Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Generate a quiz or test on any topic with a balanced mix of question types and difficulty, plus a complete answer key with explanations. Use when asked to create a quiz, write a test, make practice questions, or build an assessment. Produces well-formed questions aligned to learning objectives, tagged by difficulty and cognitive level, with an answer key and (for MCQs) plausible distractors and rationale.
.claude/skills/mohitagw15856-quiz-generator/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-06 | ✗→✓ | ▲ Improved | 19% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 6% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -9% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 13% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 20% | 0% |
Good assessment questions test understanding, not recall of trivia — and have answer keys that teach. This skill writes questions aligned to objectives, spread across difficulty and Bloom's levels, with explanations.
Given a topic, generate the full quiz anyway at a reasonable level, and mark assumed scope. Never leave "question here]" or an answer blank. For MCQs, every distractor must be plausible (reflect a real misconception), not filler.
Ask for (if not already provided):
Numbered, grouped by type. Each question tagged: [difficulty · Bloom's level].
For every question: the correct answer and a one-line explanation (for MCQs, also why each distractor is wrong where useful).
| # | Type | Difficulty | Bloom's | Objective | |---|---|---|---|---|
(Shows the spread so it's not all recall or all hard.)
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→pass | 35,992 | 38,431 | +7% | 1 | 1 | 0% | 6,111 | 5,674 | -7% | 0 | 0 | — |
case-02 | pass→pass | 16,939 | 14,348 | -15% | 1 | 1 | 0% | 1,900 | 2,550 | +34% | 0 | 0 | — |
case-03 | pass→pass | 24,596 | 33,851 | +38% | 1 | 1 | 0% | 2,981 | 4,555 | +53% | 0 | 0 | — |
case-04 | pass→fail | 16,073 | 41,924 | +161% | 1 | 1 | 0% | 3,275 | 6,421 | +96% | 0 | 0 | — |
case-05 | pass→pass | 42,361 | 33,200 | -22% | 1 | 1 | 0% | 5,988 | 5,125 | -14% | 0 | 0 | — |
case-06 | fail→pass | 124,914 | 29,878 | -76% | 1 | 1 | 0% | 3,885 | 4,606 | +19% | 0 | 0 | — |
case-07 | fail→pass | 54,728 | 42,441 | -22% | 1 | 1 | 0% | 8,233 | 8,721 | +6% | 0 | 0 | — |
case-08 | fail→pass | 45,119 | 49,840 | +10% | 1 | 1 | 0% | 8,228 | 7,478 | -9% | 0 | 0 | — |
case-09 | fail→pass | 29,095 | 26,944 | -7% | 1 | 1 | 0% | 3,620 | 4,102 | +13% | 0 | 0 | — |
case-10 | fail→fail | 34,981 | 40,773 | +17% | 1 | 1 | 0% | 5,380 | 6,591 | +23% | 0 | 0 | — |
case-11 | fail→pass | 26,007 | 44,004 | +69% | 1 | 1 | 0% | 3,446 | 4,149 | +20% | 0 | 0 | — |
case-12 | fail→pass | 16,122 | 22,856 | +42% | 1 | 1 | 0% | 2,504 | 4,656 | +86% | 0 | 0 | — |
case-13 | pass→pass | 17,077 | 38,092 | +123% | 1 | 1 | 0% | 3,022 | 4,804 | +59% | 0 | 0 | — |
case-14 | fail→fail | 28,372 | 74,262 | +162% | 1 | 1 | 0% | 5,244 | 8,708 | +66% | 0 | 0 | — |
case-15 | fail→pass | 28,880 | 22,594 | -22% | 1 | 1 | 0% | 4,064 | 3,723 | -8% | 0 | 0 | — |
case-16 | pass→pass | 30,149 | 35,647 | +18% | 1 | 1 | 0% | 3,195 | 5,993 | +88% | 0 | 0 | — |
case-17 | pass→pass | 26,384 | 24,430 | -7% | 1 | 1 | 0% | 3,789 | 5,571 | +47% | 0 | 0 | — |
case-18 | fail→pass | 28,129 | 29,172 | +4% | 1 | 1 | 0% | 5,484 | 4,770 | -13% | 0 | 0 | — |
case-19 | pass→pass | 39,452 | 18,323 | -54% | 1 | 1 | 0% | 3,952 | 4,538 | +15% | 0 | 0 | — |
case-20 | fail→pass | 22,055 | 19,951 | -10% | 1 | 1 | 0% | 3,106 | 3,871 | +25% | 0 | 0 | — |
case-21 | fail→pass | 25,020 | 39,620 | +58% | 1 | 1 | 0% | 4,882 | 6,707 | +37% | 0 | 0 | — |
case-22 | fail→pass | 56,544 | 73,422 | +30% | 1 | 1 | 0% | 8,215 | 7,385 | -10% | 0 | 0 | — |
case-23 | fail→pass | 14,340 | 23,971 | +67% | 1 | 1 | 0% | 2,127 | 3,572 | +68% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 23 cases were attempted. The headline lift of +48 percentage points is the difference between those two pass rates over the 23 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.