Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Chinese-to-English Translation & Polish

    1

    Translate Chinese into natural English, polish drafts against Chinese sources, and produce aligned bilingual output with fidelity checks.

    Free

    1 useSecurity scanned
    Chinese-to-English Translation & Polish

    Chinese-to-English Translation & Polish

    Example session with this skill installed

    Use zh-en-translation-polish to translate this illustrative research statement into natural English. Return paragraph-by-paragraph Chinese-English output and preserve every qualification:

    本研究比较两种校准方案。初步结果提示,在本次测试条件下,第二种方案可能降低测量波动;这一发现并不能证明它在所有设备上都更好。

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

    Chinese-English translation

    本研究比较两种校准方案。初步结果提示,在本次测试条件下,第二种方案可能降低测量波动;这一发现并不能证明它在所有设备上都更好。

    This study compares two calibration approaches. Preliminary results suggest that the second approach may reduce measurement variability under the conditions tested. The finding does not establish that it performs better across all devices.

    Fidelity check

    • “初步” remains “Preliminary”; the result is not presented as settled.
    • “可能” remains “may”; no guaranteed improvement is added.
    • “本次测试条件下” limits the statement to the conditions tested.
    • The final sentence retains the restriction on generalizing to every device.

    Use and review

    The passage is a short technical statement, so terminology and evidential limits take priority over rhetorical compression. For a full document, use consistent terminology and review source coverage section by section. An advisory scanner can identify candidates for review, but a clean scan does not establish semantic accuracy.

    This input was written for this listing and the translation is illustrative. It is not a report of an actual calibration experiment, a model benchmark, or a claimed improvement over another translation system.

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

    About this skill

    Translate Chinese passages into natural English or polish an English draft against its Chinese source. This workflow adapts to academic, technical, business, and expressive writing while preserving factual content, qualifications, modality, attribution, numbers, terminology, and the author’s intended meaning.

    It combines register selection, expression diagnosis, source-fidelity checks, and an advisory Python scanner for common Chinglish, punctuation, and formatting candidates. For longer texts it checks source coverage and translation grounding in both directions, reviews material in sections, and preserves speaker and caption attribution. It can return English-only output or paragraph-by-paragraph Chinese-English output, according to the request.

    The complete package includes four supporting reference files, the advisory scanner and its tests, semantic quality cases, bilingual README files, installation guides, and the MIT license.

    Requirements: an Agent Skills-compatible host; document inputs depend on your agent’s reading tools. Python 3 is needed for the advisory scanner. Warnings are candidates for review, not a quality score or a requirement to remove every warning. The release does not claim measured model translation performance. This skill does not cover English-to-Chinese translation, original English composition, or simple word lookups.

    Documentation, installation instructions, and a complete ZIP are available without GitHub at https://www.lumenghe.com/en/skills/zh-en-translation-polish/ . Chinese documentation: https://www.lumenghe.com/skills/zh-en-translation-polish/ .

    Version: 1.1.1. Verified source commit: c0137b8cc4bcce620e02142174013e9b717b9288. Packaged 2026-10-24.

    Code, prompts, and package organization are released under the MIT license. Preserve the included copyright and license notices. Brief quotations in supporting reference materials remain the copyright of their original authors and publishers.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Translation & Localization.

    Chinese-to-English translation and source-grounded polishing only. Semantic accuracy depends on the host model and source material; specialist and publication work needs human review. Document extraction requires host tools. The Python scanner is advisory and cannot prove fidelity or overall quality. No model-performance benchmark is claimed.

    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 buying a skill.

    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

    1 use

    Times used to date

    Free to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 24 days ago

    • Free with an Agensi account

    Software
    Python 3Node.js

    Permissions

    Terminal / Shell
    Read Files
    Write Files

    Reads user-supplied source and draft files and writes requested translation artifacts. Shell/Python runs the local advisory scanner when appropriate. The translation workflow and scanner do not require network access, credentials, or external accounts; installing software or fetching optional documentation is separate.

    Listed24 days ago

    What's inside

    Frequently Asked Questions

    Use an Agent Skills-compatible host with access to the source text. Document extraction and output files depend on host tools. Python 3 is needed for the advisory scanner; Node.js, GitHub access, and external service accounts are not required for translation. Documentation and the complete ZIP are available at https://www.lumenghe.com/en/skills/zh-en-translation-polish/ . Preserve any existing installation before updating.

    New in Translation & Localization

    Free