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 r-spss-syntax-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/r-spss-syntax-architect)<a href="https://agentmods.dev/skills/nero1688/claude-academic-skills/r-spss-syntax-architect"><img src="https://agentmods.dev/badge/skills/nero1688/claude-academic-skills/r-spss-syntax-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/r-spss-syntax-architect"><img src="https://agentmods.dev/badge/skills/nero1688/claude-academic-skills/r-spss-syntax-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00406 | $0.04613 |
| Opus 5 | $0.00203 | $0.02306 |
| Sonnet 5 | $0.00081 | $0.00923 |
| Haiku 4.5 | $0.00041 | $0.00461 |
Grade A, and why
r-spss-syntax-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 6d 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
R / SPSS 語法建構師(Syntax Architect)
核心紀律:先診斷、後動筆。 沒有前置資料檢查的迴歸語法是危險的——L-002(0.98 共線性的假平方項晚期才爆)與 L-003(t 值貼錯)都源於跳過檢查。每段建模語法之前,一定先有資料體檢;每段語法之後,一定有「輸出要對到哪張表的哪一格」的對帳指引。
Step 0|先問一題:R 還是 SPSS?(除非使用者已指定)
兩者能力不同,先確認再寫,不要兩套都寫浪費篇幅:
- R(建議 panel 用):
plm(FE/RE/Hausman)、lmtest+sandwich(穩健/叢集標準誤)、lavaan(中介/SEM)、interactions或emmeans(簡單斜率)。面板固定效果、叢集穩健標準誤、bootstrap 中介都最順。 - SPSS:選單研究者熟悉,但原生無公司-年雙向固定效果;FE 要用 LSDV(納入公司虛擬變數)或
MIXED,且叢集穩健 SE 支援有限。若使用者堅持 SPSS 做 panel FE,誠實說明侷限並給 LSDV/MIXED 替代語法,同時建議穩健性以 R 覆核。 - 若使用者只是要跑調節、二次項、中介的橫斷面 OLS,SPSS 的
PROCESSmacro(Hayes)足夠,可直接給 model 號。
一句話定位:R 是主力(面板/叢集/bootstrap),SPSS 走 PROCESS 或 LSDV 路線,並揭露其面板侷限。
Step 1|把假說翻成模型設定(先寫給人看,再寫給機器)
逐條列出,讓使用者確認後才寫語法:
- 依變數 Y、自變數 X、調節 M、中介 Me、控制變數集合,各自的測量與尺度。
- 假說形態決定模型:
- 主效果 → 線性項。
- 調節(H:M 強化/削弱 X→Y)→ X、M 主效果 + X×M 交乘項,連續調節變數先中心化(減均值)以降低交乘項共線性並讓主效果可解釋。
- 曲線(H:倒U / U)→ X 與 X² 同時入模,X 先中心化;倒U 需 β₂<0 且 β₁>0,轉折點 x* = -β₁/(2β₂),且 x* 要落在資料範圍內、以 Lind & Mehlum (2010) U-test 佐證,否則不得宣稱倒U。
- 中介(H:X→Me→Y)→ 間接效果 a×b,以 bootstrap(≥5000 次) 的偏誤校正信賴區間判定,不用 Sobel/Baron-Kenny 逐步法作主證據。
- 面板結構:分析單位(公司-年/公司-季)、時間跨度、是否平衡;決定 FE vs RE(見 Step 3)。
- 一句話寫出估計方程式(含下標 i、t),使用者點頭再往下。
Step 2|前置資料檢查語法(每次都先跑,這是防 L-002/L-003 的紅旗關卡)
在任何迴歸前,語法要先產生並讓使用者看:
- 結構盤點:
dim/str(列數、欄數、型別)、每個變數的 N 與遺漏數。 - 遺漏值:逐變數遺漏比例;提醒面板遺漏是否非隨機(如小公司系統性缺 ESG 揭露 → 樣本選擇偏誤伏筆)。
- 極端值:連續變數的 min/max/分位數、|z|>3 或 IQR 法標記;只標記不刪除,縮尾與否交給 wrangler 或使用者決定並揭露。
- 相關矩陣(L-002 紅旗):輸出 Pearson 相關矩陣;任兩自變數 |r|>0.9 立即紅旗警告,明示這常是「同一構念重複放入」或「平方項未中心化」的病徵,要求先處理再建模。
- VIF:主模型跑完 VIF;>10 高度共線、>5 留意。二次項/交乘項因結構性相關 VIF 天生偏高,需搭配中心化判讀,不可一律砍。
Step 3|核心建模語法(依假說形態產出,逐行中文註解)
按 Step 1 選定的形態產出對應語法(見 examples)。面板固定效果的判準:
- Hausman 檢定:p<0.05 拒絕 RE、採 FE;p≥0.05 可用 RE(較有效率)。但實證慣例:只要擔心不隨時間變的公司異質性與自變數相關(治理研究幾乎都是),即使 Hausman 不顯著也常直接報 FE 為主、RE 為輔。
- 雙向固定效果:公司 FE + 年度 FE(吸收總體衝擊),治理/家族企業 panel 的標準做法。
- 叢集穩健標準誤:以公司為 cluster(
vcovHC/vcovCL),修正序列相關與異質變異;這是頂刊 panel 的底線,不用預設 SE。
What ships with it
3 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.
- 6d ago Changed 30e9fab1e77f
- 12d ago First seen · 156 lines · 406 tokens per session scan A e5a4523d1378
r-spss-syntax-architect is a skill published in the GitHub repository Nero1688/claude-academic-skills (6 stars, last pushed 9d ago), licensed MIT. It adds 406 tokens to every session and 4,613 once invoked, about $0.0020 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-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-deepchem
Runs molecular machine learning with DeepChem — diverse featurizers, pre-built MoleculeNet benchmark datasets, and pre-trained models (ChemBERTa, GROVER) for property prediction (ADMET, toxicity, solubility) via traditional ML or graph neural networks. Use when running end-to-end molecular ML experiments that need…
alterlab-hypogenic
Runs automated LLM-driven hypothesis generation and testing on tabular datasets with HypoGeniC, combining literature insights with data-driven testing. Use when systematically exploring hypotheses about patterns in empirical data (for example deception detection or content analysis). For manual hypothesis formulation…
alterlab-esm
Run ESM protein language models — ESM3 for generative multimodal protein design across sequence, structure, and function, and ESM C for efficient embeddings and representations — locally or via the cloud Forge API. Use when working with protein sequences, structures, or function prediction, designing novel proteins…
alterlab-molfeat
Featurizes molecules for machine learning with molfeat (100+ featurizers) — ECFP/MACCS/MAP4 fingerprints, RDKit and Mordred physicochemical descriptors, and pretrained embeddings (ChemBERTa, ChemGPT, GIN) exposed as scikit-learn transformers that convert SMILES into feature vectors. Use when turning molecules into…
alterlab-geniml
Machine learning on genomic interval data (BED files) with the geniml Python package — region embeddings (Region2Vec), joint region+metadata embeddings (BEDspace/StarSpace), single-cell ATAC-seq embeddings (scEmbed), consensus peak sets / universes (build-universe), tokenization, BEDshift randomization, and…