认 5-10 道)
  • 难度要求(基础/中等/拔高/综合,默认中等)
  • 是否需要答案和解析
  • 是否先做后批改
  • 特定知识点或考点的针对性出题

Missing Information Handling

未提供出题范围

markdown
可以帮你出题。请告诉我:

1. 科目和章节(如"高数第五章 定积分");
2. 题型(选择/填空/判断/简答/计算/可混合);
3. 数量(默认 5-10 道);
4. 难度(基础/中等/拔高,默认中等)。

如果有教材或讲义,也请提供,我能出更贴合材料的题目。

范围太广

markdown
可以,但"生物学"范围太大了。你想练习哪个部分?

- 细胞生物学
- 遗传学
- 生态学
- 人体生理
- 其他具体章节

告诉我具体范围,我能出更有针对性的题。

只说了"出题",没有任何上下文

markdown
好的,我来帮你出题。请补充以下信息:

1. 科目 / 章节 / 知识点?
2. 题型?(默认混合)
3. 数量?(默认 5 道)
4. 难度?(默认中等)
5. 是否需要答案和解析?

Document and Reference Handling

当用户提供材料时:

  1. 先用 Read 读取所有相关文件
  2. 以用户提供的材料为出题的主要依据
  3. 优先考查材料中的核心知识点
  4. 使用材料中的术语、公式、定义
  5. 不编造材料中没有的知识点或事实
  6. 材料不完整时,基于已有内容出题并标注覆盖范围有限
  7. 如果用户指定了章节,严格在该章节范围内出题

Question Design Principles

出题原则

  • 覆盖核心知识点,不重复考同一点
  • 题目表述清晰无歧义
  • 难度与用户要求匹配
  • 测试理解而非单纯记忆(除非用户要求)
  • 干扰项有合理的设计逻辑
  • 不出偏题、怪题(除非用户要求)

干扰项设计(选择题)

好的干扰项应该:

  • 基于常见错误理解设计
  • 与正确答案形式相近
  • 具有一定迷惑性
  • 每个干扰项都有明确的错误原因

避免:

  • 明显不相关的选项
  • 所有选项长度差异过大
  • 使用"以上都对/以上都不对"作为常规手段

Bloom 认知层级

层级说明对应难度
记忆识别、回忆基本事实基础
理解解释、归纳、比较基础-中等
应用在新情境中使用知识中等
分析分解、识别关系和模式中等-拔高
评价判断、论证、批评拔高
创造设计、构建、提出方案拔高

难度校准

  • 🟢 基础:直接套用公式/定义,一步计算,明确知识点
  • 🟡 中等:需要 2-3 步推理,或需要选择合适方法
  • 🔴 拔高:综合多个知识点,需要创造性思维,或有陷阱

Workflow

  1. 识别出题范围(科目、章节、知识点)
  2. 确定题型、数量、难度
  3. 如果提供了材料,先读取并提取核心知识点
  4. 设计题目,确保覆盖核心知识点
  5. 设计干扰项(选择题)或评分要点(主观题)
  6. 编写答案和解析
  7. 校验:答案正确、解析清晰、难度匹配、无歧义
  8. 分开输出题目和答案

Output Formats

选择题

markdown
### 第 {N} 题 🟡 中等

{题目内容}

A. {选项 A}
B. {选项 B}
C. {选项 C}
D. {选项 D}

> 考查知识点:{知识点名称}

答案与解析:

markdown
### 第 {N} 题

**答案:{X}**

**解析:**
{为什么选 X}

**干扰项分析:**
- A:{为什么错}
- B:{为什么错}
- C:{为什么错}

填空题

markdown
### 第 {N} 题 🟢 基础

{题目内容} __________

> 考查知识点:{知识点名称}

简答题

markdown
### 第 {N} 题 🔴 拔高

{题目内容}

> 考查知识点:{知识点名称}
> 建议用时:{X} 分钟

计算题

markdown
### 第 {N} 题 🟡 中等

{题目内容}

> 考查知识点:{知识点名称}
> 建议用时:{X} 分钟

答案与解析:

markdown
### 第 {N} 题

**答案:** {最终答案}

**解题步骤:**
1. {第一步}
2. {第二步}
3. {第三步}
...
**最终结果:** {答案}

**易错点:** {提醒}

Quality Criteria

好的练习题必须:

  • 事实准确,答案正确
  • 符合要求的难度级别
  • 与出题范围和材料一致
  • 题目表述清晰无歧义
  • 选择题干扰项设计合理
  • 解析讲清"为什么对"和"为什么错"
  • 覆盖核心知识点,不偏不怪
  • 有学习价值,促进理解

Constraints

  • 不编造事实、公式、定义或参考文献
  • 不超出用户指定的范围出题
  • 不把不确定的答案表述为确定的
  • 不出过于简单或过于刁钻的题(除非用户要求)
  • 不重复考查同一个知识点(除非用户要求)
  • 不在题目中使用歧义表述
  • 需要联网查最新事实且工具可用时使用搜索
  • 搜索不可用时明确说明而非猜测

Style Guidelines

默认风格:

  • 清晰
  • 结构化
  • 教育性
  • 准确
  • 实用
  • 友好

优先使用:

  • 简洁的题目表述
  • 清晰的标签和编号
  • 便于核对的答案格式
  • 强化学习的解析

避免:

  • 模棱两可的表述
  • 过于复杂的题干
  • 没有解析的答案
  • 超纲的内容

Example Interactions

示例 1:未提供范围

User:

text
给我出几道题。

Assistant:

markdown
好的,请告诉我:

1. 科目 / 章节 / 知识点?
2. 题型?(选择/填空/判断/简答/计算/混合)
3. 数量?(默认 5 道)
4. 难度?(🟢 基础 / 🟡 中等 / 🔴 拔高)

如果有教材或讲义,也请提供路径。

示例 2:按章节出题

User:

text
高数第三章,出 5 道选择题,中等难度。

Assistant 行为:

  1. 确认范围:高数第三章(微分中值定理与导数应用)
  2. 识别核心知识点
  3. 生成 5 道中等难度选择题
  4. 先输出题目,再输出答案与解析

示例 3:基于材料出题

User:

text
根据这份讲义出 10 道题,混合题型。

Assistant 行为:

  1. 读取讲义文件
  2. 提取核心知识点
  3. 按知识点分配题型
  4. 生成 10 道题,覆盖讲义重点
  5. 分开输出题目和答案解析

参考文件

规则

  • references/question-design-rules.md — 出题原则与干扰项设计
  • references/difficulty-calibration.md — 三级难度校准标准(基础/中等/拔高 + Bloom 认知层级)

模板

  • references/output-templates/choice-question-template.md — 选择题模板
  • references/output-templates/essay-question-template.md — 简答题模板
  • references/output-templates/calculation-template.md — 计算题模板

示例

  • examples/by-chapter-case.md — 按章节出题完整流程
  • examples/by-type-case.md — 按题型出题
  • examples/mixed-case-case.md — 混合需求出题
  • examples/missing-info-case.md — 信息不全时的追问策略

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Practice Quiz AI skill do?

This skill should be used when the user asks to "出题", "做练习", "生成测验", "刷题", "给我出几道题", "做几道题练练", "出一套练习", "按章节出题", "按题型出题", "选择题", "填空题", "计算题", "简答题", "测测我", "考考我对这章的掌握", "出几道巩固题", "帮我做课后练习", or when the user wants practice questions generated by chapter, type, or difficulty, with answers, explanations, and study-focused assessment.

Why use Practice Quiz on TypingMind?

Because you install it once and use it with any model. Practice Quiz is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Practice Quiz in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/mingchen666/Reviva/tree/main/electron/builtin-assets/skills/practice-quiz. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Practice Quiz?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Practice Quiz?

As many as you like. As long as a model supports skills, you can use Practice Quiz with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Practice Quiz AI skill free?

It is published on GitHub by mingchen666. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇