agentleFS
TakaGotoTakaGoto/rag-learning-academy/.claude/skills/quiz/SKILL.md

quiz

Skill24 starsChanged 19 days agoMITView on GitHub

Test your understanding of a RAG concept

15 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use progress, learn and 1 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • remenoscodesSkill

    progress

    Longitudinal language learning progress report with metrics, trends, and insights

    Also in 4 projects that use this

  • genomewalkerSkill

    learn

    Learn from web sources, generate SKILL.md, and store key patterns in soul memory. Trigger keywords: learn, skill-gen, web-learn, documentation, tutorial.

    Also in 4 projects that use this

  • VercelSkill

    setup

    Set up Vercel CLI and project configuration. Use when the user says "set up Vercel", "configure Vercel", "link to Vercel", or "vercel init".

    Also in 4 projects that use this

The file

We split this skill into the rules it gives an agent

9 rules. 0 are common, 6 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 14 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If the user specifies a topic (e.g., /quiz chunking), use that topic.

    line 14
  2. Very specific:

    If no topic is given, read progress/module-tracker.md to find the most recently completed lesson and quiz on that.

    line 15
  3. Very specific:

    If no progress exists, suggest running /start or /lesson first.

    line 16
  4. Distinctive:

    Create 5-10 questions that mix the following types:

    line 20
  5. Distinctive:

    Test understanding of "why" and "how" things work.

    line 23
  6. Distinctive:

    Wait for the learner's response

    line 40
  7. Distinctive:

    If incorrect, explain the misconception and link it back to the relevant concept

    line 43
  8. Distinctive:

    After all questions are answered, present a summary:

    line 47
  9. Distinctive:

    When answers are wrong, be straightforward: explain what's actually going on without sugarcoating.

    line 83

“Common” is measured: kept by at least 6 in 10 of the 14 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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)

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.