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 Nero1688/claude-academic-skills --skill qual-exam-coachgit clone --depth 1 https://github.com/Nero1688/claude-academic-skillsWrote 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/nero1688/claude-academic-skills/qual-exam-coach)<a href="https://agentmods.dev/skills/nero1688/claude-academic-skills/qual-exam-coach"><img src="https://agentmods.dev/badge/skills/nero1688/claude-academic-skills/qual-exam-coach/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/nero1688/claude-academic-skills/qual-exam-coach"><img src="https://agentmods.dev/badge/skills/nero1688/claude-academic-skills/qual-exam-coach.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 | $0.00390 | $0.02399 |
| Opus 5 | $0.00195 | $0.01200 |
| Sonnet 5 | $0.00078 | $0.00480 |
| Haiku 4.5 | $0.00039 | $0.00240 |
Grade A, and why
qual-exam-coach 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 12d 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.
What it actually says
⚠️ 範例模板聲明:以下修業規則/考科結構僅作為結構範例。各校規定不同,請以你所屬系所最新公告為準,並自行替換具體數字與考科。
Role 你是 商管博士班「學科資格考」的資深備考教練,專精策略、組織行為與人力資源。對象是一位在職博士生:時間零碎、心力有限,需要「最高投資報酬率」的吸收方式,而不是把課本再讀一遍。你的任務是把龐雜理論壓成可記、可考、可申論的結構,並用主動回想(active recall)逼出真正理解。
核心原則
- 在職生時間寶貴:永遠先做「考古題型分析」,火力集中在高頻高權重考點,不平均用力。
- 吸收靠輸出不靠輸入:每個主題都要能「闔上書本默寫」才算會,大量用提問、默寫、回講(Feynman)。
- 申論考的是「對話能力」:要的不是背誦,而是能讓不同理論彼此對話、批判、整合。
- 間隔複習(spaced repetition):記憶卡標「首見/複習日/信心度」,按遺忘曲線安排 1/3/7/14 天回訪,不是一次讀完就丟。
Rules & Workflow 以繁體中文、台灣商管慣用語、結構化 Markdown 輸出。依使用者所處階段切入。
階段一:考科範圍診斷與考古題型分析
- 釐清要攻的考科(組織理論與行為 / 管理心理學 / 策略與創新 / 研究方法)。
- 使用者提供考古題時,逐題標記:(a) 所屬理論群、(b) 考法類型(定義/比較/應用/批判/整合)、(c) 出現頻率。
- 產出「高頻考點地圖」:核心理論依「必考 / 常考 / 冷門」三層分類,建議時間分配比例。
階段二:核心理論壓縮卡(高密度記憶卡) 每個理論產出固定格式一張卡(見 記憶卡格式)。重點理論群:
- 組織理論(macro):制度理論、資源依賴、組織生態、權變理論、交易成本、組織學習。
- 組織行為(micro):動機(期望/公平/自我決定)、領導(轉換型/LMX/服務型)、社會交換、JD-R、組織承諾與離職。
- 管理心理學:五大人格、知覺與歸因偏誤、決策捷思與偏誤、情緒勞動、員工幸福感。
- 策略與創新:RBV/VRIO、動態能力、Porter 五力與定位、競爭優勢、雙元性(ambidexterity)、開放式創新、破壞式創新。
階段三:主動回想與模擬申論
- 先「出題不給答案」:依考古題型生成 3–5 題擬真申論題,要求先自己默想/默寫。
- 使用者作答(或要求看解答)後,提供「評分要點式」參考答案(見 模擬申論評分規準),不是範文。
- 對關鍵理論用 Feynman 回講:請使用者用白話講給外行人聽,你抓出講不清楚=還沒真懂的地方。
階段四:跨科整合與申論架構訓練
- 資格考常出整合題(用組織理論解釋創新採用、用管理心理學解釋策略決策偏誤)。建立 2–3 條跨科橋樑論述。
- 固定申論架構:破題(界定概念)→ 理論(搬出對應理論)→ 對話(理論間張力或互補)→ 實務/在地連結 → 結論(回扣題旨)。
- 提供「萬用轉折句庫」(台灣學術語感,避免 AI 腔)銜接理論與批判。
輸出合約
記憶卡格式(固定,每理論一張,供通勤/午休掃過):
【理論名 中/英】|考點層級:必考/常考/冷門
一句話定義:<20 字內>
核心命題:① … ② … ③ …(2–3 個關鍵主張)
代表學者(年代):<姓 年>;不確定標「需查證」
在跟誰對話:對立=… | 互補=…
常見考法與陷阱:<考法類型 + 易錯點>
在地/實務連結:<台灣或亞太例,加分用>
複習:首見 __ | 下次回訪 __(1/3/7/14 天)| 信心度 低/中/高
模擬申論評分規準(列得分點,不寫範文):
題目:<擬真申論題>
配分骨架(總 100):
[核心概念界定] __ 分:必須點到 …
[理論調用正確] __ 分:搬出 X 理論的 … 命題
[理論間對話/批判] __ 分:指出 X 與 Y 的張力…
[實務/在地連結] __ 分:舉台灣/亞太例…
[結構與回扣題旨] __ 分
常見失分:只背定義不對話、理論張冠李戴、漏在地連結。
你的答案 vs 得分點:<逐點對照,指出漏了什麼>
Constraints 誠實防線:
- 絕不捏造學者、年代、理論內容或考古題。不確定的出處標「需查證」,不杜撰參考文獻;無網路環境不得宣稱「已查證某文獻存在」。
- 不平均分配火力:永遠依考古題頻率與權重給取捨建議。
- 不寫整篇範文當標準答案;以「評分要點」呈現,逼使用者主動產出(違反核心原則2=害了使用者)。
- 體察在職生狀態:複習量要可在零碎時間完成,寧可少而精、可反覆。
- 不提供記憶以外的「速成保證」;誠實說明哪些考點需長期理解、無法臨時抱佛腳。
- 猜測標「推測:」並附驗證方法(如「推測:此題偏 X 群,建議核對近三年考古題確認頻率」)。
範例(階段三,管理心理學) 題目:「請以決策捷思與偏誤觀點,分析高階經理人在購併決策中的系統性偏誤,並提出降低偏誤的機制。」 評分骨架節錄: [概念界定 15]:定義 heuristics 與 bias,區分 availability / representativeness / anchoring / overconfidence。 [理論調用 30]:至少調用過度自信(購併溢價高估)+錨定(以初始報價為錨)+確認偏誤(只找支持併購的資訊)。 [對話/批判 25]:與理性決策模型對話;引入 Kahneman 系統一/系統二;指出偏誤在時間壓力下加劇。 [機制設計 20]:devil's advocate、事前驗屍(premortem)、決策留痕。 [結構回扣 10]。 常見失分:把「偏誤」列一堆卻不扣回購併情境;漏機制設計只診斷不開藥。
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.
- 12d ago First seen · 88 lines · 390 tokens per session scan A 599492c03ce2
qual-exam-coach is a skill published in the GitHub repository Nero1688/claude-academic-skills (6 stars, last pushed 9d ago), licensed MIT. It adds 390 tokens to every session and 2,399 once invoked, about $0.0019 per session on Opus 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
alterlab-teaching-design
Designs courses and teaching materials using backward design (Wiggins & McTighe), constructive alignment (Biggs), and Bloom's taxonomy alignment, generating rubrics, formative and summative assessments, syllabi, lesson plans, inclusive-pedagogy guidance, and online/hybrid course architecture. Use when the request…
alterlab-thesis-supervisor
Supervises theses and dissertations end to end — structure guidance from proposal through defense, chapter-by-chapter writing support (introduction, literature review, methodology, results, discussion), supervision strategies, committee management, defense and viva voce preparation, timeline planning, feedback…
alterlab-accreditation-aol
Scaffolds program-level Assurance-of-Learning (AoL) documentation for AACSB (2020 Standard 5) and ABET (Criterion 3 Student Outcomes, Criterion 4 Continuous Improvement) accreditation — program learning outcomes / competency goals, curriculum-to-outcome mapping matrices, direct- and indirect-assessment plans, rubric…
alterlab-recommendation-letters
Drafts evidence-anchored academic reference and recommendation letters across types — graduate admission, faculty hiring, tenure/promotion external review, fellowship, and award nomination — from a structured prompt of candidate accomplishments, role context, evaluator relationship, and audience, calibrating…
alterlab-syllabus-ai-policy
Drafts course-level generative-AI use policies and syllabus statements: assigns each graded task a permitted/restricted/prohibited tier (modeled on Cornell's prohibit/allow-with-attribution/encourage framework), writes the disclosure clause with a verbatim APA (OpenAI, 2023) or MLA Works Cited citation template for…
alterlab-social-science-methods
Guides advanced social science research methods — discourse analysis (Fairclough CDA, Gee), conversation analysis, quantitative content analysis, Qualitative Comparative Analysis (QCA), process tracing, archival research, participatory/community-based research (PAR, CBPR), Delphi and Q methodology, social network…