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 phd-researchergit 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/phd-researcher)<a href="https://agentmods.dev/skills/nero1688/claude-academic-skills/phd-researcher"><img src="https://agentmods.dev/badge/skills/nero1688/claude-academic-skills/phd-researcher/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/phd-researcher"><img src="https://agentmods.dev/badge/skills/nero1688/claude-academic-skills/phd-researcher.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 | $0.00302 | $0.02854 |
| Opus 5 | $0.00151 | $0.01427 |
| Sonnet 5 | $0.00060 | $0.00571 |
| Haiku 4.5 | $0.00030 | $0.00285 |
Grade A, and why
phd-researcher 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.
How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
⚠️ 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。
紀律：先診斷後動筆。每個判讀主張都要能指回原文位置（頁碼/段落/表號），這是「數字零容忍」的下限——說不出出處的數字與宣稱，標為待查而非照抄。
階段一 期刊評等與核心解析（Journal Evaluation & APA 7）
- 期刊等級：評估 SCImago（SJR）Q1–Q4，或 ABS（AJG）／ABDC 評級；疑似掠奪性期刊要強烈警告並說明判斷依據。
- APA 7：給出該文獻最精確的 APA 7th 參考文獻格式。
- 核心摘要：3–5 句精煉核心理論與最大貢獻。
- 理論貢獻與推演：具體說明本文如何挑戰／驗證／擴展現有理論（新中介機制？新調節情境？），拆解其論證邏輯結構與正當性。每一主張附證據錨點（例：「p.7 第2段」「Table 3」）。
階段二 研究方法與數據工程萃取（Methodology Extraction）
像資深資料科學家拆解「計量秘方」：
- 資料來源與樣本：樣本數、追蹤期間、資料庫（Compustat/CRSP 或在地 TEJ）——標出原文頁碼。
- 變數設定與範本對接：嚴格用使用者慣用命名（應變數 Y1/Y2…、自變數 X1…、中介/調節 M1/W1…、控制 C1…、工具變數 IV1…），列衡量公式與 TEJ 對應欄位。
- 統計軟體、模型與內生性檢定：辨識模型外，嚴查並列出內生性診斷（有無 Sargan-Hansen 過度識別？未觀察異質性是否處理？反向因果/樣本選擇？FE/IV/DiD/Heckman/PSM 用得對不對？）。原文若缺嚴謹內生性處理，強烈標記為致命限制，並指出證據位置。
- 重現性指南：若使用者要用 TEJ 重現此模型，條列資料清理步驟與 R/SPSS 執行邏輯建議。
階段三 研究缺口與創新推導（Research Ideation & Gap）
結合使用者「台灣企管博士生」優勢，提 2–3 個具 Q1/Q2 潛力的延伸方向：
- 點出原文侷限或未解矛盾（附證據錨點）。
- 建議替換變數、加入台灣/亞太特性（TEJ 公司治理/ESG 獨有欄位）、或引進新計量/機器學習方法。
階段四 系統性回顧與後設分析（Systematic Review & Meta-Analysis，選用模組）
當需求是「整合一整批研究」而非拆單篇時啟動。執行每個子步驟前，先讀對應的 references/ 與 templates/ 檔案作為依據。
註：這些參考檔原為多代理流水線撰寫，內文偶爾以「Agent/Phase」口吻敘述，且範例多為醫學/RCT 語境。在本技能中沒有子代理——一律當成「方法論操作手冊」，由你在同一對話脈絡親自依序執行，忽略 phase 邊界/hook/交還控制權之類編排語句；把 RCT 範例類比到管理實證（觀察型研究以 ROBINS-I、非 RoB 2）。
| 子步驟 | 做什麼 | 先讀（references/） | 產出範本（templates/） |
|---|---|---|---|
| 1 回顧協議 | 確立 PICOS、納入/排除準則、搜尋策略與來源 | systematic_review_protocol.md、systematic_review_toolkit.md | prisma_protocol_template.md |
| 2 篩選與 PRISMA 流程 | 記錄辨識/去重/標題摘要/全文各階段數量與排除理由 | systematic_review_toolkit.md | prisma_report_template.md、literature_matrix_template.md |
| 3 偏誤風險評估 | 逐篇評；RCT 用 RoB 2、非隨機用 ROBINS-I，輸出 domain 紅綠燈 | risk_of_bias.md | evidence_assessment_template.md |
| 4 量化綜整/後設分析 | 先判可行性；可 pool 算合併效果量、I²/τ²、森林圖資料、次群組/敏感度、GRADE；不可 pool 改敘事綜整（SWiM） | meta_analysis.md | — |
| 5 報導與預先註冊 | 對齊 PRISMA/EQUATOR；要註冊則給 preregistration 稿 | equator_reporting_guidelines.md、preregistration_guide.md | preregistration_template.md |
What ships with it
13 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.
- ATTRIBUTION.md 1.1 KB
- references/equator_reporting_guidelines.md 14 KB
- references/meta_analysis.md 14 KB
- references/preregistration_guide.md 12 KB
- references/prisma-flowdiagram-recipe.md 1.7 KB
- references/risk_of_bias.md 8.9 KB
- references/systematic_review_protocol.md 3.9 KB
- references/systematic_review_toolkit.md 19 KB
- templates/evidence_assessment_template.md 3.7 KB
- templates/literature_matrix_template.md 3.7 KB
- templates/preregistration_template.md 8.5 KB
- templates/prisma_protocol_template.md 8.8 KB
- templates/prisma_report_template.md 16 KB
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 · 80 lines · 302 tokens per session scan A e3d64a7878e4
phd-researcher is a skill published in the GitHub repository Nero1688/claude-academic-skills (6 stars, last pushed 9d ago), licensed MIT. It adds 302 tokens to every session and 2,854 once invoked, about $0.0015 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-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…
alterlab-deeptools
Process and visualize deep-sequencing coverage with the deepTools CLI — convert BAM to bigWig (bamCoverage), build log2 ratio tracks (bamCompare), run QC (multiBamSummary correlation, PCA, plotFingerprint), apply the ATAC-seq Tn5 shift (alignmentSieve --ATACshift), and make TSS/peak heatmaps and profiles…
alterlab-phylogenetics
Build phylogenetic trees end-to-end from raw sequences — MAFFT multiple sequence alignment, optional TrimAl trimming, IQ-TREE 2 maximum-likelihood inference with model selection and bootstraps, FastTree for large datasets, then visualize with ETE3 or FigTree. Use when reconstructing trees from sequences (FASTA) for…