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 bilingual-paper-readergit 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/bilingual-paper-reader)<a href="https://agentmods.dev/skills/nero1688/claude-academic-skills/bilingual-paper-reader"><img src="https://agentmods.dev/badge/skills/nero1688/claude-academic-skills/bilingual-paper-reader/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/bilingual-paper-reader"><img src="https://agentmods.dev/badge/skills/nero1688/claude-academic-skills/bilingual-paper-reader.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 | $0.00389 | $0.01996 |
| Opus 5 | $0.00195 | $0.00998 |
| Sonnet 5 | $0.00078 | $0.00399 |
| Haiku 4.5 | $0.00039 | $0.00200 |
Grade A, and why
bilingual-paper-reader 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
雙欄論文閱讀器（Bilingual Paper Reader）
這個 skill 實際上是什麼（先講清楚，避免誤解）
- 閱讀器是一支、論文是資料檔。
reader.html可重複使用，任何論文轉成 JSON 都用它開。 - 翻譯與預先標記需要你（Claude）在場。 閱讀器本身是靜態 HTML，沒有 LLM， 無法自己翻譯。每篇論文要開一次 session 讓你翻。
- 標記存在瀏覽器 localStorage，清除瀏覽器資料會一併清掉—— 重要筆記務必用「匯出筆記」存成 Markdown 備份。這點要主動告訴使用者。
- 掃描版 PDF（無文字層）抽不到文字，需先 OCR。工具會明確報錯，不會產出空檔。
與同族 skill 分工
| 需求 | 該用 |
|---|---|
| 一批文獻的橫向比較（建庫、矩陣、APA7、DOI） | literature-matrix-builder |
| 規模化文字量化（財報語調、主題模型、LLM 標註） | text-analytics-architect |
| 單篇方法論逆向、找研究缺口、系統性回顧 | phd-researcher |
| 單篇論文的雙語精讀與重點標記 | 本 skill |
精讀完的判斷（核心主張／創新點／弱點）可回填進 literature-matrix-builder
的綜整欄——兩支是天然接力。Claude Code 環境呼叫同族技能須加 anthropic-skills: 前綴。
工作流程
Step 1｜PDF → 論文資料檔
python scripts/pdf_to_paper.py paper.pdf -o paper.json --title "論文標題"
會切段、濾掉頁首頁尾雜訊、標出疑似表格的段落（skip: likely_table）。
若報錯說抽不到文字，代表是掃描版 PDF，請使用者先 OCR。
Step 2｜先建術語對照表
翻譯前先掃一遍全文，把反覆出現的關鍵術語列進 JSON 的 glossary。
這一步不能跳過——術語不一致是學術翻譯最常見也最傷的錯誤。
規範見 references/translation-discipline.md。
Step 3｜逐段翻譯
填每段的 trans。紀律見 references/translation-discipline.md，重點：
- 一段對一段，不合併不拆分
- 人名／期刊名／統計符號／變數名不翻
- 數字、係數、p 值原樣照抄（數字零容忍）
- 因果強度用詞不可弱化或加強（
suggests≠ 證明） - 看不懂就標「原文語意不明確，暫譯為…」，不要硬翻出通順的錯譯
翻譯量要先講：全文常有 50–120 段。先問使用者要全翻還是先翻 摘要／引言貢獻段／方法／結論這四塊，不要默默決定。
Step 4｜五色預先標記
填每段的 marks。分類判準與位移算法見 references/highlight-taxonomy.md。
寧少勿濫——每段都標等於沒標。
Step 5｜交付與判斷
告訴使用者怎麼開，並附上你的判斷（比標記更有價值）：
## 這篇的關鍵判斷
- 核心主張：〔一句話〕
- 最創新之處：〔一句話；貢獻宣稱不明確就直說〕
- 最大弱點：〔區分作者自承 vs 你讀出來的〕
- 與你研究的關聯：〔一句話〕
輸出格式
# 精讀：〔論文標題〕
## 處理狀態
- 段落 N 段（其中 M 段為表格已略過）
- 已翻譯：〔全文／指定章節〕
- 預先標記：核心 a、創新 b、方法 c、限制 d、金句 e
## 這篇的關鍵判斷
〔如上四點〕
## 怎麼開
1. 用瀏覽器開啟 scripts/reader.html
2. 把 〔paper.json 路徑〕 拖進去
3. 選取文字可自己畫螢光筆；按「匯出筆記」存成 Markdown
## 提醒
- 標記存在瀏覽器 localStorage，清除瀏覽器資料會消失，重要筆記請匯出備份
- 〔翻譯中標為語意不明確的段落，請對照原文第 N 頁確認〕
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.
- 11d ago First seen · 110 lines · 389 tokens per session scan A f8b24671388c
bilingual-paper-reader is a skill published in the GitHub repository Nero1688/claude-academic-skills (6 stars, last pushed 9d ago), licensed MIT. It adds 389 tokens to every session and 1,996 once invoked, about $0.0019 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-open-notebook
Run Open Notebook, a self-hosted open-source alternative to Google NotebookLM with a full REST API, for AI-powered research and document analysis. Use when organizing research materials into notebooks, ingesting diverse content sources (PDFs, videos, audio, web pages, Office documents), generating AI-powered notes and…
alterlab-treatment-plans
Generates concise (3-4 page), focused medical treatment plans in LaTeX/PDF format across all clinical specialties — general medical treatment, rehabilitation therapy, mental health care, chronic disease management, perioperative care, and pain management — using SMART goal frameworks, evidence-based interventions with…
alterlab-pdf-explore
Explore a single PDF in depth — parse it once, then answer questions across its sections, figures, tables, and appendices — comparing methods across sections, extracting every instance of a pattern within the document, and reading values off its charts and tables. Use when interrogating one paper or report end-to-end…
alterlab-markitdown
Convert files and Office documents to clean, LLM-friendly Markdown with Microsoft MarkItDown (markitdown CLI/Python), supporting PDF, DOCX, PPTX, XLSX, images (EXIF + OCR), audio (transcription), HTML, CSV, JSON, XML, ZIP archives, EPUB e-books, and YouTube transcript URLs, with optional AI image descriptions. Use…
compile-latex
Compile a .tex with latexmk and report ranked errors with file:line attribution across \input'd files, plus a diff against the last compile. TRIGGER on "compile this", "build my paper", "build the beamer deck", "why won't this compile", "what are the latex errors", "did my edit add warnings", or any request to build…
acmmm-camera-ready
Use when preparing the ACM MM (ACM Multimedia) camera-ready version of record — de-anonymizing safely, completing the ACM rights form and CCS concepts, meeting ACM sigconf requirements, releasing code/data/media artifacts and any earned reproducibility badge, registering, and planning the oral/poster presentation in…