Borrowing it
Nothing to install: this file belongs to tobyilee/course-builder. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/tobyilee/course-builder/main/.claude/skills/quiz-generation/SKILL.mdgit clone --depth 1 https://github.com/tobyilee/course-builderWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/tobyilee/course-builder/quiz-generation)<a href="https://agentmods.dev/skills/tobyilee/course-builder/quiz-generation"><img src="https://agentmods.dev/badge/skills/tobyilee/course-builder/quiz-generation/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/tobyilee/course-builder/quiz-generation"><img src="https://agentmods.dev/badge/skills/tobyilee/course-builder/quiz-generation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00050 | $0.01380 |
| Opus 5.5 | $0.00020 | $0.00552 |
| Sonnet 5.5 | $0.00010 | $0.00276 |
| Haiku 4.5 | $0.00005 | $0.00138 |
Grade A, and why
quiz-generation scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quiz Generation — Section-Level Assessment
섹션 끝에서 summative 평가를 수행. class 단위가 아닌 섹션 단위인 이유: class는 formative(배우는 중), section은 summative(개념 연결 평가).
문항 수
- 5~9개, 10개 절대 금지
- 기준 공식:
round(section_duration / 15), 최소 5, 최대 9 - 동일 LO에 2문항 허용 (복수 관점 평가)
Bloom 분포 (문항 배분)
| Section 유형 | Remember | Understand | Apply | Analyze | Evaluate | Create |
|---|---|---|---|---|---|---|
| 입문 섹션 | 1~2 | 2 | 1~2 | 1 | - | - |
| 중급 섹션 | 0~1 | 1 | 2 | 2 | 1 | - |
| 고급 섹션 | 0 | 0~1 | 1 | 2 | 1~2 | 1 |
필수: Apply+Analyze ≥ 2. 단순 암기 위주 평가 금지.
문항 타입
mcq_single (단일 선택)
- 선택지 4개 고정
- 정답 정확히 1개
- Bloom: Remember~Analyze 모두 가능
{
"id":"S1.Q1", "type":"mcq_single",
"stem":"서버 컴포넌트가 포함되지 않는 번들은?",
"choices":["서버 번들","클라이언트 번들","Edge 런타임","SSR 출력"],
"correct":["B"],
"explanation":"서버 컴포넌트는 서버에서만 실행되고 클라이언트 번들에 직렬화된 페이로드만 전달됩니다.",
"distractor_rationales":{
"A":"서버 번들에는 포함됩니다 — 오히려 당연",
"C":"Edge 런타임도 서버 환경의 일종",
"D":"SSR 출력에도 RSC 결과가 들어갑니다"
},
"lo_ids":["LO-1.2"], "bloom":"Understand", "difficulty":3
}
mcq_multi (복수 선택)
- 선택지 4~5개
- 정답 2~3개, 선지문에 정답 수 명시 ("다음 중 맞는 것 2개를 고르시오")
- 채점: 부분점수 or 올오낫싱 명시
true_false
- 개념 오해 교정용으로만 사용
- stem은 교과서적 정답이 아닌 학습자가 헷갈리는 명제
- Bloom은 Understand/Analyze에 한정 (Remember에는 부적합 — 너무 쉬움)
short_answer
- 자기채점용, rubric 필수
{
"type":"short_answer",
"stem":"서버 컴포넌트와 SSR의 차이를 2문장으로 설명하시오.",
"rubric":[
"서버 컴포넌트는 클라이언트 번들 제외 (1pt)",
"SSR은 HTML 문자열을 렌더링 (1pt)",
"두 기술은 동시 사용 가능 (1pt)"
],
"lo_ids":["LO-1.3"], "bloom":"Analyze"
}
Distractor (오답 선지) 품질
원칙
- plausible (학습자가 실제로 할 법한 오해)
- 정답과 길이·디테일 균형
- 문법적·구조적으로 정답과 동일 패턴
좋은 distractor 생성법
- 학습자의 흔한 오개념 수집 (note의 Pitfalls 섹션 참조)
- 비슷한 개념과 혼동 유도 (SSR vs RSC vs CSR)
- 맞는 말이지만 질문에 답하지 않는 서술
나쁜 distractor
- "모든 것", "아무것도" (보통 오답)
- 이상하게 짧거나 긴 것 (정답이 드러남)
- 명백히 거짓 (학습 가치 없음)
Explanation 규칙
- 모든 문항 필수
- 정답 해설 + (mcq류) 각 오답별 왜 틀렸는지
- 최소 2문장, 최대 5문장
- 설명이 곧 미니 복습 — 투자 가치 있음
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 127 lines · 50 tokens per session scan A e6fa6f55afce
quiz-generation is a skill published in the GitHub repository tobyilee/course-builder (27 stars, last pushed 6mo ago), licensed MIT. It adds 50 tokens to every session and 1,380 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
quiz-generation compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| quiz-generationtobyilee/course-builder | Skill | 27 | 6mo ago | MIT | A | 50 | Claude Code |
| hr-onboardingnexu-io/open-design | Skill | 106k | today | Apache-2.0 | A | 62 | Claude Code, Codex |
| book-mirrorgarrytan/gbrain | Skill | 32k | today | MIT | A | 138 | Claude Code |
| exam-forecastanthropics/claude-for-legal | Skill | 9.9k | today | Apache-2.0 | A | 73 | Claude Code |
| lean-formalizewanshuiyin/Auto-claude-code-research-in-sleep | Skill | 19k | yesterday | MIT | A | 81 | Claude Code |
| deck-course-modulenexu-io/html-anything | Skill | 9.4k | yesterday | Apache-2.0 | A | 25 | Claude Code, Codex |
| eli5companion-inc/feynman | Skill | 10k | 7d ago | MIT | A | 63 | Claude Code, Codex |