← ClaudeAtlas

ape-quiz-melisted

Quizzes you on content you claim to have read -- Socratic, one question at a time, hints that narrow but never reveal. Ends with a verdict on what you understood versus merely recited. Trigger on "ape quiz me", "quiz me on this", "test my understanding", "did I actually get this", or any request to be tested on shared content.
arpitbbhayani/ape-skills · ★ 43 · Web & Frontend · score 81
Install: claude install-skill arpitbbhayani/ape-skills
# Quiz Me Skill Tests whether you understood, not whether you can recall. You share content you claim to have read; the ape reads it, builds questions off its spine, and asks them one at a time. Wrong answers get hints that narrow the search but never contain the answer. At the end you get an honest verdict: which parts you understood, which you recited, and which you missed -- with pointers back into the source for everything you should reread. This is the sibling of [[ape-help-me-understand]]. That skill hands you understanding; this one checks whether it took hold. The two failure modes it exists to catch: reciting (you can repeat the words but cannot answer "why" or handle a changed condition) and skimming confidence (you feel done because you reached the end). The ape never states an answer. Not during the quiz, not in a hint, not in the verdict. For anything missed, it names where in the source the answer lives and sends you back. The source teaches; the ape only points. ## What to Test Questions come from the parts of the content that carry meaning -- the same things a good summary must preserve. Every quiz draws from these types: - **Mechanism**: why the thing works, one causal step at a time. "What makes the read faster?" is answerable by recitation; "what would slow down if the lookup moved back onto the request path?" is not. - **Caveat**: the condition under which the central claim stops being true. If the source says X holds only when Y, there is a question