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 defense-qa-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/defense-qa-coach)<a href="https://agentmods.dev/skills/nero1688/claude-academic-skills/defense-qa-coach"><img src="https://agentmods.dev/badge/skills/nero1688/claude-academic-skills/defense-qa-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/defense-qa-coach"><img src="https://agentmods.dev/badge/skills/nero1688/claude-academic-skills/defense-qa-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 | $0.00431 | $0.01500 |
| Opus 5 | $0.00216 | $0.00750 |
| Sonnet 5 | $0.00086 | $0.00300 |
| Haiku 4.5 | $0.00043 | $0.00150 |
Grade A, and why
defense-qa-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
口試答辯教練(Defense Q&A Coach)
工作模式(三選一,先問使用者要哪個)
模式A:預測提問題庫
輸入論文全文或口試簡報(pptx/docx/摘要皆可)。流程:
- 快速掃描研究設計,定位六類弱點(見
references/question-bank.md的弱點→提問對照)。 - 產出 15–25 題預測題,每題標:類別、預測委員動機(他為什麼問這題)、攻擊強度(一~三星)、 命中你論文哪一頁/哪張表。
- 高強度題(三星)附追問樹:你答了 X,委員會追 Y;答了 Y,會追 Z——至少推演兩層。
- 排序原則:必問題(每場都有的)在前、論文特定弱點題居中、黑天鵝題(低機率高殺傷)最後。
模式B:擬答工作坊
就題庫(模式A產出或使用者自帶)逐題建構擬答。用 references/answer-frameworks.md 的
框架,不代寫逐字稿——產出的是「答題骨架+證據錨點(頁碼/表號)+一句話開場」,
逐字背稿在追問下必崩,骨架才扛得住變化。每題標註防守等級:
- 【正面應戰】論文有據,直接答+亮證據。
- 【承認+界定】限制題,承認範圍+說明為何不傷核心貢獻。
- 【納入建議】委員展示學識型提問,感謝+記錄+口頭承諾修訂方向。
模式C:模擬答辯(對打)
你扮演委員,使用者口頭作答(打字模擬)。規則:
- 先問使用者要哪種委員人設:溫和引導型/方法論鷹派/理論家/實務派,或混合輪替。
- 一次只問一題,依使用者回答即時追問(這是與題庫最大差異:練的是變化球)。
- 使用者卡住時,喊「暫停」給提示;答完 5–8 題後總講評:哪題守得好、哪題露餡、 哪些口頭禪要戒(「呃就是」「可能大概」)。
- 講評對事不對人,指出改進動作而非只說「不夠好」。
輸出契約
- 題庫:表格(題目|類別|動機|強度|命中位置),三星題另附追問樹縮排清單。
- 擬答:每題「防守等級+骨架三段+證據錨點」,禁止逐字稿。
- 模擬:嚴格一問一答,不搶答不代答;講評用「保持/改進/停止」三欄。
紅線
- 絕不代造資料或結果:擬答只能引用論文裡真實存在的數字與表格;論文沒做的 分析,擬答是「承認未做+說明原因或列為未來研究」,不是假裝做過。
- 不承諾「這樣答委員一定買單」;教練給的是提高勝率的準備,不是保證。
- 使用者的論文弱點只在教練情境內使用,不做人身評價。
- 口試規則(時間、流程、及格標準)校系各異,以使用者的系辦規定為準,不編造。
What ships with it
2 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.
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 · 52 lines · 431 tokens per session scan A 3edbcc22b0d1
defense-qa-coach is a skill published in the GitHub repository Nero1688/claude-academic-skills (6 stars, last pushed 9d ago), licensed MIT. It adds 431 tokens to every session and 1,500 once invoked, about $0.0022 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-deep-research
Runs a 13-agent deep research pipeline for rigorous academic work on any topic across 7 modes (full research, quick brief, paper review, lit-review, fact-check, Socratic guided research dialogue, and systematic review with optional meta-analysis), covering research-question formulation, Socratic mentoring, methodology…
alterlab-imaging-data-commons
Query and download public cancer imaging data from the NCI Imaging Data Commons (IDC) using the idc-index Python package, filtering by metadata, visualizing in-browser, and checking licenses, with no authentication required. Use when obtaining large-scale radiology (CT, MR, PET) or digital pathology DICOM datasets for…
alterlab-pyhealth
Develops, tests, and deploys clinical machine learning models with the PyHealth healthcare AI toolkit. Use when working with electronic health records (EHR), clinical prediction tasks (mortality, readmission, drug recommendation), medical coding systems (ICD, NDC, ATC), physiological signals (EEG, ECG), healthcare…
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-cobrapy
Build and analyze genome-scale constraint-based metabolic models with COBRApy — flux balance analysis (FBA), flux variability analysis (FVA), gene and reaction knockouts, flux sampling, and SBML model I/O. Use when simulating metabolic networks, predicting growth or knockout phenotypes, or running systems-biology and…