academic-journal-polisher

academic-journal-polisher is a skill for Claude Code, Codex from Nero1688/claude-academic-skills. It costs 295 tokens per session (3,381 once invoked), scanned A, original, MIT.

A Chinese-language editing and review workflow for Taiwanese business and management research papers. It focuses on topics such as family businesses, corporate governance, and ESG-related research.

In plain words
What is it for?
Reviewing and polishing Chinese academic manuscripts, checking terminology, improving sentence flow, and preparing text for Taiwanese journals or oral defenses.
Why use it?
It separates reviewer feedback from the polished text and removes formulaic AI phrasing while preserving the paper's meaning and technical terms.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Reviewing and polishing Chinese academic manuscripts, checking terminology, improving sentence flow, and preparing text for Taiwanese journals or oral defenses.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nero1688/claude-academic-skills/academic-journal-polisher
Install

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.

Any agent
npx skills add Nero1688/claude-academic-skills --skill academic-journal-polisher
Clone the repo
git clone --depth 1 https://github.com/Nero1688/claude-academic-skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for academic-journal-polisher

README.md
[![agentmods](https://agentmods.dev/badge/skills/nero1688/claude-academic-skills/academic-journal-polisher/github.svg)](https://agentmods.dev/skills/nero1688/claude-academic-skills/academic-journal-polisher)
Your own site
<a href="https://agentmods.dev/skills/nero1688/claude-academic-skills/academic-journal-polisher"><img src="https://agentmods.dev/badge/skills/nero1688/claude-academic-skills/academic-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.

agentmods 80×15 button for academic-journal-polisher

Your own site · 80×15
<a href="https://agentmods.dev/skills/nero1688/claude-academic-skills/academic-journal-polisher"><img src="https://agentmods.dev/badge/skills/nero1688/claude-academic-skills/academic-journal-polisher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 295 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,381 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00295 $0.03381
Opus 5.5 $0.00118 $0.01352
Sonnet 5.5 $0.00059 $0.00676
Haiku 4.5 $0.00030 $0.00338

Measured 5d ago against content hash 4fae09071ddb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

academic-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 5d 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.

skills/academic-journal-polisher/SKILL.md · 127 lines

What it actually says

引用鐵律(零虛構文獻):交付物裡的每一筆文獻都要真實存在、書目正確。不憑記憶寫文獻;交付前逐筆查證(DOI 指向同一篇、作者/年份/期刊對得上);中文文獻要人工核實並留下證據;沒通過的就刪掉,或明確標【待核實】,絕不拿資料庫裡「最像的那篇」充數。細則見 research-orchestrator 的 references/citation-integrity.md。

階段零:敘事架構檢查(先看骨架,再看句子) 潤飾前先確認全文的敘事弧撐不撐得住:緒論的 hook/研究問題/缺口/貢獻/ so-what 五元素能不能各自指出在第幾段、各節開頭是否承接上一節結論而非重啟 話題、結論是否回應緒論的承諾。必讀 references/narrative-architecture-check.md。 三層由巨到微依序是:敘事架構(本階段)→ 論證力度(階段四)→ 詞彙層(階段二)。 三層由巨到微依序是:敘事架構(本階段)→ 論證力度(進階層,本包未收錄)→ 詞彙層(階段二)。 若想量化句長、過渡詞密度等文體訊號輔助判斷,可另跑 q1-journal-polisher 的 scripts/prose_metrics.py --lang zh(純訊號,非判決, 兩支潤飾技能共用同一支腳本)。敘事弧本身的缺口(例如貢獻句只寫「填補實證 空白」而非理論貢獻)只標示、交由作者補——本 skill 不代作者決定理論框定。

階段一:批判性審查(先讀懂再改)

  • 論點是否因潤飾風險而偏移?先確認原意,再動文字。
  • 語氣是否符合台灣商管學術慣例(不過度口語、不過度華麗、結論有據)?
  • 台灣術語是否到位:控制股東、金字塔結構、盈餘分配權與控制權偏離、獨立董事、集團企業、TESG、公司治理評鑑——用詞不準要指出。

階段二:去 AI 腔(原則+why+例外,不機械禁用) 去 AI 腔的目的是讓文字讀起來像人寫的、有邏輯血肉,不是背一張禁用詞表。以下每條都附「為什麼」與「例外」:

  • 慎用萬用套話:「值得注意的是」「在當今數位時代」「綜上所述」「基於上述」「顯而易見」「不可否認」。 why:這些是填充詞,刪掉不影響語意,卻讓文字顯得空轉、像 AI 生成。 例外:正式綜述段落收尾用一次「綜上」承接是可接受的;問題在「濫用」與「每段都來一句」,不是這個詞本身有罪。判準是刪掉後語意有沒有損失——沒有就刪。

  • 分號(;)原則性避免,但不絕對禁止:中文學術寫作中,作者常把英文 semicolon 習慣直接搬過來,用分號硬連兩個本該分開或用轉折詞銜接的句子,讀起來生硬。 why:多數情況改用逗號+轉折詞、或直接斷句,會更符合中文語感。 例外(重要,避免誤傷):分號在「並列多個含逗號的子項」時是正確且必要的用法,例如「本研究控制了公司規模,以資產總額衡量;負債比率,以總負債除以總資產衡量;以及產業別,以 TEJ 產業代碼分類」——這種列舉不可改成逗號,否則層次混亂。表格註解、變數定義清單中的分號通常正確。先判斷是「濫用連接」還是「正確並列」,只改前者。

  • 切斷生硬邏輯連接詞:機械式的「此外」「再者」「另一方面」連續開頭,改以句子前後的邏輯流動承接。 why:好的學術中文靠論證推進,不靠連接詞貼合。 例外:對比、遞進關係真實存在時,保留一個精準的轉折詞比硬拆更清楚。

  • 句式:避免過度工整的對稱句、四字排比堆疊,那是中文 AI 生成的特徵。

階段三:保留原始註解與規範

  • 表格與圖的完整註解一律保留,除非冗餘且不符學術規範,否則不刪。改動註解要在審查意見中說明。

階段四:結構層論證力度檢查(詞彙乾淨之後真正決勝的一關) 階段二清掉的是表面。口試委員說「這篇很空」時,看到的是結構層: 詞都乾淨了、句子也通順,論證卻沒有重量。必讀 references/argument-force-check.md, 逐條核對其中八項訊號(對立句式通膨、三項並列慣性、段落等重、對稱避險、無成本宣稱、 文獻點名清單、機制缺席、主題句過度整齊)。

該檔開頭已寫明兩件必須遵守的事,不可略過: (a)此檢查的依據來自小說領域的研究,其「人味」指標(敘事罕見度、時序跳接) 不能直接搬到實證論文——實證論文本來就該清楚線性;可轉移的只有 「AI 傾向選擇無成本、無立場、可預測的表達」這一點。 (b)目的不是規避 AI 偵測——偵測工具假陽性高且隨模型更新失效。這八項就算完全 不考慮 AI 也都該修。若使用者要求「讓偵測器測不出來」,明說本 skill 不做那件事, 能做的是把論證改強。

分級處理(決定能不能代改):

  • 需作者補內容(第 4、5、7 條:缺立場/缺具體限制/缺機制)→ 只標示、不代寫。 代寫等於替作者捏造研究主張,違反下方誠實防線。
  • 可代改(第 1、2、6、8 條)→ 改寫後併入「潤飾後文本」。
  • 提醒即可(第 3 條段落配重)→ 屬作者的編輯決定。

<output_contract> 明確分區塊(保留原設計的好處:作者能分開看「你怎麼評」與「改成什麼」)。 區塊編號不是工作流階段的一對一鏡像:階段一與階段二的成果都收斂到 「一、審查意見」與「二、潤飾後文本」。 階段四則單獨對應「四、結構層論證力度」——它獨立一區,是因為多數項目 不能代改、要作者自己補,和可直接取用的潤飾後文本性質不同, 混在一起作者會誤以為都改好了。

## 一、審查意見
- [問題類型] <哪一句/哪一段> | 問題:<...> | 建議:<...>
  嚴重度:Major(影響專業度/語意)| Minor(用詞優化)
(若潤飾可能觸及語意,於此標「此改動涉及語意,請作者確認未偏移原意」)

## 二、潤飾後文本
(可直接取用的乾淨版本;改動較大處以 [原:...] 行內標註,方便作者核對)

## 三、保留未動
(列出寫得好、刻意不動的句子——包括「這裡的分號是正確並列,未改」)

## 四、結構層論證力度
(依 references/argument-force-check.md 八項核對;詞彙層乾淨不代表這關過了)

**需作者補內容**(本 skill 不代寫,代寫=替作者捏造研究主張)
- [第N條] <哪一段> | 缺什麼:<...> | 補的方向:<...>

**已代改**(改動已含在上方「二、潤飾後文本」,此處只列條號與處數)
- 第1條 對立句式:N 處 第6條 文獻點名清單:N 處…

**提醒**
- <段落配重等由作者決定的事項>

若八項皆未命中,寫「結構層未見明顯弱點」——不要為了填表硬找。

</output_contract>

After(潤飾後文本): "家族企業的控制股東常因盈餘分配權與控制權偏離而衍生第二類代理問題(controlling-minority agency problem),使其公司治理機制與股權分散的公司有本質差異。本研究即聚焦於此一台灣家族企業普遍存在的治理情境。"

審查意見摘要:刪「值得注意的是/在當今數位時代/綜上所述/不可否認」四處 AI 套話(刪後語意無損);三個分號皆為「濫用連接」非並列,改為斷句與因果承接;「顯得尤為重要」為空泛判斷,改為可辨識的治理差異論述;補「第二類代理問題」術語使定位更精準。實質主張(此議題有研究價值)保留,只換更像成熟學者的說法。 (對照:若原句為「本研究控制了公司規模;負債比率;產業別」,此處分號為並列,應保留不改。)

Files

What ships with it

3 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.

Changes

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.

  1. 5d ago Changed · +2 lines 4fae09071ddb
  2. 1mo ago Changed · +46 lines ea0dc0701419
  3. 1mo ago Changed · +4 lines a1572d7a2c3c
  4. 1mo ago First seen · 75 lines · 295 tokens per session scan A a9608e6c3a94

Subscribe to this mod's changes

academic-journal-polisher is a skill published in the GitHub repository Nero1688/claude-academic-skills (13 stars, last pushed 5d ago), licensed MIT. It adds 295 tokens to every session and 3,381 once invoked, about $0.0012 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 2026-08-31.

Related

Other skills, from other repositories

alterlab-qiime2-amplicon

Runs 16S/ITS amplicon (microbiome) analysis with the QIIME 2 distribution (2026.7; the "amplicon" distribution was renamed "qiime2" in 2026.4) in the correct order: manifest import, cutadapt trim-paired primer removal BEFORE dada2 denoise-paired (trunc-len chosen from the demux quality .qzv), feature-classifier…

AlterLab-IEU/AlterLab-Academic-Skills · 270 tokens

alterlab-paper-writer

Drafts and revises academic papers through a 12-agent pipeline with hardened LaTeX output (apa7 class, PDF compiled from LaTeX), supporting IMRaD, literature review, theoretical, case study, policy brief, and conference paper structures, APA 7.0 (default), Chicago, MLA, IEEE, and Vancouver citation formats, bilingual…

AlterLab-IEU/AlterLab-Academic-Skills · 271 tokens

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-IEU/AlterLab-Academic-Skills · 266 tokens

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)…

AlterLab-IEU/AlterLab-Academic-Skills · 166 tokens

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-IEU/AlterLab-Academic-Skills · 126 tokens

alterlab-teaching-design

Designs courses and teaching materials using backward design (Wiggins & McTighe), constructive alignment (Biggs), and Bloom's taxonomy alignment, generating rubrics, formative and summative assessments, syllabi, lesson plans, inclusive-pedagogy guidance, and online/hybrid course architecture. Use when the request…

AlterLab-IEU/AlterLab-Academic-Skills · 123 tokens