Cell Manuscript Editing logo

Cell Manuscript Editing

Community
yrui-cmd
cell-manuscript-editing

深度润色已有英文科研论文,在尽量保留作者原意、数据、科学判断和表达习惯的前提下, 改善英文准确性、论证逻辑、证据与结论匹配、段落结构和术语一致性,并减少模板化、 宣传式和模型化表达,使文本保持真实作者声音。 适用于英文论文润色、修改 Introduction/Methods/Results/Discussion/Conclusion、 检查过度推断、按作者风格改稿、论文去 AI 感/去 AI 味/humanize,以及把作者已有中文内容 忠实转写为学术英文;这里的自然化是写作质量改进,不用于推断作者身份或规避 AI 检测; 不用于脱离已有研究内容从零写论文、处理审稿回复、撰写文献综述或准备投稿包。

Overview

Publisheryrui-cmd
RepositoryCell
Skill namecell-manuscript-editing
Stars
111
Forks
1
Bundled files
14
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 14 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by yrui-cmd on GitHub. Read the source before you install it.

Installation

Install the Cell Manuscript Editing AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/yrui-cmd/Cell/tree/main/skills/cell-manuscript-editing
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/yrui-cmd/Cell.git /tmp/Cell
mkdir -p .claude/skills
cp -r /tmp/Cell/skills/cell-manuscript-editing .claude/skills/cell-manuscript-editing
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Cell Manuscript Editing in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Cell Manuscript Editing on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Cell Manuscript Editing is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

英文科研论文深度润色

让修改后的英文仍像作者本人写的,只是科学含义更准确、逻辑更清楚、证据边界更严密、语言更符合正式期刊表达。修改优先级为:科学准确性、论证逻辑、证据匹配、信息完整性、段落结构、语言准确性、流畅度、文风美化。

用户未另行指定时,默认以短句和中等长度句为主,一个句子尽量承载一个核心判断。只在多层从句、插入语或多重逻辑妨碍阅读时拆句,不按固定字数切句,也不把全文改成碎短句。逐句核对语法,并按动作时间和句子功能选择时态;用户在当前任务提出的新风格要求优先。

使用边界

先锁定用户要求的范围,不把局部润色升级为全文重写。

  • language_edit:修改语法、用词、简洁性和衔接;发现严重科学或逻辑风险时另行指出。
  • logic_edit:在指定范围内修复论证顺序、证据链、替代解释和结论强度。
  • audit:只报告问题、风险和建议,不直接改原文。
  • translation_edit:把作者已有中文研究内容忠实转写为英文,不逐字翻译,也不增加原意之外的信息。
  • comprehensive_edit:只有用户明确要求全面润色时,才同时处理结构、逻辑、证据和语言。

缺少可供润色或忠实转写的原文、研究事实与必要上下文时,不从常识补写论文内容。完整综述使用 cell-review;审稿回复使用 cell-reviewer-response;定稿后的期刊格式和投稿材料使用 cell-submission。

按需读取

不可改变的事实

未经明确证据,不改变数据、数值、单位、样本和组别身份、研究阶段、实验条件、方法、统计结果、效应方向、图表编号、引文身份和专业实体名称。不能把相关改成因果,把可能性改成确定性,把局部结果推广为普遍规律,或补造数据、机制、作者观点和文献。

原文存在歧义时使用最保守且最接近原意的英文,并标出会影响科学判断的未决点。语言更自然不是提升结论强度的理由。

润色流程

1. 锁定输入和范围

读取指定原文及完成判断所需的相邻段落、图表、引文或作者说明。明确论文部分、润色模式、允许调整范围和必须保留的术语。文件任务保留原件,在副本上工作;不能只根据摘要或文件名判断全文。

2. 先理解再修改

识别文本要回答的科学问题、核心判断、直接观察、解释、进一步推论和重要判断的证据来源。先处理逻辑与证据层级,再调整英文;不能用顺滑语言掩盖论证缺口。

3. 最小必要修改

准确、清楚的原句可以保留。优先删除重复、修正术语和指代、调整必要句序、补清真实逻辑关系、降低无依据的强断言,并去除空洞评价和机械套话。长句妨碍理解时按核心判断拆分,再补清句间关系;不要为了显示修改量重写每句话。

4. 去除模板腔并恢复作者节奏

按 自然化流程 做最多两遍有界编辑:第一遍处理聊天残留、空泛铺垫、意义膨胀、虚构对立、无来源权威和通用结尾;第二遍检查重复句式、连接词堆积、同义词轮换与机械节奏。单个词、被动语态、we、必要限定词、三项并列或某种标点都不是自动改写理由。

完整文件或较长章节应在可提取为 UTF-8 文本时运行:

bash
python scripts/academic_prose_lint.py path/to/manuscript.txt

结果是人工复核线索,不是 AI 作者判定或验收分数。没有实质问题时保持原文,不通过反复改写、故意语病、随机标点或虚构个人经历制造所谓“人类感”。

5. 继承作者选择

同一任务中持续继承作者已确认的术语、结论强度、句长偏好、禁用表达和不修改区域。需要跨章节复用时,从 示例 profile 建立任务级文件并运行:

bash
python scripts/check_author_profile.py path/to/author-style-profile.json

profile 是显式任务资料,不代表跨会话自动记忆。用户的新明确要求覆盖旧偏好,但不能覆盖科学事实。

6. 回核最终英文

对照原文、图表和可用证据复核数字、比较对象、方向、限定词、术语、时态、图号和引文。逐句检查主谓一致、句子完整性、冠词、单复数、介词、修饰关系和指代;拆句或重组后再次检查语法、时态与逻辑衔接。确认删减没有移除必要条件,重组没有改变时间或因果关系,中文转写没有增加新含义。

完整文件或较长章节应保存修改前后两个文本版本并运行:

bash
python scripts/check_manuscript_preservation.py before.txt after.txt

该脚本只比较部分可机械保护的数值、单位、交叉引用、引文、公式、链接和直接引语。无论结果是否通过,仍须人工复核否定、归因、因果、不确定性、比较方向和研究范围。

输出

  • 短文本:默认提供润色后的完整英文,再简要说明会影响理解的关键修改;用户要求只给修改稿时不附解释。
  • 审核任务:区分确定问题与待确认风险,给出原文定位、原因和最小修复方案。
  • 文档任务:沿用用户指定或原文件格式;只有用户要求时才生成修订痕迹、逐条对照或额外报告。
  • 证据不足:指出需要补证据或降低强度的位置,不偷偷插入看似合理的引用。

完成条件

  • 修改范围与用户要求一致,没有擅自扩写、从零续写或整章替换。
  • 事实、数字、实体、图表和引文与可用材料一致。
  • 观察、解释和推论层级清楚,结论强度由证据决定。
  • 段落围绕明确问题展开,术语与缩写一致。
  • 英文准确、直接、克制且自然,没有为“学术感”堆叠抽象词、套话或宣传式意义。
  • 模板化模式已经结合上下文和作者样本复核;没有把模式命中误报成作者身份判断,也没有为了规避检测而制造噪声。
  • 已检查长难句的阅读负担,并在拆句后复核语法、时态和逻辑衔接;没有因简化句式损失科学含义。
  • 最终版本已经回读;未取得的证据和未完成的检查被如实说明。

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Cell Manuscript Editing AI skill do?

深度润色已有英文科研论文,在尽量保留作者原意、数据、科学判断和表达习惯的前提下, 改善英文准确性、论证逻辑、证据与结论匹配、段落结构和术语一致性,并减少模板化、 宣传式和模型化表达,使文本保持真实作者声音。 适用于英文论文润色、修改 Introduction/Methods/Results/Discussion/Conclusion、 检查过度推断、按作者风格改稿、论文去 AI 感/去 AI 味/humanize,以及把作者已有中文内容 忠实转写为学术英文;这里的自然化是写作质量改进,不用于推断作者身份或规避 AI 检测; 不用于脱离已有研究内容从零写论文、处理审稿回复、撰写文献综述或准备投稿包。

Why use Cell Manuscript Editing on TypingMind?

Because you install it once and use it with any model. Cell Manuscript Editing is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Cell Manuscript Editing in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/yrui-cmd/Cell/tree/main/skills/cell-manuscript-editing. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Cell Manuscript Editing?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Cell Manuscript Editing?

As many as you like. As long as a model supports skills, you can use Cell Manuscript Editing with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Cell Manuscript Editing AI skill free?

Yes. It is published on GitHub by yrui-cmd under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇