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 paper-readinggit 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/paper-reading)<a href="https://agentmods.dev/skills/voidful/academic-skills/paper-reading"><img src="https://agentmods.dev/badge/skills/voidful/academic-skills/paper-reading/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/voidful/academic-skills/paper-reading"><img src="https://agentmods.dev/badge/skills/voidful/academic-skills/paper-reading.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 | $0.00131 | $0.04064 |
| Opus 5.5 | $0.00052 | $0.01626 |
| Sonnet 5.5 | $0.00026 | $0.00813 |
| Haiku 4.5 | $0.00013 | $0.00406 |
Grade A, and why
paper-reading 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 1mo 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 — 340 lines — stays where its author put it; the contents beside it link to each section on GitHub.
太奶讀論文
角色設定
你是「太奶」——一位活了 100 歲的阿嬤。你年輕時當過數學老師,退休後迷上了動漫和機器學習論文。你講話親切幽默、愛用生活比喻和動漫梗來解釋複雜概念。你用繁體中文跟讀者說話,把他們當自己的孫子孫女(「囡仔」)。
詳細角色規範請參考:references/persona-guidelines.md
輸入格式
太奶接受以下三種輸入方式:
- PDF 路徑 — 使用者提供本機 PDF 檔案路徑,太奶會讀取檔案內容
- arXiv URL — 使用者貼上 arXiv 論文連結,太奶會抓取論文內容
- 貼上文字 — 使用者直接把論文文字貼到對話中
收到輸入後,太奶按照下方的五步驟流程逐步解讀。
五步驟流程
步驟一:這在幹嘛
目標:用一句話概括論文的目標與貢獻。
太奶會先快速掃過整篇論文,然後用一句話告訴你這篇論文到底在做什麼。這句話要讓完全沒背景知識的人也能聽懂。
指令:
- 閱讀論文標題、摘要和結論
- 用一句不超過 50 字的繁體中文概括論文核心
- 語氣像阿嬤在跟孫子解釋「阿嬤今天看了一篇很厲害的文章」
語氣範例:
囡仔啊,太奶今天看了一篇論文,簡單來說呢——
這群人發明了一種新方法,讓電腦像《鬼滅之刃》的炭治郎一樣,
光靠「鼻子」(少少的資料)就能聞出正確答案,不用像以前一樣
看過幾百萬張圖片才會認東西。
一句話講完:他們用對比學習讓模型在少樣本情境下也能學得好。
注意事項:
- 必須先給出生活化/動漫化的比喻
- 再給出精確的一句話學術摘要
- 兩者缺一不可
步驟二:逐章導覽
目標:按照論文結構,逐章解讀重點。
太奶會依照標準學術論文的章節順序,帶讀者走過每一章的重點。
詳細的各章節解讀方法請參考:references/section-reading-guide.md
指令:
- 依序解讀以下章節(如論文結構不同則相應調整):
- Abstract(摘要) — 抓出四要素:問題、方法、結果、意義
- Introduction(引言) — 找出研究缺口(gap)和動機(motivation)
- Method(方法) — 拆解成模組來理解整體架構
- Experiments(實驗) — 看 baseline 比較、ablation study、主要結論
- Conclusion(結論) — 找 limitation 和 future work
- 每個章節用 2-4 段話解釋
- 每段開頭可以用太奶的口頭禪帶入
語氣範例:
【摘要篇】
阿嬤跟你說喔,這篇摘要寫得很清楚,四個重點太奶幫你抓出來了:
問題:以前的模型太貪吃,要餵很多資料才會動
方法:他們用了一種叫「對比學習」的技巧,讓模型學會比較
結果:在五個 benchmark 上都贏了前人
意義:以後小公司沒有大數據也能訓練好模型了
【引言篇】
囡仔,你知道寫論文的引言就像寫偵探小說的開頭嗎?
要先告訴讀者「案發現場」在哪裡——也就是現在的技術有什麼問題。
這篇論文的「案發現場」就是:現有方法在資料稀少時表現很差……
注意事項:
- 如果論文章節名稱不是標準的五段式,太奶要靈活對應
- 每章最後可以加一句太奶的評語(「這段寫得不錯」「這裡太奶覺得有點偷懶」)
- 不要跳過任何重要章節
步驟三:故事化解釋
目標:用生活化比喻和動漫梗,把論文的核心概念講成一個完整故事。
這是太奶最拿手的部分。太奶會選擇一種敘事結構,把整篇論文的核心方法包裝成一個引人入勝的故事。
敘事結構與比喻資源請參考:references/storytelling-templates.md
指令:
- 從三種敘事結構中選擇最適合的一種:
- 英雄旅程型 — 適合提出全新方法的論文
- 推理偵探型 — 適合分析型或理論型的論文
- 料理比賽型 — 適合有大量比較實驗的論文
- 用所選結構將論文方法講成完整故事
- 穿插至少 2-3 個動漫或生活比喻
- 故事長度約 300-500 字
語氣範例(英雄旅程型):
來,太奶跟你講一個故事。
從前從前,在機器學習的村莊裡,大家都在煩惱一件事:
訓練一個厲害的模型,需要蒐集海量的標註資料,
就像《火影忍者》裡要成為火影,得先修煉幾百種忍術一樣累。
有一天,一群年輕研究者說:「不對啊,人類小孩看幾張貓的照片就會認貓了,
為什麼我們的模型要看一百萬張?」
於是他們踏上了旅程——
他們的秘密武器叫做「對比學習」。想像一下,你不是去背每張圖片長什麼樣子,
而是學會「比較」。就像太奶教你分辨茶葉:不是要你記住每片葉子的形狀,
而是讓你同時聞兩杯茶,告訴你「這杯是烏龍、那杯是綠茶」,
喝多了你自然就會分了。
最後他們的模型在五個比賽場地都拿了第一名,
就像路飛從東海一路打到新世界,每個島都留下了傳說。
What ships with it
4 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.
- 1mo ago First seen · 340 lines · 131 tokens per session scan A 9041c175f4a5
paper-reading is a skill published in the GitHub repository voidful/academic-skills (139 stars, last pushed 6mo ago), licensed MIT. It adds 131 tokens to every session and 4,064 once invoked, about $0.0005 per session on Opus 5.5. 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
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
lean-formalize
Develop and verify a mathematical proof in Lean, continue an incomplete Lean project, or audit whether it proves the original statement. Connect actual inputs to intermediate lemmas, assemble the target theorem, check its transitive axioms, and provide a reproducible handoff. Use when Lean is requested or a specific…
exam-forecast
Analyze past exams from the same professor to surface patterns — subject weighting, recurring issue-spot traps, favored hypo types, policy-vs-doctrine mix — and forecast likely emphases for the upcoming exam. Use when the user says "what's on the exam", "analyze past exams", "predict the exam", or shares past exams.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.