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 spatial-data-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/spatial-data-architect)<a href="https://agentmods.dev/skills/nero1688/claude-academic-skills/spatial-data-architect"><img src="https://agentmods.dev/badge/skills/nero1688/claude-academic-skills/spatial-data-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/spatial-data-architect"><img src="https://agentmods.dev/badge/skills/nero1688/claude-academic-skills/spatial-data-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 | $0.00691 | $0.02783 |
| Opus 5 | $0.00345 | $0.01392 |
| Sonnet 5 | $0.00138 | $0.00557 |
| Haiku 4.5 | $0.00069 | $0.00278 |
Grade A, and why
spatial-data-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 7d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
空間與地理資料分析架構師(Spatial Data Architect)
核心定位:家族缺的「空間那條線」
家族原本能處理面板、文字、多源,但沒有一支管「帶地理位置的資料」。本 skill 補上, 服務三類場景:
- 全台不動產 / hedonic 房價研究:實價登錄成交點 → 網格/行政區聚合 → 空間迴歸資料。
- 區域研究:公司總部地理定位、產業群聚、區域經濟變數的空間結構。
- 不動產事業應用:成交密度熱區圖、區域價格地圖——說服力強且可放簡報。
Step 1|座標系統(第一道、也最常被忽略的關卡)
台灣空間資料的頭號陷阱:
- WGS84(EPSG:4326):經緯度(度),Google Maps、GPS、多數 API 用。緯度 ~22-26、經度 ~120-122。
- TWD97 / TM2(EPSG:3826):投影座標(公尺),台灣官方圖資、部分政府資料用。數值是六、七位數的公尺。
- 鐵律:兩者不可混用;把 TWD97 的公尺數當經緯度餵進 H3/地圖,結果會完全錯位卻不報錯。
轉換用 pyproj(
Transformer.from_crs("EPSG:3826","EPSG:4326")),細節與台灣行政區代碼見references/taiwan-spatial-notes.md。本 skill 的聚合腳本內建 WGS84 範圍檢查,抓到投影座標會擋下。
Step 2|地理編碼 + 驗證退路(防 AI 幻覺座標)
地址→座標時,LLM 或線上地理編碼服務都會犯錯(同名地點、模糊地址、直接編一個)。
紀律(與 text-analytics 的 LLM 標註信效度同源,讀 references/geocoding-validation.md):
- 白名單/行政區約束:地址已知在某縣市,回傳座標必須落在該縣市界內,否則標記人工複核。
- 中心點/合理範圍檢查:座標落在台灣範圍外、或距該行政區中心過遠 → 離群,不自動採用。
- 抽樣人工核對:隨機抽 N 筆把座標貼回地圖看對不對,報一致率——這是資料品質的直接證據。
- 保留原始地址與來源:每個座標記
_geocoder與_asof(呼應 multi-source-data-integrator 的譜系)。 - 語言紀律:LLM 地理編碼是「輔助工具+人工驗證」,論文不寫「AI 定位了 X」。
Step 3|H3 六角網格聚合(比行政區更適合密度比較)
為什麼不直接用行政區:行政區面積差幾十倍,密度比較會被面積扭曲;H3 六角格面積相等、 鄰居距離一致、解析度可調,且個別地址被歸併到網格=天然去識別(隱私紅線)。
# 已實測腳本:點資料 → H3 網格聚合(含 WGS84 防線與筆數對帳)
python scripts/spatial_aggregate.py deals.csv --lat 緯度 --lng 經度 --value 成交價 --agg median --res 8
python scripts/spatial_aggregate.py # 無參數=跑內建自我測試
解析度選擇(台灣不動產):res 7≈邊長 1.2km(區域)、res 8≈0.5km(里級)、res 9≈0.2km(街廓)。
配方與 res 對照見 references/h3-aggregation-recipe.md。
隱私紅線:網格內筆數過小(如 n<3)可反推個別交易,畫圖與釋出前要遮罩或併格。
Step 4|空間計量意識(不越權,交棒 r-spss)
空間資料違反「觀測獨立」假設——鄰近的價格會互相影響。本 skill 負責診斷與資料準備, 估計交棒 r-spss-syntax-architect:
- 空間自相關:Moran's I 檢定殘差是否有空間結構(有=普通 OLS 標準誤失效)。
- 空間權重矩陣 W:鄰接(共邊)/距離帶/k 最近鄰;W 的選擇要理論化並做穩健性。
- 模型選擇:空間落後(SAR,外溢透過 Y)vs 空間誤差(SEM,外溢透過遺漏變數); 用 LM 檢定選型。hedonic 房價幾乎必然有空間自相關,純 OLS 會被審稿人打。
- 產出空間權重與診斷 → 交 r-spss(R 的 spdep/spatialreg)跑估計。
What ships with it
7 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.
- 7d ago First seen · 94 lines · 691 tokens per session scan A 3a321ace3276
spatial-data-architect is a skill published in the GitHub repository Nero1688/claude-academic-skills (6 stars, last pushed 9d ago), licensed MIT. It adds 691 tokens to every session and 2,783 once invoked, about $0.0035 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 2026-09-05.
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)…