Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    English-to-Chinese Translation & Polish

    1

    Translate English into natural Chinese, polish Chinese drafts against the source, and produce paragraph-by-paragraph bilingual output.

    Free

    2 usesSecurity scanned
    English-to-Chinese Translation & Polish

    English-to-Chinese Translation & Polish

    Example session with this skill installed

    Use en-zh-translation-polish to translate the following instructional text into natural Chinese. Return paragraph-by-paragraph English–Chinese output and a brief note on your approach. Preserve all qualifications.

    Before revising a translation, identify its intended audience and purpose. A technical manual needs consistent terminology and precise instructions. An essay may allow more flexibility in sentence rhythm, but that flexibility does not justify changing the author’s meaning.

    Keep numbers, qualifications, and causal relationships intact. When a sentence sounds awkward in Chinese, rebuild its structure instead of replacing individual words mechanically. Then compare the revision with the English source to check for omissions or unintended additions.

    • Read your context and instructions
    • Compiled the english-to-chinese translation

    English–Chinese translation

    Before revising a translation, identify its intended audience and purpose. A technical manual needs consistent terminology and precise instructions. An essay may allow more flexibility in sentence rhythm, but that flexibility does not justify changing the author’s meaning.

    修改译稿前,应先明确读者和翻译用途。技术手册需要统一的术语和准确的操作说明。散文的句式与节奏可以处理得更灵活,但这种灵活性不能成为改变作者原意的理由。

    Keep numbers, qualifications, and causal relationships intact. When a sentence sounds awkward in Chinese, rebuild its structure instead of replacing individual words mechanically. Then compare the revision with the English source to check for omissions or unintended additions.

    数字、限定条件和因果关系都应准确保留。句子在中文里读着别扭时,应重组句式,避免机械地逐词替换。修改后,再对照英文原文,检查是否有遗漏或无意增加的内容。

    Translation note

    文本属于说明性文字,偏硬,自由度约 3/10。以准确为先,保留用途、限定条件和因果关系;调整句式,使中文自然流畅,避免逐词替换。

    This demonstration uses illustrative input written for this listing. The translation is an example, not a measured quality benchmark.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    A practical workflow for English-to-Chinese translation and source-grounded polishing, based on Ye Zinan’s translation methodology.

    Use it to translate English passages or improve a Chinese draft against the English original. It adapts its approach to the text type: technical and formal texts prioritize accuracy, while essays and other expressive texts allow more stylistic freedom.

    Features:

    • Diagnose and reduce common translationese patterns.
    • Preserve numbers, terminology, qualifications, links, and source meaning.
    • Produce paragraph-by-paragraph English–Chinese output for full-text projects; respect requests for Chinese-only output.
    • Normalize Chinese punctuation while preserving English, code, formulas, and links.
    • Use three supporting reference tables for text analysis, translation techniques, and quality checks.

    This is an agent skill, not a standalone translation engine. It uses the capabilities of your existing AI agent. Document input requires that the host agent can read the supplied file. Human review is recommended for publication or specialist use.

    Open source, with documentation and a complete ZIP available from the creator website without GitHub. Code, prompts, and organization are released under the MIT license. Brief source quotations in the reference materials remain the copyright of their respective authors and publishers. Full attribution and license information are included in the package.

    The translation workflow and ZIP installation do not require Node.js, Git, or a GitHub account. Python 3 is used for punctuation processing. Node.js, Git, and GitHub access apply only to the optional Star History maintenance files included with the full source package.

    Version 1.1.1 clarifies fidelity boundaries across registers, checks source coverage and translation grounding in both directions, and adds chunked review for long texts and clearer attribution. The complete package includes bilingual documentation, installation guides, supporting files, and original quality-check cases; these cases are not a measured model-performance benchmark.

    Creator: HoraceLuBFA Documentation and complete ZIP: https://www.lumenghe.com/en/skills/en-zh-translation-polish/ 中文说明: https://www.lumenghe.com/skills/en-zh-translation-polish/ Latest source release: 1.1.1 Verified source commit: 3ab66c74c6442c3a97c7016a0f4675118f13bc50 Packaged: 2026-10-24. Agensi package updates remain subject to platform review.

    Translation quality depends on the host model and the supplied source. The skill is English-to-Chinese only. It is not an OCR or document-parsing engine; document inputs require host support. Specialist terminology and publication-ready results need human review.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    2 uses

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 24 days ago

    • Free with an Agensi account

    Requires

    Python 3
    Git
    Node.js

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Network Access
    Environment Variables

    Reads supplied documents and writes requested translation files. Shell/Python supports punctuation normalization and deriving Chinese-only files. The translation workflow needs no external account. Optional Star History maintenance files use Node.js, GitHub network access, and the runner-provided GITHUB_TOKEN; these are not needed for translation and no credential is included.

    Listed1 month ago
    Updated23 days ago

    What's inside

    Frequently Asked Questions

    This is a structured workflow for your existing AI agent, using Ye Zinan’s methodology, register-sensitive expression checks, and source-grounded review. It aims to reduce translationese while preserving meaning, qualifiers, terminology, links, code, and formulas. Output quality still depends on the host model and needs appropriate review.

    Use an Agent Skills-compatible host that can read the supplied input. Short passages can be handled in chat. Document parsing and file delivery depend on the host tools, and Python 3 is used for the punctuation-processing example.

    Yes, while it defaults to a paragraph-by-paragraph bilingual layout for easy review, you can specifically request a Chinese-only version for your final output.

    Yes. Technical and formal texts prioritize precise terminology and explicit relationships, while expressive texts allow more flexibility in rhythm and wording. Fidelity remains a requirement in every register; stylistic freedom does not permit adding or removing meaning.

    The 1.1.1 source package includes SKILL.md, three reference tables, bilingual README and installation guides, quality-check cases, supporting maintenance files, and the MIT license. Agensi serves its approved package while updates are reviewed. The complete latest ZIP is also linked at https://www.lumenghe.com/en/skills/en-zh-translation-polish/ .

    Yes. The workflow code, prompts, and organization are MIT licensed. Documentation and the complete ZIP are available without GitHub at https://www.lumenghe.com/en/skills/en-zh-translation-polish/ . Attribution and copyright notices for brief source quotations are retained in the package.

    New in Translation & Localization