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 experiment-design-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/experiment-design-architect)<a href="https://agentmods.dev/skills/nero1688/claude-academic-skills/experiment-design-architect"><img src="https://agentmods.dev/badge/skills/nero1688/claude-academic-skills/experiment-design-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/experiment-design-architect"><img src="https://agentmods.dev/badge/skills/nero1688/claude-academic-skills/experiment-design-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 | $0.00476 | $0.02073 |
| Opus 5.5 | $0.00190 | $0.00829 |
| Sonnet 5.5 | $0.00095 | $0.00415 |
| Haiku 4.5 | $0.00048 | $0.00207 |
Grade A, and why
experiment-design-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 1mo 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
實驗設計架構師(Experiment Design Architect)
Step 1|因果假說的可操弄性檢查
- X 必須可操弄:「家族企業 vs 非家族」不可隨機分派——那是準實驗或檔案研究的事, 誠實轉回 research-method-selector。可操弄的是知覺與情境:資訊揭露方式、 領導語氣、誘因框架。
- 倫理可行性:操弄不得造成實質傷害或重大欺瞞;需要欺瞞時必須有 debriefing 計畫。
Step 2|設計選型(核心決策樹)
| 決策 | 選項與判準 |
|---|---|
| 受試者間(between) | 每人只見一種處理:無沾染、需較大 N;操弄易被識破時的預設 |
| 受試者內(within) | 每人歷經多處理:N 效率高、統計力強;但有順序/練習/沾染效應,必須對抗平衡 |
| 混合(mixed) | 一因子間+一因子內;調節假說常用 |
對抗平衡(counterbalancing)技術(受試者內設計的生命線):
- 2 條件:AB/BA 兩序隨機半分。
- 3+ 條件:拉丁方陣(k 條件 k 序列,每條件在每位置恰一次);條件更多或 怕殘留效應用平衡拉丁方陣(每條件緊跟其他條件恰一次)。
- 三種方法(完全對抗平衡/標準拉丁方陣/Williams平衡拉丁方陣)各控制哪種順序效果、
何時該選哪個,見
references/counterbalancing.md;產生方陣與受試者分派表用python scripts/latin_square.py --conditions 4 --subjects 24 --seed 42(CSV 輸出,含標準與 Williams 兩種方陣)。 - 順序當因子丟進分析驗證無順序主效果,結果報告要交代。
因子設計:2×2 起跳講交互作用;cell 數 × 每 cell 最低 30–50 人估算總 N; 超過 2×3 要自問每個 cell 的理論必要性(cell 越多,樣本與解釋負擔平方成長)。
Step 3|情境實驗(vignette,商管主流)
遵循 Aguinis & Bradley (2014) 準則(可直接用 templates/vignette-template.md 起草,
含情境骨架/操弄變項填空/操弄檢核題/擬真度題四段結構):
- 情境撰寫:操弄變數間只改關鍵句,其餘逐字相同;長度 150–300 字; 用受試者熟悉的產業語境(擬真度 realism)。
- 擬真度檢核:前測問「此情境在真實職場發生的可能性」(7 點量表,均值 ≥5)。
- 紙上人物風險:提醒外推限制,討論節要寫;可用「決策後果真實化」 (抽獎金額隨決策變動)提升 consequentiality。
- 每情境版本 → 隨機分派 → 操弄檢核 → 依變數測量 → 人口統計(順序固定)。
Step 4|前測、操弄檢核、檢定力
- 前測(pilot):小樣本(每 cell 15–20)先驗:操弄檢核通過率、情境擬真度、
完成時間。前測失敗就改材料,不硬上。計畫與判準先訂,套用
templates/pretest-plan.md(含通過門檻表與前測結果紀錄表)。 - 操弄檢核:直接測受試者對操弄變數的知覺(操弄「高低揭露透明度」就測 知覺透明度),正式分析報 t/F 值;檢核不過的受試者處置規則先訂 (剔除 vs 保留敏感度分析並陳)。
- 先驗檢定力:效果量引前研究或 meta(管理實驗 d≈0.3–0.5 常見), α=.05、power=.80;G*Power 參數寫進設計書,審稿人要看。
- 預先註冊:假說、設計、N、淘汰規則、分析計畫上 AsPredicted/OSF (接 phd-researcher 的 preregistration 模板)——頂刊實驗研究的新常態。
Step 5|執行與交棒
- 隨機化用真隨機(平台內建或亂數表),記錄種子;分派後檢查各組人口變數平衡。
- 資料品質:沿用 survey-research-architect 的注意力檢查與時間防線。
- 交棒:設計矩陣+資料 → r-spss-syntax-architect(ANOVA/混合模型+簡單效果) → management-figure(交互作用圖)→ 投稿前雙檢。
What ships with it
4 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.
- 1mo ago Changed · +6 lines ea3f73f8700e
- 1mo ago First seen · 73 lines · 476 tokens per session scan A b2071d0bb790
experiment-design-architect is a skill published in the GitHub repository Nero1688/claude-academic-skills (13 stars, last pushed 5d ago), licensed MIT. It adds 476 tokens to every session and 2,073 once invoked, about $0.0019 per session on Opus 5.5. 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-qiime2-amplicon
Runs 16S/ITS amplicon (microbiome) analysis with the QIIME 2 distribution (2026.7; the "amplicon" distribution was renamed "qiime2" in 2026.4) in the correct order: manifest import, cutadapt trim-paired primer removal BEFORE dada2 denoise-paired (trunc-len chosen from the demux quality .qzv), feature-classifier…
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-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-esm
Run ESM protein language models — ESMC for embeddings and representations, ESMFold2 for structure prediction, and ESM3 for generative multimodal protein design across sequence, structure, and function — locally or through the hosted Biohub Platform API (formerly Forge). Use when working with protein sequences…