Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/mathruffian-dot/teaching-exam-skillsnpx agentmods add skills/mathruffian-dot/teaching-exam-skills/jh-math-examWrote 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/mathruffian-dot/teaching-exam-skills/jh-math-exam)<a href="https://agentmods.dev/skills/mathruffian-dot/teaching-exam-skills/jh-math-exam"><img src="https://agentmods.dev/badge/skills/mathruffian-dot/teaching-exam-skills/jh-math-exam/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/mathruffian-dot/teaching-exam-skills/jh-math-exam"><img src="https://agentmods.dev/badge/skills/mathruffian-dot/teaching-exam-skills/jh-math-exam.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00215 | $0.09869 |
| Opus 5.5 | $0.00086 | $0.03948 |
| Sonnet 5.5 | $0.00043 | $0.01974 |
| Haiku 4.5 | $0.00021 | $0.00987 |
Grade A, and why
jh-math-exam scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 671 lines — stays where its author put it; the contents beside it link to each section on GitHub.
國中數學段考命題審題技能
技能概覽
本技能支援兩種模式，協助教師完成國中數學段考的完整命題與審題流程：
模式 A：出題模式（全新命題）
- 需求訪談 — 確認年級、範圍、題型、配分
- 規劃雙向細目表 — 章節 × 認知層次比例
- 生成題目 — 按 Bloom 四級分類產出
- 幾何圖形渲染 — 若有幾何題，自動呼叫 jh-math-geometry 技能的渲染腳本產生配圖 PNG
- 格式輸出 — 題目卷、答案卷、雙向細目表（三份 Word），幾何圖自動插入對應位置
模式 B：審題模式（審核現有考卷）
- 接收考卷 — 使用者貼入文字或上傳圖片/Word
- 逐題審查 — 判定 Bloom 層次、section 歸屬、答案與題目品質
- 輸出分級報告 — 顯示統計與偏差提示
- 格式輸出 — 僅產出雙向細目表（一份 Word）
環境約定（所有 Step 共用）
本技能不假設任何特定沙箱或工具名稱，路徑一律依下列約定：
| 名稱 | 意義 |
|---|---|
本技能目錄（$SKILL_DIR） |
這份 SKILL.md 所在的資料夾 |
output/ |
當前工作目錄下的產出資料夾：中間檔（exam_data.json、幾何圖）與最終 Word 都放這裡 |
$GEOM_DIR |
jh-math-geometry 技能的 scripts/：同 repo 的 skills/jh-math-geometry/scripts/，或已安裝的 jh-math-geometry 技能 |
SKILL_DIR="<本技能目錄的絕對路徑>" # 例：~/.claude/skills/jh-math-exam
mkdir -p output
# 幾何腳本位置：同 repo 的 skills/jh-math-geometry/，或已安裝的 jh-math-geometry 技能
GEOM_DIR=""
for d in "$SKILL_DIR/../jh-math-geometry/scripts" "$HOME/.claude/skills/jh-math-geometry/scripts"; do
[ -f "$d/geometry_renderer.py" ] && GEOM_DIR="$d" && break
done
echo "幾何腳本目錄：${GEOM_DIR:-（找不到，幾何題將無法配圖）}"
python3 -m pip install -q python-docx lxml cairosvg # 首次使用安裝一次；Linux 系統 Python 拒絕時加 --break-system-packages
- Windows 若沒有
python3指令，把下文的python3換成python；Bash 片段請在 Git Bash／WSL 執行。- 文中的「視覺確認」一律指讀取檔案（用你的檔案讀取工具開啟
.svg／.png），不依賴任何特定工具。- 產出留在
output/，完成後在對話中列出檔案路徑即可，不需再複製到別處。
處理流程
Step 1：需求確認（必做）
向使用者確認以下資訊（未提供則詢問）：
| 項目 | 說明 |
|---|---|
| 年級 | 七年級 / 八年級 / 九年級 |
| 學期 & 次別 | 第一學期第三次段考 等 |
| 考試範圍 | 章節名稱 + 版本（翰林版 / 康軒版 / 南一版） |
| 題型需求 | 選擇題幾題、非選擇題幾題、配分 |
| 難度目標 | 參考 Bloom 各級比例，或教師自訂 |
| 模式 | A. 出題（全新產出題目卷+答案卷+細目表） / B. 審題（審核現有考卷，只產細目表） |
Step 2：建立雙向細目表
雙向細目表格式（本技能內建，不需外部檔案）：
- 縱軸：教材章節（依考試範圍列出各節名稱，如「1-1 等差數列」）
- 橫軸：認知層次（記憶 / 理解 / 應用 / 分析）
- 細格：
分數（題數），例如6（2）；最右欄「小計」，最下兩列「合計」與「百分比」 - 表頭：學年度、學期、年級、次別、考試範圍；需要時加「對應課綱」欄（學習內容代碼 N/A/S/F/D，請上網查教育部十二年國教數學領綱）
| 章節 \ 層次 | 記憶 | 理解 | 應用 | 分析 | 小計 |
|---|---|---|---|---|---|
| 1-1 等差數列 | 4（1） | 8（2） | 12（3） | 6（2） | 30（8） |
| … | |||||
| 合計 | 10 | 20 | 40 | 30 | 100 |
| 百分比 | 10% | 20% | 40% | 30% | 100% |
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.
- 1mo ago Changed · -176 lines 4169804e6110
- 1mo ago First seen · 847 lines · 215 tokens per session scan A a5271b2137ea
jh-math-exam is a skill published in the GitHub repository mathruffian-dot/teaching-exam-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 215 tokens to every session and 9,869 once invoked, about $0.0009 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 2026-08-31.
Other skills, from other repositories
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
exam-forecast
Analyze past exams from the same professor to surface patterns — subject weighting, recurring issue-spot traps, favored hypo types, policy-vs-doctrine mix — and forecast likely emphases for the upcoming exam. Use when the user says "what's on the exam", "analyze past exams", "predict the exam", or shares past exams.
lean-formalize
Develop and verify a mathematical proof in Lean, continue an incomplete Lean project, or audit whether it proves the original statement. Connect actual inputs to intermediate lemmas, assemble the target theorem, check its transitive axioms, and provide a reproducible handoff. Use when Lean is requested or a specific…
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.