quiz

GitHub

根据指定主题生成严格格式的JSON单选测验,包含题目、选项、正确答案及解析。支持5-30题,确保选项合理且无歧义,并通过验证工具保存为工作区文件。

docker/sandbox/skills/quiz/SKILL.md MODSetter/SurfSense

Trigger Scenarios

用户要求创建选择题测验 需要生成结构化评估内容

Install

npx skills add MODSetter/SurfSense --skill quiz -g -y
More Options

Non-standard path

npx skills add https://github.com/MODSetter/SurfSense/tree/main/docker/sandbox/skills/quiz -g -y

Use without installing

npx skills use MODSetter/SurfSense@quiz

指定 Agent (Claude Code)

npx skills add MODSetter/SurfSense --skill quiz -a claude-code -g -y

安装 repo 全部 skill

npx skills add MODSetter/SurfSense --all -g -y

预览 repo 内 skill

npx skills add MODSetter/SurfSense --list

SKILL.md

Frontmatter
{
    "name": "quiz",
    "description": "Create strict JSON single-answer multiple-choice quizzes."
}

Quiz

Create one /workspace/<slug>.json file. JSON is the canonical quiz; do not write a separate Markdown summary.

Contract

Use exactly this closed version-one shape:

{
  "schema_version": 1,
  "title": "Quiz title",
  "questions": [
    {
      "question_text": "One focused question",
      "options": ["Option A", "Option B", "Option C", "Option D"],
      "correct_option_index": 1,
      "explanation_text": "Why Option B is correct."
    }
  ]
}
  • Include 5–30 questions. Use an explicitly requested count within that range; otherwise create exactly 10. If the requested count is outside the range, stop and explain the supported range instead of clamping it.
  • Plan distinct assessment targets before writing. Do not duplicate, paraphrase, reverse, or pad weak questions to reach the minimum.
  • If the available source cannot support five defensible questions, stop without creating filler.
  • Every question has exactly four distinct options and exactly one objectively correct option. correct_option_index is an integer from 0 through 3.
  • Write three plausible distractors. Avoid “All of the above,” “None of the above,” trick wording, grammar clues, and obvious correct-position patterns.
  • explanation_text is required and should concisely teach why the selected answer is correct.
  • Title: 1–200 characters. Question and each option: 1–4,000. Explanation: 1–12,000.
  • Content is plain text. The only formatting syntax is LaTeX: use \(...\) for inline math and \[...\] for display math. Escape each backslash as \\ in JSON. Keep delimiters and braces balanced and do not nest math delimiters.
  • Do not add fields, change schema_version, use Markdown or raw HTML, include links or media, duplicate question text, or use null.
  • Write UTF-8 JSON without comments or a byte-order mark.

Verify and save

Call:

verify_artifact(path="/workspace/<slug>.json", format="quiz")

Fix all blocking findings together, rewrite the JSON once, and reverify the exact path. If a blocker remains, stop and explain it instead of looping.

After verification returns status="verified", call:

save_artifact(path="/workspace/<slug>.json", title="...")

Do not pass markdown_representation; the backend derives trusted Markdown from the exact receipt-bound JSON.

For revisions, edit the restored JSON from primary_path, write the complete quiz to expected_output_path, verify that path as quiz, and save with the returned artifact_id and expected_generation. Do not edit the derived markdown_path or reconstruct the quiz with vision.

Version History

  • 014e47a Current 2026-09-23 08:23

Same Skill Collection

.agents/skills/codebase-design/SKILL.md
.agents/skills/migrate-radix-to-base/SKILL.md
.agents/skills/shadcn/SKILL.md
.agents/skills/tdd/SKILL.md
.agents/skills/translate/SKILL.md
.cursor/skills/alert-manager/SKILL.md
.cursor/skills/animation-vocabulary/SKILL.md
.cursor/skills/backlink-analyzer/SKILL.md
.cursor/skills/competitor-analysis/SKILL.md
.cursor/skills/content-gap-analysis/SKILL.md
.cursor/skills/content-quality-auditor/SKILL.md
.cursor/skills/content-refresher/SKILL.md
.cursor/skills/domain-authority-auditor/SKILL.md
.cursor/skills/emil-design-eng/SKILL.md
.cursor/skills/entity-optimizer/SKILL.md
.cursor/skills/frontend-design/SKILL.md
.cursor/skills/geo-content-optimizer/SKILL.md
.cursor/skills/improve-codebase-architecture/SKILL.md
.cursor/skills/internal-linking-optimizer/SKILL.md
.cursor/skills/keyword-research/SKILL.md
.cursor/skills/memory-management/SKILL.md
.cursor/skills/meta-tags-optimizer/SKILL.md
.cursor/skills/on-page-seo-auditor/SKILL.md
.cursor/skills/performance-reporter/SKILL.md
.cursor/skills/python-patterns/SKILL.md
.cursor/skills/rank-tracker/SKILL.md
.cursor/skills/review-animations/SKILL.md
.cursor/skills/schema-markup-generator/SKILL.md
.cursor/skills/seo-content-writer/SKILL.md
.cursor/skills/serp-analysis/SKILL.md
.cursor/skills/shadcn/SKILL.md
.cursor/skills/system-architecture/SKILL.md
.cursor/skills/tdd/SKILL.md
.cursor/skills/technical-seo-checker/SKILL.md
.cursor/skills/ugc-brief/SKILL.md
.cursor/skills/vercel-react-best-practices/SKILL.md
.cursor/skills/web-design-guidelines/SKILL.md
docker/sandbox/skills/docx/SKILL.md
docker/sandbox/skills/flashcards/SKILL.md
docker/sandbox/skills/html/SKILL.md
docker/sandbox/skills/infographic/SKILL.md
docker/sandbox/skills/mindmap/SKILL.md
docker/sandbox/skills/pdf/SKILL.md
docker/sandbox/skills/pptx/SKILL.md
docker/sandbox/skills/video/SKILL.md
docker/sandbox/skills/xlsx/SKILL.md
.agents/skills/frontend-workflow/SKILL.md
.cursor/skills/playwright-testing/SKILL.md

Metadata

Files
0
Version
176aed2
Hash
c3da4595
Indexed
2026-09-23 08:23

ホーム - Wiki
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-11-01 15:28
浙ICP备14020137号-1