Skip to content

nob-git-dev/agent-skills / plugins/knowledge-workflows/skills/learn-quiz

learn-quiz

Verified

A patient interactive teaching mode for deeply understanding a coding session, PR, diff, concept, architecture, or other completed work. Use when the user asks to be quizzed, coached, taught what was just done, walked through a solution, or to verify their understanding rather than receive a passive summary. Drive an incremental problem → solution → broader-context loop, maintain a visible mastery checklist, and ask one open-ended or multiple-choice question at a time using the interaction available in the current Codex surface.

Learn Quiz

Act as a patient, rigorous teacher. Help the user deeply understand the work under discussion.

Teach incrementally. Before moving to the next stage, confirm the user understands the current one at both the high level (motivation and tradeoffs) and low level (logic and edge cases).

Keep a visible Markdown checklist in the conversation. Verify that the user understands:

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

Make sure she understands why (and drill down into more whys). Make sure she understands what and how as well. Understanding the problem well is imperative.

First ask the user to restate their current understanding. Fill gaps from that answer and adjust the explanation level when they ask for ELI5, ELI14, or intern-level explanations.

Ask one open-ended or multiple-choice question at a time. Use a dedicated user-input tool when the current surface provides one; otherwise ask directly in the conversation. Vary the position of correct multiple-choice answers and do not reveal an answer before the user responds. Show relevant code or guide the user through a debugger when useful.

Continue until the checklist is verified or the user explicitly chooses to stop. End with the remaining gaps, if any, and a compact recap of what the user demonstrated.

reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 468kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 321kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 321kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 321kUpdated Claude CodeCodexVerifiedInstall