en-zh-translation-polish

en-zh-translation-polish is a skill for Claude Code from HoraceLuBFA/en-zh-translation-polish. It costs 103 tokens per session (3,427 once invoked), scanned A, original, MIT.

An English-to-Chinese translation and editing process focused on natural Chinese rather than word-for-word wording.

In plain words
What is it for?
It analyzes the text type, translates and polishes each paragraph, and can produce an English-Chinese parallel document or a Chinese-only version.
Why use it?
It reduces stiff, English-shaped phrasing while preserving the source text's meaning, tone, and intended effect.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit It analyzes the text type, translates and polishes each paragraph, and can produce an English-Chinese parallel document or a Chinese-only version.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/horacelubfa/en-zh-translation-polish/en-zh-translation-polish
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add HoraceLuBFA/en-zh-translation-polish --skill en-zh-translation-polish
Clone the repo
git clone --depth 1 https://github.com/HoraceLuBFA/en-zh-translation-polish

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for en-zh-translation-polish

README.md
[![agentmods](https://agentmods.dev/badge/skills/horacelubfa/en-zh-translation-polish/en-zh-translation-polish/github.svg)](https://agentmods.dev/skills/horacelubfa/en-zh-translation-polish/en-zh-translation-polish)
Your own site
<a href="https://agentmods.dev/skills/horacelubfa/en-zh-translation-polish/en-zh-translation-polish"><img src="https://agentmods.dev/badge/skills/horacelubfa/en-zh-translation-polish/en-zh-translation-polish/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for en-zh-translation-polish

Your own site · 80×15
<a href="https://agentmods.dev/skills/horacelubfa/en-zh-translation-polish/en-zh-translation-polish"><img src="https://agentmods.dev/badge/skills/horacelubfa/en-zh-translation-polish/en-zh-translation-polish.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 103 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,427 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00103 $0.03427
Opus 5 $0.00051 $0.01714
Sonnet 5 $0.00021 $0.00685
Haiku 4.5 $0.00010 $0.00343

Measured 12d ago against content hash d7f607bebf85, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

en-zh-translation-polish scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

SKILL.md · 168 lines

How it starts

The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.

英译汉翻译润色 (English→Chinese Translate & Polish)

把英文译成地道中文并产出英中对照译文。核心信条(叶子南):英译汉最致命的错误是把英语的“形合”结构迁移进汉语造成翻译腔;好译文 = 以读者为中心、按文本类型调节归化尺度、发挥汉语意合优势、兼顾音韵节奏

交付物

默认产出一个英中对照 Markdown 文件;用户要“全中文版”时再脚本派生。

  1. <名称> 翻译(中英对照).md — 唯一真源。每段英文原文作为 blockquote (> ),紧跟其下是中文译文。
  2. (按需)<名称> 翻译(全中文).md — 脱离对照文件用脚本机械派生(删掉 > 行),不要重打中文。
    python3 - "<名称> 翻译(中英对照).md" "<名称> 翻译(全中文).md" <<'PY'
    import sys, re
    src, dst = sys.argv[1], sys.argv[2]
    lines = open(src, encoding='utf-8').read().split('\n')
    kept = [ln for ln in lines if not ln.lstrip().startswith('>')]
    open(dst,'w',encoding='utf-8').write(re.sub(r'\n{3,}','\n\n','\n'.join(kept)).strip()+'\n')
    PY
    

    顺序要求:先跑阶段 6 的标点归一,再派生全中文版——派生脚本原样继承标点,不会再纠正。

若输入只是聊天里的一小段(几句话),直接在回复里给对照即可,不必落盘;成篇文章或用户指明保存才写文件。命名沿用源文件名,无工具前缀(除非用户要)。目标文件已存在则更新而非新建。

工作流(严格按序;每段译文都要走完润色,不是初译就交)

阶段 0 — 文本分析:定归化档位 ★必做第一步

先回答:这是硬文本还是软文本?属纽马克哪一类?自由度大致几分(1–10)? 详见 reference/text-analysis-and-qa.md 小节 A。

  • 偏硬(自由度 1–3):政治/法律/经贸/科技/合同/说明书。→ 贴原文逻辑,选词精准,准确 > 流畅,少介入,术语用固定译法。某些“西化”是为精确付的合理代价。
  • 偏中 (4–6):教科书/新闻/一般论述。→ 平衡,默认交际翻译。
  • 偏软 (7–9):文学/散文/评论/讲演/广告/宣传/营销。→ 大胆发挥意合与汉语之美,可调结构、可换形象,流畅/效果优先
  • 别忘文本外因素:翻译目的、读者是谁。档位一句话写进给用户的说明里。

阶段 1 — 理解 → 脱离语言外壳

读懂原文后,抛开英文词句,在脑中形成意义/图像,再用中文重构(不要在词面上挪移)。遇到结构纠缠的短语用“解包袱法”理清隐含语义关系(见 reference/techniques.md)。

阶段 2 — 按档位初译

意合优先起译:能不用连接词就不用,长句拆成流水短句,被动转主动,定语别堆在名词前。

阶段 3 — 润色诊断(核心)逐段过三张表

  1. 翻译腔病症 — 对照 reference/translationese-symptoms.md 逐条排查并修:形合迁移/连接词冗余、长前置定语、“的的不休”、被动滥用、抽象名词作主语、习语硬译、语义关系隐含不清。
  2. 技巧库 — 用 reference/techniques.md 的手段修:词性转换、增/减词、分句/合句、语序移位、定语从句转状语/独立句、正反译、被动转化。
  3. 隐喻决策 — 基本/图像图式隐喻(旅程、大小、冷热…)可直译;文化专属隐喻糅合或舍弃;直译≠应直译,看档位(reference/text-analysis-and-qa.md 小节 B)。

阶段 4 — 音韵节奏打磨

读出声。利用双音节/四字结构、“偶字易适奇字难平”、对偶排比;并列词组尽量配偶字(“飞机小,便宜”→“体积不大,造价便宜”)。但软文本才放开;硬文本点到为止。

阶段 5 — 准确性质检

对照 reference/text-analysis-and-qa.md 小节 C 逐项核:擅自改结构/移焦点、漏译情态虚词、擅自添词、搭配、指代、逻辑关系、专名术语数字、语域对齐。

红线:放松准确性 ≠ 理解错误。理解错误没有原谅的余地。

Read the full file on GitHub · 168 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 168 lines · 103 tokens per session scan A d7f607bebf85

Subscribe to this mod's changes

en-zh-translation-polish is a skill published in the GitHub repository HoraceLuBFA/en-zh-translation-polish (107 stars, last pushed 2d ago), licensed MIT. It adds 103 tokens to every session and 3,427 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.