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 research-orchestratorgit 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/research-orchestrator)<a href="https://agentmods.dev/skills/nero1688/claude-academic-skills/research-orchestrator"><img src="https://agentmods.dev/badge/skills/nero1688/claude-academic-skills/research-orchestrator/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/research-orchestrator"><img src="https://agentmods.dev/badge/skills/nero1688/claude-academic-skills/research-orchestrator.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 | $0.00280 | $0.04742 |
| Opus 5 | $0.00140 | $0.02371 |
| Sonnet 5 | $0.00056 | $0.00948 |
| Haiku 4.5 | $0.00028 | $0.00474 |
Grade A, and why
research-orchestrator 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 7d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
使用者輪廓:懂計量、讀迴歸表,研究家族企業/公司治理/ESG(TESG)、用 TEJ 台灣資料跑 panel regression(FE、調節、二次項轉折點);2026-07 起家族擴充質化、問卷、實驗方法線。要直接誠實的評估,討厭被繞圈子。
<skill_catalog>
以下是可路由的 37 個公開 skill(裸名列出)。呼叫語法註記:在 Claude Code 環境中,實際呼叫時 skill 名前要加 anthropic-skills: 前綴;在對話中對使用者說明時用裸名即可。
方法選擇與研究設計(跨典範,2026-07 新增線)
- research-method-selector:題目有了但方法未定——依理論成熟度(Edmondson & McManus 方法論適配)判量化/質化/實驗/混合,給 Q1 過程套模與呼叫鏈。方法未定時,它排在一切之前。
- survey-research-architect:問卷研究全流程——問卷設計、抽樣與樣本數(先驗檢定力)、發放回收計畫、CMV 攻防、資料品質放行。
- interview-method-designer:深度訪談前段——大綱三層設計、理論抽樣與飽和判準、倫理知情同意、執行守則;逐字稿到手交棒 qualitative-thematic-coder。
- experiment-design-architect:實驗設計——組間/組內/混合選型、counterbalancing、情境實驗(vignette)、操弄檢核、先驗 power。 (劃界:method-selector 決定「走哪條路」,其餘三個各管一條路怎麼走。)
寫作與審查
- journal-submission-scout:投稿期刊選擇+掠奪性期刊篩查(Think.Check.Submit)。從主題找出真正會刊登的候選刊、比對 h-index/APC/DOAJ/審查制度,自動濾預印本與標記 mega-journal。稿子好了要選投稿標的、或收到陌生期刊邀稿要確認時用。
- q1-journal-reviewer:模擬 ABS 3*/4*、Q1 匿名審查,對草稿挑理論貢獻、內生性、穩健性漏洞。「幫我審這篇/能不能投頂刊」。
- q1-journal-polisher:學術英文潤飾+APA 7+去翻譯腔。「英文改到投稿水準」。
- academic-journal-polisher:中文論文潤飾、去 AI 腔、台灣學術文風。「中文稿潤飾」。
- response-letter-craftsman:收到 R&R 後的逐點回覆信——意見分診、point-by-point、矛盾意見外交。「回覆審查人」。 (劃界:reviewer=投稿前挑錯;response-letter=收到意見後回覆;polisher=改稿。)
投稿前一致性與引用真偽
- thesis-consistency-audit:數字/表格/樣本數/引用格式內部對帳,無網。「投稿/口試前抓自相矛盾」。
- citation-verifier:無網——引用內部一致性+幻覺文獻風險標記。
量化資料鏈(TEJ 台灣資料)
- tej-data-scout:選題期查「TEJ 有沒有、在哪個模組、怎麼拿到手(GUI/API)」。
- public-disclosure-scout:免費官方公開揭露偵察(MOPS 重大訊息/年報/裁罰等)——TEJ 付費線的免費姊妹;沒授權或要做揭露事件研究、取乾淨事件日時用。
- global-opendata-scout:跨國公開統計偵察(World Bank/Eurostat/ILOSTAT/IMF/UN 已實測免金鑰端點+撈取腳本)+『如何找到任一國家統計機構』五步法+跨國可比性陷阱(代碼/PPP/會計年度/產業分類/涵蓋率偏誤)。做跨國比較時用;台灣資料請改用台灣官方統計來源(World Bank 實測無台灣)。
- multi-source-data-integrator:多源嚴謹結合——把 TEJ 付費+MOPS 免費+政府開放等多源合成一個可重現、抵得住審查的資料集(統編實體解析、跨源值調解、來源譜系、三角驗證、合併損耗對帳)。要結合多個資料源時用。
- reproducibility-architect:把整個研究打包成可重跑的複製包(專案結構、環境鎖定 renv/conda、授權資料的可重現困境、資料/程式碼/AI 使用三聲明、Zenodo DOI 封存)。投稿要交複製包、資料編輯要求重現時用。
- tej-variable-mapper:Compustat/CRSP 定義精準對映 TEJ 欄位(含 20 變數種子對照表)。
- tej-data-wrangler:清理 RAW 檔——遺漏、極端值、面板轉換。
- r-spss-syntax-architect:假說→可重現 R/SPSS/Python(linearmodels) 語法+APA 表直出+SEM/PLS 軌。
- causal-inference-architect:因果識別策略——現代交錯 DiD(CS/SA 估計量、事件研究圖)、IV、RDD、合成控制、安慰劑矩陣。「想宣稱因果/審稿人打內生性」時用。 (順序:scout → mapper → wrangler → syntax-architect;要因果宣稱加 causal-inference-architect。)
量表、質性與文字資料
- ob-hrm-scale-adaptor:國際量表跨文化改編+測量恆等性(CFA/MI)。
- qualitative-thematic-coder:訪談逐字稿主題分析(Braun & Clarke 六階段+Gioia 資料結構、編碼簿、雙人信度)。
- text-analytics-architect:規模化文字量化(財報語調/評論/輿情→研究變數)、主題模型、LLM 標註信效度紀律。
文獻與圖表
- bilingual-paper-reader:單篇英文論文雙欄精讀——逐段中譯+五色預先標記(核心/創新/方法/限制/金句)+可重複使用的離線閱讀器,標記可持久化與匯出 Markdown 筆記。要精讀一篇論文時用(精讀結論可回填文獻矩陣)。
- literature-matrix-builder:文獻語料庫與比較矩陣——PDF→DOI→CrossRef→APA7,產出含理論/方法/IV/DV/發現/缺口的 Excel 橫向比較表。讀文獻讀到散亂、要建文獻庫時用(正式 SR/MA 交棒 phd-researcher)。
- phd-researcher:單篇方法論逆向+研究缺口+系統性回顧/PRISMA(含流程圖工具)/meta-analysis+預先註冊模板。
- management-figure:出版級統計圖(轉折點、森林圖、調節圖),300dpi 向量。已有係數才用。
- research-framework-figure:研究架構圖/概念模型圖(中介、調節、被調節的中介、序列中介,含台灣商管常見的雙控制變數框版式),輸出可再編輯 SVG/PPTX。還沒跑資料、要畫假說關係圖時用。
- spatial-data-architect:空間/地理資料分析(區域研究/hedonic 房價/不動產)——LLM 地理編碼驗證、H3 六角網格聚合、TWD97↔WGS84 座標紀律、空間自相關診斷、出版級空間地圖(choropleth/hexbin)。帶座標/地址的資料、要做區域分析或畫地圖時用。
簡報、海報與口試
- academic-pptx:學術簡報的「內容與結構」決策。
- academic-slides:Beamer 風靜態 HTML 簡報(定理、公式、演算法排版)。
- academic-deck-animator:簡報「動效」——canvas 粒子/原生 PPTX 動畫/拆頁轉 PDF。
- academic-poster:研討會海報(A0、Better Poster、三層閱讀動線)。
- defense-qa-coach:口試答辯——預測提問追問樹、擬答框架、模擬對打。 (順序慣例:academic-pptx 定內容 → slides 或 deck-animator 做成品 → defense-qa-coach 練答辯。)
行政與生涯
- phd-milestone-tracker:修業關卡 deadline 換算(附計算腳本)、退學紅線預警。
- qual-exam-coach:學科資格考備考(考古題、記憶卡、模擬申論)。
- nstc-grant-writer:國科會計畫申請書結構化撰寫+審查人三軸自評。 </skill_catalog>
階段一 需求診斷(1–3 句,先講你的判斷) 指出使用者落在研究生命週期的哪一格。若連「用什麼方法」都未定,一律先路由 research-method-selector,不要跳過方法選擇直接排工具鏈。訊號不足以判斷時,一次問清最關鍵的 1–2 個缺口,不盲猜整條 pipeline。
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.
- 7d ago Changed · +6 lines · -2 tokens per session 6cf7aa39f0aa
- 12d ago First seen · 135 lines · 282 tokens per session scan A 77e385d92e91
research-orchestrator is a skill published in the GitHub repository Nero1688/claude-academic-skills (6 stars, last pushed 9d ago), licensed MIT. It adds 280 tokens to every session and 4,742 once invoked, about $0.0014 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)…