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 text-analytics-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/text-analytics-architect)<a href="https://agentmods.dev/skills/nero1688/claude-academic-skills/text-analytics-architect"><img src="https://agentmods.dev/badge/skills/nero1688/claude-academic-skills/text-analytics-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/text-analytics-architect"><img src="https://agentmods.dev/badge/skills/nero1688/claude-academic-skills/text-analytics-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 | $0.00484 | $0.02062 |
| Opus 5 | $0.00242 | $0.01031 |
| Sonnet 5 | $0.00097 | $0.00412 |
| Haiku 4.5 | $0.00048 | $0.00206 |
Grade A, and why
text-analytics-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 11d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
文字資料研究架構師(Text Analytics Architect)
Step 0|複雜文件前處理(語料若來自 10-K/年報/永續報告,先做這步)
若語料是版面複雜的揭露文件(10-K、年報、ESG 永續報告、掃描檔),pdftotext 直抽會把
表格壓平、多欄交錯、頁尾混進正文——髒進髒出。先讀 references/document-preprocessing.md:
用版面感知抽取(內建 pdf skill 輕量首選;複雜表格升級到 MinerU 類工具)轉成保留語意結構
的乾淨文字,並驗抽取品質、保 source map、遮罩 PII,再進 Step 1。乾淨學術 PDF 或純逐字稿
可跳過本步。
Step 1|語料與構念(效度先行)
- 構念是什麼、文字為什麼是它的合理載體?(管理階層樂觀→MD&A 語調:有文獻 傳統 ✓;企業文化→官網文案:載體效度要自己論證)
- 語料邊界:期間、來源、語言、誰寫的(代筆/公關稿問題)、選擇偏誤 (只有大公司開法說會=樣本截斷)。
- 版權與條款:爬蟲前查 robots.txt 與平台 ToS;財報屬公開資訊,評論平台多有 限制——法遵先於方法。個資(用戶名、可識別內容)在語料階段就去識別。
Step 2|方法階梯(由可解釋到黑箱,能低不高)
| 階 | 方法 | 適用 | 頂刊接受度 |
|---|---|---|---|
| 1 | 字典法(LM 財金詞典、中文情緒詞典) | 構念有成熟詞典(語調、不確定性) | 高(可解釋、可重現) |
| 2 | 主題模型(LDA/STM;短文本用 BERTopic) | 探索語料結構、建主題份額變數 | 高(需人工命名+效度檢) |
| 3 | 監督式分類(嵌入+分類器) | 有標註資料、構念複雜 | 中高(報 out-of-sample 表現) |
| 4 | LLM 標註 | 構念需理解語境、標註量大 | 上升中,紀律見 Step 3 |
原則:低階能解決就不上高階;高階結果用低階方法三角驗證(BERTopic 主題與 關鍵詞頻是否一致)。STM 可帶共變數(主題隨公司特徵變化),管理研究常用。
Step 3|LLM 標註的信效度紀律(2026 審稿新戰場)
- 人工基準先行:隨機抽 200–300 則,兩位人工編碼(規則同 qualitative-thematic-coder 的編碼簿紀律),Cohen's κ ≥ .70 才有資格當基準。
- LLM 對齊基準:LLM 標註與人工黃金標準的一致性(κ/F1)達標才可放大; 報告混淆矩陣,錯的類型要看(系統性偏誤 vs 隨機)。
- 凍結與記錄:prompt 全文、模型名與版本、溫度、日期寫進附錄;研究期間 不換模型不改 prompt(改了=重新驗證)。
- 偏誤稽核:對敏感維度(公司規模、產業)分組檢查標註分布,防 LLM 的 系統性傾向汙染變數。
- 語言紀律:LLM 是「標註工具」,論文寫 machine-assisted annotation with human validation,不寫「AI 判斷了 X」。
Step 4|中文特化
- 斷詞:繁中首選 CKIP(學術標準),jieba 加自訂詞典(公司名、財經術語)備援。
- 繁簡:語料混雜時先統一(OpenCC),詞典的繁簡版本要對齊。
- 停用詞與否定詞:中文否定(「不」「未」「非」)緊鄰情緒詞會翻轉極性, 字典法必須處理 negation window。
- 中文情緒/語調詞典:優先用有文獻出處的(如 NTUSD 及財金領域中文詞典), 自建詞典要報建構程序與人工校驗。
Step 5|文字變數出廠檢查(進迴歸前)
- 敘述統計+分布(文字變數常右偏,考慮轉換)。
- 效度三角:與已知相關的結構化變數方向一致嗎?(語調悲觀 vs 當期虧損)
- 極端值人工抽讀 10 則:分數極端的文本讀起來真的是那樣嗎?
- 交棒:變數進 r-spss-syntax-architect(一般建模)或 causal-inference-architect (文字變數當結果/處理的識別設計);出圖 management-figure。
紅線
- LLM 標註未經人工基準驗證,不得直接當研究變數——這是資料造假的灰色地帶。
- 爬蟲守法遵、語料去個資;平台禁爬就換來源,不硬爬。
- 主題模型的主題必須人工閱讀命名+代表文本抽驗,不能只看 top words 就編故事。
- 所有 pipeline(斷詞→清理→模型→變數)腳本化可重現;「跑一次的結果」不進論文。
What ships with it
2 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.
- 11d ago First seen · 78 lines · 484 tokens per session scan A 65c3616b8fb8
text-analytics-architect is a skill published in the GitHub repository Nero1688/claude-academic-skills (6 stars, last pushed 8d ago), licensed MIT. It adds 484 tokens to every session and 2,062 once invoked, about $0.0024 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)…