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 survey-research-architectgit 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/survey-research-architect)<a href="https://agentmods.dev/skills/nero1688/claude-academic-skills/survey-research-architect"><img src="https://agentmods.dev/badge/skills/nero1688/claude-academic-skills/survey-research-architect/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/survey-research-architect"><img src="https://agentmods.dev/badge/skills/nero1688/claude-academic-skills/survey-research-architect.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 | $0.00449 | $0.01790 |
| Opus 5 | $0.00225 | $0.00895 |
| Sonnet 5 | $0.00090 | $0.00358 |
| Haiku 4.5 | $0.00045 | $0.00179 |
Grade A, and why
survey-research-architect 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
問卷研究架構師(Survey Research Architect)
Step 1|構念到題項(設計)
- 量表選用順位:既有中文驗證量表 > 國際量表正式改編(轉 ob-hrm-scale-adaptor 做翻譯回譯+MI)> 自編(自編=審稿最大風險,須完整走量表發展程序,勸阻輕率自編)。
- 問卷結構:篩選題 → 核心構念(依變數與自變數分區並隔開)→ 控制變數 → 人口統計(放最後)。每構念題數、計分格式(Likert 5/7 點)與原量表一致。
- CMV 程序性預防(設計進問卷,這是重點):
- 心理分離:不同構念用不同指導語/情境框架。
- 時間分離:X 與 Y 分兩波(間隔 2–4 週),用受訪者代碼串接。
- 來源分離:主管評 Y、員工評 X(組織研究金標準)。
- 匿名保證+「沒有標準答案」聲明(降社會期許)。
- 反向題節制使用(防直線作答,但過多傷信度——每構念至多一題)。
- 資料品質防線:注意力檢查題(「此題請選非常同意」)1–2 題、作答時間下限 (題數×2秒為底線)、開放題一題(偵測敷衍)。
Step 2|抽樣與樣本數(先驗,不是事後)
- 母體與抽樣框:明確定義(如台灣製造業主管),說明接觸管道與其偏誤 (EMBA 班/企業合作/研究公司 panel 各有外推性代價,誠實揭露)。
- 樣本數三算法取大者:
- 檢定力分析:主檢定的最小效果量(引前研究)→ α=.05、power=.80 反推 N。
- SEM 經驗法則:估計參數 × 5–10。
- 回收率折算:所需完成數 ÷ 預期回收率(冷名單 10–20%、有關係管道 30–60%) ÷ 品質淘汰率(留 85–90%)= 實際發放數。
- 多波次設計要再乘各波流失(每波約流失 20–40%)。
Step 3|發放與回收執行計畫
產出發放甘特表:前測(30–50 份,驗信度與語意)→ 修訂 → 正式第一波 → 催收(第 7、14 天兩次,措辭漸強但禮貌)→ 第二波(若時間分離)→ 關閉。
- 誘因設計:抽獎 vs 每人小額,揭露於知情同意;學術倫理與個資聲明(問卷首頁)。
- 回收監控:每日回收數、完成率、中斷點分析(哪一頁大量放棄=該頁有問題)。
- 無反應偏誤分析(投稿必備):早晚回覆者比較(wave analysis)+已知母體 特徵比對(產業/規模分布)。
Step 4|回收後品質放行與 CMV 事後檢驗
- 淘汰:未過注意力檢查、作答時間過短、直線作答(SD≈0)、規律作答——淘汰 標準事先寫定(最好預先註冊),不能看結果挑人。
- CMV 統計檢驗(至少兩種並陳):Harman 單因子(必做但公認不足)+ 標記變數法 (設計時就要埋理論無關標記題)或 CFA 共同方法因子。
- 放行報告:有效樣本數、淘汰明細、回收率、無反應偏誤結論 → 交棒 ob-hrm-scale-adaptor(測量模型)→ r-spss-syntax-architect(結構模型)。
紅線
- 樣本數先驗算,絕不「收到多少算多少」再事後合理化。
- CMV 單靠 Harman 單因子=審稿人眼中的敷衍;程序性預防才是本體,統計檢驗是佐證。
- 淘汰標準先於資料;看了結果再淘汰=p-hacking 近親。
- 個資與倫理:問卷不蒐集非必要個資;需 IRB 時提醒,不代做合規判斷。
- 本 skill 不執行實際發放(平台操作是使用者的事),只給計畫與檢核。
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 · 64 lines · 449 tokens per session scan A d30fd36e5694
survey-research-architect is a skill published in the GitHub repository Nero1688/claude-academic-skills (6 stars, last pushed 9d ago), licensed MIT. It adds 449 tokens to every session and 1,790 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-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)…