Borrowing it
Nothing to install: this file belongs to yazelin/ipas-ai-quiz. 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/yazelin/ipas-ai-quiz/master/.claude/skills/add-exam/SKILL.mdgit clone --depth 1 https://github.com/yazelin/ipas-ai-quizWrote 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/yazelin/ipas-ai-quiz/add-exam)<a href="https://agentmods.dev/skills/yazelin/ipas-ai-quiz/add-exam"><img src="https://agentmods.dev/badge/skills/yazelin/ipas-ai-quiz/add-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/yazelin/ipas-ai-quiz/add-exam"><img src="https://agentmods.dev/badge/skills/yazelin/ipas-ai-quiz/add-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 | $0.00067 | $0.00840 |
| Opus 5 | $0.00034 | $0.00420 |
| Sonnet 5 | $0.00013 | $0.00168 |
| Haiku 4.5 | $0.00007 | $0.00084 |
Grade A, and why
add-exam 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 11d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
該頁是 Next.js SSR,可直接 `curl` 頁面原始碼,用 grep 撈出 `/api/proxy/uploads/certification_resource/.../*.pdf` 的完整連結。把新梯次各科的 PDF 網址記到 `tools/sources.json`。 What it actually says
加一個新梯次的官方試題
iPAS 每次考完會公告該次試題(本站考古題來源)。將來有新梯次時,照此流程加入。
步驟
-
拿到官方 PDF 直連網址。iPAS AIAP 來源頁:
https://ipd.nat.gov.tw/ipas/certification/AIAP/learning-resources該頁是 Next.js SSR,可直接curl頁面原始碼,用 grep 撈出/api/proxy/uploads/certification_resource/.../*.pdf的完整連結。把新梯次各科的 PDF 網址記到tools/sources.json。 -
抽文字(每科一份):
./tools/extract.sh '<PDF網址>' /tmp/exam.txtpdftotext -layout;官方答案在每題最左欄(可能是全形 Ａ-Ｄ,要轉半形再轉 0-based:A=0 B=1 C=2 D=3)。 -
結構化成題目(這步要你 AI 判讀
/tmp/exam.txt):每題輸出{level, round, subject, question, options[4], answer, chapter, topic, explanation}, 寫成一個陣列檔/tmp/new.json。answer取最左欄官方答案。explanation自己寫(為何對 + 為何其他錯 + 概念)。chapter用官方學習指引的章節名(沿用既有題庫已用過的)。- 字串內不要用半形雙引號
",用「」。
-
帶圖題(題幹有「下圖/程式碼/圖表」純文字抽不到的):用
pdfimages -png -p '<pdf>' /tmp/e取乾淨內嵌圖(忽略每頁固定尺寸的頁首裝飾圖;不要用含左側答案欄的整頁截圖)。圖用pdfimages取出後轉 WebP lossless、命名為<該題 id>.webp存到assets/(例如assets/115-2-m-s3-f1.webp),該題填image: "assets/<id>.webp"。別沿用 PDF 原始圖號(早期 114-2 沒這樣、踩過坑);題幹寫「附圖」就一定要掛上。中文標點用全形(夾純英文括號維持半形)。 -
加入 + 驗證:
node tools/add-questions.mjs /tmp/new.json --dry-run # 先試跑 node tools/add-questions.mjs /tmp/new.json # 沒錯再加 node tools/check-questions.mjs # 健康檢查:圖/檔名/附圖漏掛/結構/標點(要全綠) node core.test.mjs -
收尾:bump
sw.js的CACHE版號;tools/sources.json該梯次標status: done;commit + push。
詳細資料 schema 見 AGENTS.md。
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.
- 11d ago First seen · 42 lines · 67 tokens per session scan A 76e3aebcd99c
add-exam is a skill published in the GitHub repository yazelin/ipas-ai-quiz (24 stars, last pushed 4d ago), licensed MIT. It adds 67 tokens to every session and 840 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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…
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
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.
master-yinguang
A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.