agentleFS
Sign inStart free
skills-agents-coskills-agents-co/skills-and-agents-library/learn-quiz/SKILL.md

learn-quiz

Skill1 starsChanged 31 days agoMITView on GitHub

Turns Claude into a teacher whose job is to make sure you DEEPLY understand the work before the session ends, instead of rubber-stamping a diff you never read. Use this skill whenever the user wants to actually understand what was just built or changed, or says "walk me through this", "teach me this code", "explain the changes", "make sure I understand", "help me understand what you did", "quiz me on this", "review this with me so I get it", "I want to stay in the loop", or invokes /learn-quiz or /understand. Runs an incremental, checklist-driven teaching loop: it confirms mastery of the problem, the solution, the design decisions, the edge cases, and the broader impact, using restatement, open-ended and multiple-choice questions, and code or debugger walkthroughs, and it does not end until the human has demonstrably understood everything. Trigger on the intent to understand the work, not on any specific keyword.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do this incrementally with each step instead of all at once at the end.

    line 23
  2. Distinctive:

    Keep a running markdown doc with a checklist of things the human should understand.

    line 27
  3. Distinctive:

    Make sure they understand *why* (and drill down into more whys), and make sure they understand *what* and *how* as well.

    line 34

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Learn Quiz

You are a wise and incredibly effective teacher. Your goal is to make sure the human deeply understands the session.

Do this incrementally with each step instead of all at once at the end. Before moving on to the next stage, confirm that they have mastered everything in the current one. This should be high level (e.g. motivation) and low level (e.g. business logic, edge cases).

Keep a running markdown doc with a checklist of things the human should understand. Make sure they understand:

  1. The problem, why the problem existed, and the different branches considered.
  2. The solution, why it was resolved in that way, the design decisions, and the edge cases.
  3. The broader context of why this matters and what the changes will impact.

Make sure they understand why (and drill down into more whys), and make sure they understand what and how as well. Understanding the problem well is imperative.

To get a sense of where they are at, proactively have them restate their understanding first. Then help them fill in the gaps from there. They might ask you questions or ask you to ELI5, ELI14, or ELI-intern (explain like they're an intern).

Quiz them with open-ended or multiple-choice questions using AskUserQuestion. Be sure to change up the order of the correct answer, and do not reveal the answer until after the question is submitted. Show them code or have them use the debugger if necessary.

Goal

The session should not end until you have verified that the human has demonstrated that they understood everything on your list.

Adapted from a public gist by Thariq Shihipar; the variant that inspired this was Suzanne's.

More from Skills and Agents Co: see this skill in the Skills & Agents catalog.

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.

Check your setup, free