From learning-skills
Quizzes the user on a plan, implementation, or codebase to reinforce understanding after AI-assisted development. Invoked explicitly via /quizzing.
How this skill is triggered — by the user, by Claude, or both
Slash command
/learning-skills:quizzing [scope: path | PR | doc | topic] (defaults to this session's latest plan/implementation)[scope: path | PR | doc | topic] (defaults to this session's latest plan/implementation)The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Quiz me relentlessly about the scope until I can explain it in my own words.
Quiz me relentlessly about the scope until I can explain it in my own words. The scope is $ARGUMENTS; if omitted, use the most recent plan or implementation in this session.
First investigate the scope. Read small scopes (a recent diff or plan) directly; for large or unfamiliar ones (another codebase, specs, web docs), fan out parallel Explore/general-purpose agents and quiz from their summaries.
Ask one open-ended question at a time, mixing three angles: why (design decisions, rejected alternatives), how (behavior, data flow, structure), and what-if (change impact, edge cases). Lean toward why for plans, how/what-if for code. Never reveal the answer before I attempt one.
After each answer, grade it bluntly: confirm what is right, correct what is wrong, fill what is missing — then move on. Drill deeper where my answers are weak; advance where they hold up.
Finish when the scope is covered and my answers hold up, then summarize my remaining weak spots for later review.
Guides collaborative design exploration before implementation: explores context, asks clarifying questions, proposes approaches, and writes a design doc for user approval.
Creates structured, bite-sized implementation plans from specs or requirements before writing code. Useful for breaking down multi-step tasks into testable steps with file structure and task boundaries.
Resolves in-progress git merge or rebase conflicts by analyzing history, understanding intent, and preserving both changes where possible. Runs automated checks after resolution.
npx claudepluginhub yasunori0418/skills --plugin learning-skills