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 voidful/academic-skills --skill experiment-designgit clone --depth 1 https://github.com/voidful/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/voidful/academic-skills/experiment-design)<a href="https://agentmods.dev/skills/voidful/academic-skills/experiment-design"><img src="https://agentmods.dev/badge/skills/voidful/academic-skills/experiment-design.svg" alt="Measured on agentmods" 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 | $0.00131 | $0.03097 |
| Opus 5 | $0.00066 | $0.01548 |
| Sonnet 5 | $0.00026 | $0.00619 |
| Haiku 4.5 | $0.00013 | $0.00310 |
Grade A, and why
experiment-design 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 8d 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 — 337 lines — stays where its author put it; the contents beside it link to each section on GitHub.
實驗設計技能
概述
本技能提供一套結構化的實驗設計流程，適用於機器學習、自然語言處理、電腦視覺等領域的學術研究。目標是協助研究者從模糊的研究想法出發，產出一份嚴謹、可重現、且具說服力的實驗計畫。
核心設計理念
好的實驗設計應具備以下特質：
- 可證偽性：實驗結果必須能夠支持或否定研究假設
- 公平性：所有比較對象在相同條件下評估
- 可重現性：他人能夠依據描述完整重現實驗
- 充分性：實驗覆蓋足夠的面向以支撐論文結論
實驗設計 Pipeline
完整的實驗設計遵循以下六步流程：
假設 → 變數 → 指標 → Baseline → Ablation → 計算預算
每一步的產出都是下一步的輸入，形成嚴謹的推導鏈。
步驟一：研究假設明確化
目的
將模糊的研究動機轉化為可驗證的具體假設。
方法
- 辨識研究問題：你想回答什麼問題？
- 提出核心假設：對問題的預期答案是什麼？
- 明確化假設：假設必須具備可測量性與可證偽性
- 分解子假設：將複雜假設拆解為可逐一驗證的子假設
假設的品質標準
| 標準 | 說明 |
|---|---|
| 具體性 | 明確指出預期的效果方向與幅度 |
| 可測量性 | 可以用量化指標來驗證 |
| 可證偽性 | 存在可能否定假設的實驗結果 |
| 相關性 | 與研究問題直接相關 |
範例
- 不佳：「我們的方法比較好」
- 良好：「在 SQuAD 2.0 資料集上，加入跨注意力機制後，F1 分數相較於純自注意力基線提升至少 2 個百分點」
詳見：實驗規劃參考
步驟二：變數定義
自變數（Independent Variables）
研究者主動操控的變數，即實驗中「改變的東西」。
- 模型架構的變體
- 訓練策略的差異
- 資料處理方式的不同
依變數（Dependent Variables）
用來衡量實驗結果的變數，即「被測量的東西」。
- 模型效能指標（準確率、F1、BLEU 等）
- 效率指標（推論時間、記憶體用量）
- 品質指標（人工評估分數）
控制變數（Control Variables）
實驗中保持不變的變數，確保比較的公平性。
- 隨機種子
- 訓練資料集與切分方式
- 超參數（非研究對象的部分）
- 硬體環境
- 預訓練模型版本
變數控制原則
- 單一變數原則：每次實驗僅改變一個自變數
- 完整記錄原則：所有變數的值都必須記錄
- 合理範圍原則：自變數的取值範圍應有理論依據
詳見：實驗規劃參考
步驟三：評估指標選擇
選擇原則
- 領域慣例：優先選擇該領域公認的標準指標
- 多面向覆蓋：同時報告效能、效率、穩健性指標
- 統計顯著性：報告多次實驗的平均值與標準差
- 合理性：指標能真正反映研究假設所關注的面向
常見指標類別
| 類別 | 指標範例 |
|---|---|
| 分類任務 | Accuracy、Precision、Recall、F1-score、AUC-ROC |
| 生成任務 | BLEU、ROUGE、METEOR、BERTScore、人工評估 |
| 資訊擷取 | MAP、MRR、NDCG、Recall@K |
| 效率指標 | FLOPs、參數量、推論延遲、記憶體佔用 |
| 穩健性 | 跨資料集表現、對抗樣本準確率 |
統計檢驗
- 報告多次隨機種子實驗的平均值與標準差
- 必要時進行統計顯著性檢驗（如 paired t-test、bootstrap test）
- 標註統計顯著性水準（p < 0.05, p < 0.01）
步驟四：Baseline 選擇與設定
必選 Baseline 類型
- 經典方法：該領域歷史上重要的方法
- 當前 SOTA：最新的最佳表現方法
- 簡單 Baseline：簡單但合理的基準方法（如隨機、多數類別、TF-IDF）
公平比較原則
- 使用相同的資料切分
- 使用相同的評估協定
- 盡可能使用原作者的程式碼與超參數
- 若需重新實現，需驗證重現結果與原論文一致
常見錯誤
- 僅與弱基線比較
- 未使用最新 SOTA 作為基線
- 基線的超參數未經調校
- 比較條件不一致（如不同的預訓練模型）
What ships with it
5 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.
- 8d ago First seen · 337 lines · 131 tokens per session scan A c4fcf8e34987
experiment-design is a skill published in the GitHub repository voidful/academic-skills (126 stars, last pushed 5mo ago), licensed MIT. It adds 131 tokens to every session and 3,097 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
phylogenetics
Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…