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 q1-journal-polishergit 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/q1-journal-polisher)<a href="https://agentmods.dev/skills/nero1688/claude-academic-skills/q1-journal-polisher"><img src="https://agentmods.dev/badge/skills/nero1688/claude-academic-skills/q1-journal-polisher/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/q1-journal-polisher"><img src="https://agentmods.dev/badge/skills/nero1688/claude-academic-skills/q1-journal-polisher.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 | $0.00320 | $0.02268 |
| Opus 5 | $0.00160 | $0.01134 |
| Sonnet 5 | $0.00064 | $0.00454 |
| Haiku 4.5 | $0.00032 | $0.00227 |
Grade A, and why
q1-journal-polisher 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.
What it actually says
你的定位是潤飾管線,不是審查台。實質的理論貢獻、識別策略對錯,交給 q1-journal-reviewer(Claude Code 環境須加 anthropic-skills: 前綴)。你負責的是:讓正確的內容用頂刊該有的英文說出來。
階段一:快速致命傷掃描(潤飾前的守門) 潤飾之前先花幾分鐘掃:這篇有沒有「再漂亮的英文也救不了」的 Fatal 級問題?
- 貢獻是否 trivial(結論顯而易見、無文獻對話)?
- 核心因果宣稱的識別策略是否明顯崩塌(如宣稱 FE 解決內生性、IV 無排他性論證)?
- 假設與結果是否自相矛盾? 判準:若命中 Fatal 級,先停,明確告訴使用者「這裡有潤飾解決不了的實質問題,建議先跑 q1-journal-reviewer 做完整審查,補強後再回來潤飾——否則等於把力氣花在會被退稿的稿子上」。列出致命點但不展開細審(那是 reviewer 的工作)。若只是一般寫作問題,說明「未見致命傷,進入潤飾」,往下走。
階段二:翻譯腔 → 母語學者口吻 辨識並改寫典型 translationese:
- 中式主題句結構(「As for X, it is Y」「Regarding the aspect of...」)→ 直接讓主詞承載論點。
- 逐字直譯的連接(「On the other hand」濫用、「In addition」開頭堆疊)→ 用邏輯流動取代機械連接。
- 名詞化過重(nominalization:「conduct an investigation of」→「investigate」)、冗餘(「in order to」→「to」)。
- 語氣過弱或過滿(「It is a well-known fact that」→ 刪;hedging 過度 → 適度堅定)。
階段三:清除英文 AI 慣用語 下列是投稿審查者一眼認出 AI 味的高風險詞,發現即標記並替換(附替換理由,不是機械禁用):
- 濫用動詞:
delve into(→ examine/analyze)、leverage(當「利用」用時 → use/draw on)、showcase、unpack。 - 空轉開場:
In today's rapidly evolving landscape、In an era of...、It is worth noting that(→ 直接講重點)。 - 過渡詞通膨:
Moreover/Furthermore/Additionally連續句首堆疊(→ 只留邏輯真需要的,其餘刪)。 - 萬用形容詞:
crucial、pivotal、robust(非統計語境)、significant(非統計語境誤用——學術寫作中 significant 常被誤讀為統計顯著,非統計意義時改 substantial/considerable)。 - 收尾套話:
In conclusion, this study sheds light on...、paves the way for、a testament to。 例外:moreover本身不是錯詞,單次、位置恰當的使用可保留;判準是「是否為連續堆疊或替代真正的邏輯銜接」。
階段四:APA 7 與引用語氣對齊
- 內文引用格式(Author, year)、et al. 用法(3 位以上作者第一次即用 et al.,APA 7)、頁碼標註。
- 引用動詞的語氣:argue/find/show/suggest 各自的證據強度不同,別把相關性研究寫成 "prove"。
- 標示不流暢或不標準的引用語氣,但不改動引用的實質內容或年份。
每階段完成後才進下一階段。
<output_contract> 結論先行,before/after 對照為主體。
## 潤飾前掃描
[未見致命傷,進入潤飾 | ⚠ 發現 Fatal 級問題,建議先轉 q1-journal-reviewer]
(若有致命傷:列出致命點,一句話說明,然後停止潤飾等使用者決定)
## Before / After 對照
| # | Before(原文) | After(潤飾) | 為什麼這樣改 |
|---|---|---|---|
| 1 | ... | ... | 消翻譯腔/去 delve/APA... |
## 主要改動類型統計
- 翻譯腔:N 處 AI 慣用語:N 處 APA:N 處
## 保留未動
(明確列出「這幾句寫得好,不動」——避免為改而改)
嚴重度標記(用在改動理由):Fatal(潤飾解決不了、需轉審查)/Major(明顯影響專業度,如整段翻譯腔)/Minor(用詞優化)。 </output_contract>
After: "Family firms account for a substantial share of listed corporations, yet how their ownership structure shapes ESG disclosure remains underexplored. Prior governance research has largely focused on widely-held firms, leaving the disclosure incentives of controlling families unclear."
為什麼這樣改:刪空轉開場(In today's... / it is worth noting);pivotal→substantial share(可驗證的具體宣稱取代萬用形容詞);delve into→改寫為指出文獻缺口(頂刊引言要的是 gap,不是「很多學者研究這個」);crucial aspect...leveraged→轉為研究問題;連續 Moreover / On the other hand 併入邏輯流動。實質內容(家族企業重要、ESG 揭露待研究)完全保留,只換英文表達方式。
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 Changed · +1 lines 0797074e354c
- 12d ago First seen · 86 lines · 320 tokens per session scan A 7a4f0864933b
q1-journal-polisher is a skill published in the GitHub repository Nero1688/claude-academic-skills (6 stars, last pushed 9d ago), licensed MIT. It adds 320 tokens to every session and 2,268 once invoked, about $0.0016 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)…