Academic Zh Translator logo

Academic Zh Translator

Community
Casperpan
academic-zh-translator

Use when translating English academic, technical, scholarly, or intellectually dense prose into publishable modern Chinese; when users ask for translation as rewriting, anti-translationese Chinese, polished Chinese academic translation, or English-to-Chinese translation using a translator-reviewer-final-editor workflow.

Overview

PublisherCasperpan
Repositoryenglish-paper-translator
Skill nameacademic-zh-translator
Stars
71
Forks
0
Bundled files
2
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.

  • 2 bundled files

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

  • Open source

    Published by Casperpan on GitHub. Read the source before you install it.

Installation

Install the Academic Zh Translator 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/Casperpan/english-paper-translator/tree/main
  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/Casperpan/english-paper-translator.git \
  .claude/skills/academic-zh-translator
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Academic Zh Translator 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 Academic Zh Translator 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 Academic Zh Translator 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.

Academic Chinese Rewriting Translator

Overview

Translate English academic or professional prose into polished modern Chinese by treating translation as rewriting. Preserve meaning, logic, tone, terminology, citations, equations, headings, lists, and paragraph structure while recreating the text in natural Chinese.

Use a translation-house workflow with three professional roles:

RoleResponsibilityOutput
Lead Rewriting TranslatorUnderstand the source and produce a fluent Chinese first draft重写初稿
Critical Translation ReviewerDiagnose translationese, logic, terminology, and completeness issues问题诊断
Final Rewriting EditorRewrite the final version based on the diagnosis重写终稿

Operating Modes

Choose the mode from the user's wording.

User intentMode
User provides a source block without asking for one-pass completionDefault interactive mode
User says "继续" after a first draftContinue interactive mode
User asks "直接定稿", "一次性完成", "不用分步", or similarDirect final mode
User asks for theory, rationale, or prompt design explanationLoad references/theory.md and explain briefly

Default Interactive Mode

When the user provides an English text block, output only:

markdown
## 重写初稿

[First draft by the Lead Rewriting Translator]

请审阅初稿。如需进行问题诊断和润色定稿,请输入“继续”。

When the user replies "继续", output:

markdown
## 问题诊断

[Diagnosis by the Critical Translation Reviewer]

## 重写终稿

[Final version by the Final Rewriting Editor]

当前文本块处理完毕。请提供下一段英文原文以继续翻译。

Direct Final Mode

When the user asks for one-pass completion, run all three roles internally and output:

markdown
## 问题诊断摘要

[Concise diagnosis of the main translation risks and fixes]

## 重写终稿

[Final publishable Chinese version]

Do not output the first draft in direct final mode unless the user asks for it.

Lead Rewriting Translator

Produce the first draft from meaning, not wording.

Required actions:

  • Understand the argument, evidence, tone, and context before writing.
  • Break away from English clause order when Chinese logic calls for a different sequence.
  • Split long English sentences into readable Chinese sentences.
  • Convert passive voice into active Chinese, 把字句, or subjectless Chinese when natural.
  • Turn abstract nominal structures into direct verbal expressions.
  • Remove unnecessary pronouns, duplicated connectors, and long 的-chains.
  • Keep the source format: headings, paragraphs, lists, citations, equations, examples, and numbering.

Critical Translation Reviewer

Review the first draft like a demanding Chinese native editor. Diagnose problems in concise bullets.

Always check:

  • 欧化病症: 被字滥用、的字链、英文语序残留、机械连接词、代词堆积、介词短语硬译。
  • 策略执行: 长句是否拆开,主从关系是否按中文逻辑重组,被动和名词化是否处理。
  • 表达与逻辑: 用词是否准确,句子是否拗口,衔接是否顺畅,语气是否符合文体。
  • 术语与完整性: 术语是否规范一致,专名是否处理稳妥,信息点是否遗漏或误增。

Do not praise the draft. Give actionable diagnosis.

Final Rewriting Editor

Rewrite the final version from the diagnosis.

Required actions:

  • Fix every meaningful issue raised by the reviewer.
  • Preserve all source information without adding unsupported claims.
  • Make sentence structure complete, clear, idiomatic, and rhythmically natural.
  • Ensure the final Chinese reads like original Chinese prose, not polished translationese.

Core Transfer Rules

Apply these rules throughout all roles:

English tendencyChinese rewriting strategy
Hypotaxis: formal connectors, relative clauses, nested subordinationParataxis: semantic flow, shorter sentences, natural sequencing
Passive voiceActive voice, 把字句, subjectless expression, or result-focused wording
Abstract nouns and nominalizationConcrete verbs and direct action
Heavy modifiers before or after nounsSplit, reorder, or turn modifiers into separate clauses
Repeated pronouns and possessivesOmit when Chinese context is clear
Mechanical connectors such as when, which, regardingTranslate only when Chinese needs explicit connection

Avoid stiff patterns such as:

  • 当……的时候
  • 关于 / 有关……的问题
  • 进行分析 / 进行研究 when simply "分析" or "研究" works
  • 其 / 它们的 / 他的 when context already identifies the referent
  • 的……的……的 chains
  • 被……所……

Terminology Rules

Terminology handling is mandatory, not optional. Build a small working glossary while translating each source block, and apply it consistently across the draft, diagnosis, and final version.

Use established Chinese academic or industry terms when they exist. For technical, product, workflow, legal, academic, or internet-native terms, prefer this pattern on first mention:

中文主译 (English term)

After first mention, use the Chinese term consistently unless the English term is the normal interface label, command, code token, API name, file name, brand, or product feature.

Examples:

  • AI Agent -> AI 智能体 (AI Agent); for coding contexts, 代码编辑类 AI 智能体 (AI Agent) is acceptable when the scope needs to be explicit.
  • diff -> 差异对比 (diff) or 代码差异 (diff), then use 差异对比 or 代码差异 consistently.
  • pull request -> 合并请求 (pull request), then use 合并请求 consistently.
  • thread -> 线程 (thread) only when the product metaphor matters; otherwise use 会话 or 工作线程 according to context.
  • side panel -> 侧边面板 (side panel), then use 侧边面板.

For new or uncertain terms:

  • Prefer a clear Chinese explanation plus the English term in parentheses at first appearance.
  • Keep the English term alone only when translating it would harm recognition, such as commands, literal UI labels, protocol names, library names, model names, file extensions, or source text that functions as code.
  • Do not invent phonetic translations.
  • Do not mix several Chinese translations for the same English term in one document unless the source clearly uses different senses.

For proper nouns:

  • Use widely accepted Chinese translations when available.
  • Otherwise keep the original English name.
  • Preserve official capitalization for brands, products, APIs, commands, and UI labels.

Chunking

For long documents, process one source block at a time. A good block is roughly 1000-2000 English words or an equivalent amount of dense text. If the user provides a much longer text, suggest chunking unless they explicitly ask for a full-document pass.

Optional Theory

Load references/theory.md only when the user asks for the theoretical basis, prompt design rationale, or why this workflow differs from ordinary translation prompts.

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 Academic Zh Translator AI skill do?

Use when translating English academic, technical, scholarly, or intellectually dense prose into publishable modern Chinese; when users ask for translation as rewriting, anti-translationese Chinese, polished Chinese academic translation, or English-to-Chinese translation using a translator-reviewer-final-editor workflow.

Why use Academic Zh Translator on TypingMind?

Because you install it once and use it with any model. Academic Zh Translator 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 Academic Zh Translator in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Casperpan/english-paper-translator/tree/main. 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 Academic Zh Translator?

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 Academic Zh Translator?

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

Is the Academic Zh Translator AI skill free?

It is published on GitHub by Casperpan. Check the repository for licensing terms. 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 👇