Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add ssmurfgg04-gif/context-m --skill quiz-masterygit clone --depth 1 https://github.com/ssmurfgg04-gif/context-mWrote 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/ssmurfgg04-gif/context-m/quiz-mastery)<a href="https://agentmods.dev/skills/ssmurfgg04-gif/context-m/quiz-mastery"><img src="https://agentmods.dev/badge/skills/ssmurfgg04-gif/context-m/quiz-mastery/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/ssmurfgg04-gif/context-m/quiz-mastery"><img src="https://agentmods.dev/badge/skills/ssmurfgg04-gif/context-m/quiz-mastery.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 | $0.00236 | $0.02794 |
| Opus 5 | $0.00118 | $0.01397 |
| Sonnet 5 | $0.00047 | $0.00559 |
| Haiku 4.5 | $0.00024 | $0.00279 |
Grade A, and why
quiz-mastery scanned grade A with 1 finding 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 9d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
result = subprocess.run([ How it starts
The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
测验大师 (Quiz Mastery)
两大核心能力
能力一：从学习资料出题
- 用户提供学习资料（.md / .txt / .docx / .pdf / .ppt / .pptx）
- 调用
generate_from_material.py获取知识点提取 prompt - 将 prompt 发给 LLM，得到知识点 JSON
- 调用
service.save_knowledge_points()保存知识点 - 调用
run_quiz.py生成出题 prompt - 将 prompt 发给 LLM，得到题目 JSON
- ⭐ 询问用户是否生成网页练习页（见下方"网页练习联动"章节）
- 用户说要 → 调用
quiz-htmlskill 生成 HTML 并打开 - 用户说不用 → 走原流程
- 用户说要 → 调用
- 逐题展示给用户，收集答案
- 调用
submit_answers.py提交评分
能力二：从题目文件练习
- 用户提供题目文件（.md / .txt / .docx / .pdf / .ppt / .pptx）
- 调用
import_quiz.py获取题目解析 prompt - 将 prompt 发给 LLM，得到标准化题目 JSON
- 调用
service.import_questions()导入题目并创建 session - ⭐ 询问用户是否生成网页练习页（见下方"网页练习联动"章节）
- 用户说要 → 调用
quiz-htmlskill 生成 HTML 并打开 - 用户说不用 → 走原流程
- 用户说要 → 调用
- 逐题展示给用户，收集答案
- 调用
submit_answers.py提交评分
何时使用（触发条件）
- 用户主动要求："出几道题"、"测试一下"、"来个小测"、"练习题"、"考考我"
- 用户说"复习"、"巩固"、"回顾"：直接触发
- 基于已有题目文件练习：用户上传题目文件后触发
⚠️ 不处理 study-buddy 的"即时练习"——那条链路由 study-buddy 走外部
exam_take，不调本 skill。
没历史数据时的兜底
当用户说"复习"但 data/user_progress/ 是空的（新用户/没答过题）：
- 不要硬启动复习流程——没数据可复习
- 主动告诉用户："还没有可复习的历史数据，要不要先用一份学习资料出题练一下？"
- 引导用户走"能力一：从学习资料出题"
难度系统
| 级别 | 含义 | 说明 |
|---|---|---|
| L1 | 识记 | 基础记忆和理解，考察概念辨认和基本事实 |
| L2 | 理解 | 深层理解，考察概念区分、原理解释和简单应用 |
| L3 | 应用 | 综合运用，考察实际场景应用、分析和问题解决 |
- 首次出题：强制从 L1 开始
- 答对当前难度：升一级（最高 L3）
- 答错当前难度：降一级（最低 L1）
题型分配规则
| 级别 | 选择题 | 判断题 | 填空题 | 简答题 |
|---|---|---|---|---|
| L1 | 70% | 30% | - | - |
| L2 | 50% | 20% | 30% | - |
| L3 | 40% | 20% | 20% | 20% |
出题数量
- 默认每次出 3 道题（一次对话展示 3 题，用户一次性回答后统一评分）
- 每轮最多 15 题（用户可要求调整数量）
- 简答题尽量少出，不自动评分（标记为
needs_review，由外部 LLM/人工评判）
薄弱知识点追踪
- 标记为薄弱：累计错误次数 ≥ 3
- 不解除：薄弱知识点只增不减，作为历史档案保留
- 内部数据保存在
data/user_progress/（错误次数、艾宾浩斯阶段等） - 同步到 USER.md 第 3 节"薄弱知识点"（由本 skill 直接写入，来源=
quiz-mastery）： | 知识点 | 错误次数 | 来源 | 备注 |- 已有该知识点 → 更新错误次数
- 未在表中 → 新增一行
遗忘曲线复习机制
基于艾宾浩斯遗忘曲线，按 1天 → 2天 → 4天 → 7天 → 15天 间隔安排复习：
- 答对：review_stage +1（推进到下一个间隔）
- 答错：review_stage 重置为 0（从头开始）
- 复习推荐包含：即将遗忘的知识点 + 最近 3 天薄弱知识点
What ships with it
18 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- .claude/settings.json 124 B
- README.md 3.3 KB
- scripts/generate_from_material.py 1.4 KB runs code
- scripts/import_quiz.py 1.5 KB runs code
- scripts/run_quiz.py 1.7 KB runs code
- scripts/submit_answers.py 1.2 KB runs code
- skill.yaml 454 B
- src/quiz_mastery/__init__.py 74 B runs code
- src/quiz_mastery/evaluator.py 2.6 KB runs code
- src/quiz_mastery/file_parser.py 9.0 KB runs code
- src/quiz_mastery/mastery_engine.py 5.3 KB runs code
- src/quiz_mastery/models.py 2.0 KB runs code
- src/quiz_mastery/planner.py 2.2 KB runs code
- src/quiz_mastery/quiz_extractor.py 3.5 KB runs code
- src/quiz_mastery/quiz_generator.py 4.6 KB runs code
- src/quiz_mastery/repository.py 1.3 KB runs code
- src/quiz_mastery/service.py 11 KB runs code
- src/quiz_mastery/utils.py 137 B runs code
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.
- 9d ago First seen · 213 lines · 236 tokens per session scan A 364345f7d14d
quiz-mastery is a skill published in the GitHub repository ssmurfgg04-gif/context-m (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 236 tokens to every session and 2,794 once invoked, about $0.0012 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
ai-style
A Chinese-language writing guide for producing or revising reader-facing text such as product announcements, public-account articles, emails, and README files. It focuses on reducing patterns that make writing sound machine-generated.
triage
A task-routing guide that identifies goals, dependencies, and acceptance conditions before work begins. It orders work as research, calculation or execution, and writing.
coding
A coding guide for writing and running Python programs in a sandbox. It requires scripts to be small and reproducible, with their actual output or errors reported.
gsd-help
Show available GSD commands and usage guide.
interview-coach
Produce a structured interview prep doc with a reusable self-introduction (60s + 30s) and per-round STAR stories, grounded in the resume, JD, intake (for round info and timeline), and hiring-recon report. Output is one markdown file.
socratic-duel-run
Run Socratic Duel through two participant subagents while the launcher only coordinates and reports.