
academic-revision-checklist
66 reader-first rules for revising academic English, drawn from 60+ revision rounds of a PhD dissertation, with a 16-item quick list, a script that flags pla…
Install with your AI
Paste into Claude Code, Cursor, or any agent — it reads the repo and wires the tool into your project.
Install and set up academic-revision-checklist (claude-skill project) into my current project. Found on https://claudeers.com/academic-revision-checklist Repo: https://github.com/JimmyRaoUF/academic-revision-checklist Homepage/docs: https://nanjierao.github.io Detected install method: claude-skill → # copy this skill into .claude/skills/academic-revision-checklist/ Category: skills. Platforms: web. Read the repo's README for exact setup and env vars, then install it and wire it into my project. Claudeers Health Verdict: active; community-verified: false. Confirm the source before running anything.
# copy the skill dir into your project: # .claude/skills/academic-revision-checklist/ (or ~/.claude/skills/academic-revision-checklist/ for all projects)
git clone https://github.com/JimmyRaoUF/academic-revision-checklist
// compatibility
| Platforms | web |
|---|---|
| Operating systems | — |
| AI compatibility | claude |
| License | NOASSERTION |
| Pricing | open-source |
| Language | Python |
academic-revision-checklist
给英文学术写作用的修改清单:66 条规则,16 条快速清单,一套「一个案例,一条规则,查全文」的做法,和一个列候选的脚本。
这些规则来自我的英文博士论文(人机交互方向,2026 年 10 月通过答辩)五周、60 多轮的修改记录。每一条都是先在一个具体的句子上卡住,修好,再抽象成一条能拿去检查的规则,然后带着它把全文查一遍。
可以直接当清单读,也可以装成 Claude 的 skill,让 Claude 按这套做法逐句帮你查。
「AI 痕迹」指什么
这里说的「AI 痕迹」,跟检测器查不查得出来没多大关系。它指的是读者第一次读就卡住、要回头再读一遍的地方。导师、委员会、审稿人读到这种地方,就会觉得是机器写的。
学校或期刊要求说明 AI 用在了哪里,就照规定写清楚。
十六条快速清单
改完一段,逐条问一遍。
- 第一次读的人会在这一句停下吗?要读两遍的,写下原因。
- 一句话只报一个结果。
- 写了 more、higher,就写出和谁比。
- significant 只用在差异、关联或检验上,不用在比例或平均数上。
- this、these、the former、the name 这类词,指的东西在前一句之内吗?
- 一个名字只指一样东西,普通词别撞上自己定义的术语。
- 冒号只用来引出列表、引文、问题或定义。
- 少用先否定再肯定的铺垫,带内容的否定留下。
- 正文不用破折号连接分句。
- 连着几句长度差不多、开头一样的,改掉一处。
- 空的过渡词和段尾总结,能删就删,删不掉就换成具体内容。
- 用自己和这个领域会用的词,能用常用词就不用生僻词。
- 论文只写研究本身,不写论文是怎么改出来的。
- 研究问题、引文、数字、自己的反思,不交给 AI 改。
- 改完重读这一段和前一段,字数上限、段落长度这些硬指标再跑一遍。
- 别人和 AI 的意见,先拿原文和数据对过,成立的才改。
66 条的完整版在 references/checklist.md,每条一句话;规则、改前改后的原句和查法在 references/patterns.md,编号一致。
文件
academic-revision-checklist/
├── README.md 就是这个文件
├── SKILL.md 给 Claude 的说明(英文)
├── LICENSE
├── references/
│ ├── checklist.md 16 条快速清单和 66 条一句话规则,从这里开始
│ ├── patterns.md 66 条的完整版:规则、论文里真改过的句子、怎么查
│ ├── workflow.md 一轮修改怎么走,外部意见怎么核对,给其他模型的提示词
│ ├── reading-protocols.md 像第一次读的人那样读,标题怎么读,出声读
│ └── lessons.md 九条原则和八条教训
└── scripts/
└── flag_candidates.py 列出脚本找得到的候选:破折号、冒号、对比句式等
规则和说明是中文写的,例子都是英文原句。
怎么用
1. 当清单读
从 references/checklist.md 开始。想知道某一条为什么要改、怎么改,就看 patterns.md 里同一个编号。
2. 装成 Claude Code 的 skill
git clone https://github.com/JimmyRaoUF/academic-revision-checklist.git ~/.claude/skills/academic-revision-checklist
然后在 Claude Code 里说「用 academic-revision-checklist 检查 chapter3.tex」,或者输入 /academic-revision-checklist。只想在一个项目里用,就放到那个项目的 .claude/skills/ 下面。
3. 在 Claude 网页版或桌面版里用
把整个文件夹打包成 zip,作为自定义 skill 上传,步骤见 Claude 帮助中心的 Use skills in Claude。文件夹名要和 skill 名一致。从 GitHub 点 Download ZIP 得到的文件夹叫 academic-revision-checklist-main,要先改回 academic-revision-checklist 再打包。也可以只把 checklist.md 和需要的 patterns.md 章节贴进对话。
4. 在 ChatGPT、Gemini 等其他模型里用
把 references/checklist.md 贴进去,再用 references/workflow.md 里的提示词模板。要它逐句读、标出读者会停下的句子,不要让它整段重写。它给的每一条意见,都先拿原文和数据核对。
5. 跑脚本
只需要 Python 3,不用装别的包。
python3 scripts/flag_candidates.py chapter3.tex --summary
python3 scripts/flag_candidates.py chapter3.tex chapter4.tex --md flags.md
python3 scripts/flag_candidates.py paper.md --max-para 150
能读 .tex、.md 和 .txt,会跳过表格、图、公式和注释。脚本负责把可疑的地方列全,判断还得靠读。我改论文时,缩写检查标出 13 处,真有问题的只有 3 处。
几样东西从不交给 AI 改
研究问题的措辞、引文原文、没有数据支撑的数字、自己写的反思段落。每一轮都把它们单列出来,只报告,不改。
作者
Nanjie (Jimmy) Rao,佛罗里达大学(University of Florida)Human-Centered Computing 博士,2026 年 10 月通过答辩。
- 个人网站:nanjierao.github.io
- Google Scholar:Nanjie Rao (Jimmy)
- 知乎:刀口饶,这份清单最早发在知乎的一个回答里
- YouTube:@drluckydadredl
觉得有用就点个 star,也可以在知乎告诉我它帮你改了哪一句。发现规则之间打架,或者有新的例子,欢迎开 issue。
许可
文字部分(README、SKILL.md 和 references/)用 CC BY 4.0,可以转载、改写、商用,注明出处就行。脚本(scripts/)用 MIT。详见 LICENSE。
引用
Rao, N. (2026). academic-revision-checklist: 66 rules for revising academic writing for a first-time reader [Computer software]. GitHub. https://github.com/JimmyRaoUF/academic-revision-checklist
English
A reader-first revision checklist for academic English: 66 rules, a 16-item quick list, a method, and a script.
It comes from five weeks and more than 60 revision rounds of my English-language HCI dissertation, defended in October 2026. Each rule began as one sentence where a reader stopped: me reading aloud, my advisor, a friend who is a native speaker, or a reviewing model. The fix was written as a rule that can be checked and then applied to the whole document.
"Reads like AI" here means the places where a first-time reader stops or reads twice. This is not a tool for getting past AI detectors.
The 16-item quick list
- Would a first-time reader stop at this sentence? If they would read it twice, write down why.
- Report one result per sentence.
- If you write "more" or "higher", say than what.
- Use "significant" only for a difference, an association or a test, never for a share or a mean.
- Does "this", "these", "the former" or "the name" point to something within the previous sentence?
- Use one name for one thing, and keep ordinary words from colliding with your defined terms.
- Use a colon only to introduce a list, a quotation, a question or a definition.
- Use few "not A but B" set-ups, and keep the negations that carry content.
- Use no em dashes to join clauses in the body text.
- When several sentences in a row have nearly the same length or the same opening, change one.
- Delete hollow transitions and paragraph endings that only summarize. If one cannot go, replace it with something specific.
- Use the words you and your field would use, and prefer the common word.
- Write about the research, not about how the text was revised.
- Keep research questions, quotations, numbers and your own reflections away from AI editing.
- After a change, reread that paragraph and the one before it, and rerun hard limits such as word caps and paragraph length.
- Check comments from people and from AI against the text and the data, and apply only what holds.
How to use it
- As a checklist: start with
references/checklist.md. The full patterns, with English before and after examples, are inreferences/patterns.md(written in Chinese). - As a Claude Code skill:
git clone https://github.com/JimmyRaoUF/academic-revision-checklist.git ~/.claude/skills/academic-revision-checklist, then ask Claude to check a chapter with it.SKILL.mdis in English. - The script needs Python 3 and nothing else:
python3 scripts/flag_candidates.py chapter.tex --summary. It lists candidates, and you decide by reading.
Author: Nanjie (Jimmy) Rao, Human-Centered Computing PhD, University of Florida (defended October 2026). Website: nanjierao.github.io. Google Scholar: Nanjie Rao (Jimmy). Zhihu: 刀口饶. YouTube: @drluckydadredl. Text under CC BY 4.0, scripts under MIT.
// faq
What is academic-revision-checklist?
66 reader-first rules for revising academic English, drawn from 60+ revision rounds of a PhD dissertation, with a 16-item quick list, a script that flags places to reread, and a Claude skill.. It is open-source on GitHub.
Is academic-revision-checklist free to use?
academic-revision-checklist is open-source under the NOASSERTION license, so it is free to use.
What category does academic-revision-checklist belong to?
academic-revision-checklist is listed under skills in the Claudeers registry of Claude-compatible tools.
// embed badge
[](https://claudeers.com/academic-revision-checklist)
// retro hit counter
[](https://claudeers.com/academic-revision-checklist)
// reviews
// guestbook
// related in Claude Skills
An agentic skills framework & software development methodology that works.
AI coding assistant skill (Claude Code, Codex, OpenCode, Cursor, Gemini CLI, and more). Turn any folder of code, SQL schemas, R scripts, shell scripts, docs,…
💫 Toolkit to help you get started with Spec-Driven Development