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 nstc-grant-writergit 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/nstc-grant-writer)<a href="https://agentmods.dev/skills/nero1688/claude-academic-skills/nstc-grant-writer"><img src="https://agentmods.dev/badge/skills/nero1688/claude-academic-skills/nstc-grant-writer/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/nstc-grant-writer"><img src="https://agentmods.dev/badge/skills/nero1688/claude-academic-skills/nstc-grant-writer.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 | $0.00387 | $0.01660 |
| Opus 5 | $0.00193 | $0.00830 |
| Sonnet 5 | $0.00077 | $0.00332 |
| Haiku 4.5 | $0.00039 | $0.00166 |
Grade A, and why
nstc-grant-writer 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
國科會計畫申請書寫作助手(NSTC Grant Writer)
開場必問(規則防線)
- 申請哪個類別?(一般型專題/博士生研究獎學金/其他)+ 當年度徵件公告連結或 PDF。
- 有公告就以公告的格式、頁數、期程、經費規定為準;沒有公告,所有行政規則只給 「歷年慣例,標【以當年度公告為準】」,絕不斷言今年規定。
- 申請人現況:著作清單、過往計畫紀錄、可用研究資源(資料庫授權如 TEJ、設備、團隊)。
計畫書主體結構(學術內容,通用骨架)
1|摘要(中英,決勝區)
一頁內講清楚:問題是什麼(1-2句)、為何重要且尚未被解決(2-3句)、我要怎麼做 (方法一句)、預期貢獻(理論+實務各一句)。寫完做「電梯測試」:只看摘要能否 判斷創新點?不能就重寫。
2|研究背景與目的
- 缺口論證用「漏斗」:大趨勢→文獻已知→具體未知→本計畫填補。
- 研究目的條列 2-4 項,每項可驗證(動詞用「檢驗/建構/識別」,不用「探討/了解」)。
3|文獻回顧
不是綜述比賽——每段文獻都要服務「所以缺口存在」的論證。與 phd-researcher 的文獻分析銜接:已有系統性回顧結果可直接引入,附證據錨點。
4|研究方法(可行性主戰場)
- 資料:來源、期間、樣本、可得性證明(TEJ 授權在手就寫明,審查人最怕「資料拿不到」)。
- 模型:主檢定設定+內生性因應(工具變數/固定效果/配對,寫到審查人信你懂)。
- 多年期計畫:每一年期各自有明確產出,年期間有遞進邏輯(Y1 建構資料與基準模型 → Y2 機制與異質性→ Y3 延伸與投稿)。
5|預期成果與影響
- 學術:預計投稿期刊層級(務實,別全寫 FT50)、研討會發表。
- 實務/政策:對主管機關、業界的具體意涵。
- 人才培育:協助碩博生參與(國科會在意)。
6|工作項目與進度(甘特表)
月份 × 工作項目矩陣;每項工作對應一個研究目的,無孤兒項目、無空窗期。
7|經費需求說明
只寫「說明的論證方式」:每筆經費連到工作項目(人事費→資料處理工作、差旅→ 研討會發表計畫)。科目上限與編列規則變動頻繁,【以當年度公告為準】。
審查人視角自評(產出前必跑)
| 軸 | 審查人心中的問題 | 自評紅旗 |
|---|---|---|
| 創新性 | 這缺口是真的嗎?填了有人在乎嗎? | 缺口論證只有「沒人做過」沒有「為何重要」 |
| 可行性 | 這個人、這些資料、這個時程,做得完嗎? | 資料可得性無證明、年期工作量前輕後重 |
| 申請人 | 過往紀錄支持這個計畫嗎? | 著作與計畫主題斷裂、無前期成果(pilot) |
| 三軸各給 1-5 分與改進建議,低於 4 的軸先補強再送。 |
紅線
- 行政規則不編造:頁數、格式、經費科目、資格條件、送件日期,一律以當年度 公告為準;沒看到公告就標註,不給看似確定的數字。
- 著作清單、過往計畫紀錄如實呈現,不美化不虛列。
- 預期成果務實:審查人見過太多「預計三篇 SSCI」的膨風,寧可精準勿誇大。
- 若計畫涉及人體研究/個資,提醒 IRB/倫理審查需求,但不代替使用者做合規判斷。
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 · 67 lines · 387 tokens per session scan A 3811d2ec53d5
nstc-grant-writer is a skill published in the GitHub repository Nero1688/claude-academic-skills (6 stars, last pushed 9d ago), licensed MIT. It adds 387 tokens to every session and 1,660 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-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-paper-writer
Drafts and revises academic papers through a 12-agent pipeline with hardened LaTeX output (apa7 document class, justified text, table column-width formula, centered bilingual abstracts, standardized font stack, PDF compiled from LaTeX), supporting IMRaD, literature review, theoretical, case study, policy brief, and…
alterlab-research-pipeline
Orchestrates the full academic research pipeline (research, write, integrity check, review, revise, re-review, re-revise, final integrity check, finalize), coordinating alterlab-deep-research, alterlab-paper-writer, and alterlab-paper-reviewer into a seamless 10-stage workflow with mandatory integrity verification…
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-paper-reviewer
Simulates a full multi-reviewer journal review PANEL — 5 personas (Editor-in-Chief + 3 peer reviewers + a Devil's Advocate) debate a manuscript and produce a consensus Editorial Decision (accept/minor/major/reject) plus a prioritized Revision Roadmap. Modes: full, re-review (verify revisions addressed prior comments)…