Skip to main content
skill CX Codex

quiz · takagoto — Claude Code skill: what it does, how to install

Generates interactive RAG quizzes with question-by-question scoring. Identifies knowledge gaps before you build retrieval pipelines.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add TakaGoto/rag-learning-academy --skill quiz -a claude-code
Open on GitHub

What quiz does

This skill generates a 5 to 10 question quiz on a selected RAG topic or checks progress/module-tracker.md for the latest completed lesson. Questions fall into four categories: conceptual reasoning, code reading, scenario analysis, and true-or-false statements that require an explanation.

Questions appear one at a time. The agent waits for your response, marks it, clarifies any misconceptions, and proceeds to the next prompt. When the quiz ends, total scores and identified gaps are appended to progress/quiz-results.md. If no tracking file exists yet, the skill redirects you to /start or /lesson.

What it helps with

  • test understanding of RAG mechanics before implementation
  • pinpoint gaps in chunking or retrieval strategies
  • log assessment scores into progress/quiz-results.md
  • receive follow-up command suggestions based on test results

Example prompts for the agent

  • /quiz chunking
  • Test my understanding of RAG retrieval strategies
  • /quiz

How to install quiz

1Skills CLI (Vercel)

npx skills add TakaGoto/rag-learning-academy --skill quiz -a claude-code

2Manually: put the files in place

~/.claude/skills/quiz/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/quiz/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about quiz

How to install quiz in Claude Code?

Run npx skills add TakaGoto/rag-learning-academy --skill quiz -a claude-code.

What does the quiz skill do?

It administers a 5 to 10 question assessment on RAG topics, evaluates answers individually, and writes results to progress/quiz-results.md.

What happens if quiz runs without a specified topic?

It inspects progress/module-tracker.md for your most recent lesson. If no tracker file is present, it prompts you to run /start or /lesson first.

Source text

SKILL.md · MIT
---
name: quiz
description: "Test your understanding of a RAG concept"
---

# Quiz: Test Your RAG Knowledge

> **Scope:** This skill **tests your understanding** with questions and scoring. For guided teaching of new concepts, use `/lesson`.

Generate and administer a quiz on a specific RAG topic to help learners assess their understanding. Quizzes reinforce learning and surface gaps.

## Step 1: Determine the Topic

- If the user specifies a topic (e.g., `/quiz chunking`), use that topic.
- If no topic is given, read `progress/module-tracker.md` to find the most recently completed lesson and quiz on that.
- If no progress exists, suggest running `/start` or `/lesson` first.

## Step 2: Generate Questions

Create 5-10 questions that mix the following types:

### Conceptual Questions (2-3)
Test understanding of "why" and "how" things work. Example: "Why might fixed-size chunking lose important context at chunk boundaries?"

### Code Reading Questions (2-3)
Show a code snippet and ask what it does, what is wrong with it, or what the output would be. Example: Show a retrieval function and ask why it might return irrelevant results.

### Scenario-Based Questions (2-3)
Present a real-world situation and ask the learner to choose the best approach. Example: "You have a corpus of legal contracts averaging 50 pages each. Which chunking strategy would you start with and why?"

### True/False with Justification (1-2)
A statement the learner must evaluate and explain. Example: "Larger chunk sizes always improve retrieval quality. True or false? Explain."

## Step 3: Administer the Quiz

Present questions one at a time. Wait for the learner's answer before moving to the next question. Do not reveal the correct answer until the learner has responded.

For each question:
1. Present the question clearly
2. Wait for the learner's response
3. Evaluate the response — is it correct, partially correct, or incorrect?
4. Provide the correct answer with a clear explanation
5. If incorrect, explain the misconception and link it back to the relevant concept

## Step 4: Score and Review

After all questions are answered, present a summary:

```
Quiz Results: [Topic]
Score: [X]/[Total] ([percentage]%)
---
Strengths: [areas where the learner did well]
Gaps: [areas that need review]
Recommendation: [what to study next]
```

## Step 5: Track Results

Save the quiz results to `progress/quiz-results.md` with the date, topic, score, and any identified gaps. Append to the file if it already exists.

## Step 6: Suggest Next Steps

Based on the score, suggest 2-3 relevant next steps using slash commands:

- **90-100%**: Congratulate them.
  - `/challenge` — put your mastery to the test with a real-world challenge
  - `/build` — apply your knowledge by building a hands-on component
  - `/lesson` — continue to the next lesson in your track
- **70-89%**: Good progress. Recommend reviewing the specific gaps.
  - `/build` — reinforce your understanding by building what you just learned
  - `/lesson` — continue to the next lesson or revisit a weak area
  - `/explain` — get a deeper explanation of any concepts that felt shaky
- **Below 70%**: Encourage them.
  - `/lesson` — revisit the lesson to strengthen your foundations
  - `/explain` — get a deep-dive explanation on the weak areas
  - `/glossary` — review key terms you may have missed

## Guidelines

- Questions should be practical and relevant, not trivia
- Accept reasonable alternative answers — RAG is a field with multiple valid approaches
- When answers are wrong, be straightforward: explain what's actually going on without sugarcoating. "Not quite — here's the thing" beats "Great try! You're on the right track!"
- Vary difficulty within the quiz (start easier, build up)

© TakaGoto · MIT · TakaGoto/rag-learning-academy

Similar skills

All skills for AI and ML →

quiz by other authors comes first.

From the same set16

start Walks a newcomer through picking a language and track, scoring their level, and running a first RAG pipeline in the same session. CX Codex +1 ★ 24repo stars sandbox Quickly scaffolds a minimal retrieval-only RAG pipeline with sample data for hands-on experimentation. CX Codex +1 ★ 24repo stars roadmap This skill maps RAG coursework, achievements, knowledge gaps, and suggested next steps. Use it to see what you’ve finished and what to study next. CX Codex +1 ★ 24repo stars recap Builds a brief recap of the previous lesson from progress files: what you covered, the main ideas, and what comes next. Handy when you come back to a course after a break. CX Codex +1 ★ 24repo stars paper-review Takes you through a RAG research paper section by section: background, method, results, and what to borrow for your own pipeline. Useful when a skim of the abstract is not enough. CX Codex +1 ★ 24repo stars journal The skill saves short notes about what you understood or got stuck on, appending them to progress/journal.md. Useful when you want a learning diary without the ceremony. CX Codex +1 ★ 24repo stars fix Diagnoses and repairs broken RAG pipelines without lectures or theory. Useful when retrieval returns garbage or the model hallucinates. CX Codex +1 ★ 24repo stars explain This skill teaches RAG concepts, from plain-language intuition to code and practical trade-offs. Use it to dig into topics such as embeddings, chunking, or hybrid search. CX Codex +1 ★ 24repo stars

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor