Creator · HoraceLuBFA
Last updated · Sep 7, 2026
>-
Creator · HoraceLuBFA
Last updated · Sep 7, 2026
>-
Creator · HoraceLuBFA
Last updated · Sep 7, 2026
>-
Creator · HoraceLuBFA
Last updated · Sep 7, 2026
>-
Sandbox only
Install targets
Codex install prompt
Install the "en-zh-translation-polish" agent skill from https://github.com/HoraceLuBFA/en-zh-translation-polish/blob/main/SKILL.md. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: >- After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {"event_id":"install_<unique-id>","skill_slug":"horacelubfa-en-zh-translation-polish","task":"Install en-zh-translation-polish","agent":"codex","outcome":"success","install_used":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.Supply asset profile
Deep research, source comparison, literature review, RAG, knowledge search, and reports.
Scenario
RAG and knowledge
I need my agent to build a RAG workflow over documents and retrieve reliable context.
Agent fit
Claude Code + CLI + Codex
Codex, Claude Code, Cursor, CLI, or custom agents.
Install
Ready
npx skills add HoraceLuBFA/en-zh-translation-polish --skill en-zh-translation-polish
Maintenance
fresh
5d since push
Risk
Needs review
Quality score needs review
GitHub quality
106
71/100 Quality · 76/100 Trust
Coverage tags
Review notes
Quality score needs review · Stars/forks activity: 106 stars, 5 forks; issue activity unavailable in current metadata
Agent adoption scorecard
These scores combine public repository metadata, OpenAgentSkill review signals, maintenance freshness, and install readiness. They are a shortlist signal, not a replacement for human review.
Quality
StrongSolid option that is likely worth shortlisting for production workflows.
Trust
Sandbox onlyUseful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.
Audit
Needs reviewA machine-readable review of install readiness, security metadata, maintenance, and adoption risk.
OpenAgentSkill Trust Score v5
Run only in a sandbox and compare close alternatives before using it for real work.
Stars
106 GitHub stars
Repo activity
106 stars, 5 forks
Maintenance
5d since push
License
MIT
Install
npx skills add HoraceLuBFA/en-zh-translation-polish --skill en-zh-translation-polish
Install safety
Agent-readable metadata
Use this block or the embedded JSON to decide whether an agent should install this skill, choose an alternative, or ask for human review first.
Suited tasks
Suited agents
Install decision
Trust and risk
Outcome loop
Install command
npx skills add HoraceLuBFA/en-zh-translation-polish --skill en-zh-translation-polishDo not use when
Agent safety v2
Sparse or mixed signals. Useful for discovery, but not for autonomous installation.
Test manually in an isolated workspace and compare against safer alternatives.
high
Skill metadata references terminal, CLI, shell, subprocess, or command execution workflows.
medium
Skill likely fetches remote pages, APIs, repositories, or external services.
medium
Skill may read or write project files, documents, generated artifacts, or local workspace state.
Agent resolve plan
The Resolve API returns the selected skill, alternatives, safety policy, audit notes, install target, and copy-paste prompt an agent can follow without scraping this page.
Open JSON
/api/agent/resolve?task=Use%20en-zh-translation-polish%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Resolve text
/api/agent/resolve?task=Use%20en-zh-translation-polish%20for%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text
Install handoff
/api/skills/horacelubfa-en-zh-translation-polish/install
Agent should check
Copy prompt
Task: Use en-zh-translation-polish in this workspace.
Resolve first: https://www.openagentskill.com/api/agent/resolve?task=Use%20en-zh-translation-polish%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Review install handoff: https://www.openagentskill.com/api/skills/horacelubfa-en-zh-translation-polish/install
Install command: npx skills add HoraceLuBFA/en-zh-translation-polish --skill en-zh-translation-polish
Before running it, summarize audit warnings, required permissions, and the fallback skill if install is risky.Agent handoff
Use the public install endpoint to fetch the command, safety checklist, target prompts, and canonical links for this skill.
Install handoff
/api/skills/horacelubfa-en-zh-translation-polish/install
LLM text format
/api/skills/horacelubfa-en-zh-translation-polish/install?format=text
Find alternatives
/api/skills/search?q=en-zh-translation-polish&limit=3
Agent prompt
Use en-zh-translation-polish for this task. Review https://www.openagentskill.com/api/skills/horacelubfa-en-zh-translation-polish/install, then install with: npx skills add HoraceLuBFA/en-zh-translation-polish --skill en-zh-translation-polishRegistry metadata
This page exposes the same decision, trust, audit, use-case, and install signals through the Registry API, so agents can rank this skill without scraping the UI.
Manifest
/api/registry/manifest/horacelubfa-en-zh-translation-polish
LLM text
/api/registry/manifest/horacelubfa-en-zh-translation-polish?format=text
Install alias
/api/registry/install/horacelubfa-en-zh-translation-polish
Recommend
/api/registry/recommend?task=Use%20en-zh-translation-polish%20in%20an%20agent%20workflow&limit=3
Agent fit
Local desktop
Use-case tags
Platforms
Claude Code
Audit report
A machine-readable review of install readiness, security metadata, maintenance, and adoption risk.
Agent decision cockpit
Prototype with this skill first; keep a fallback candidate ready.
Role in stack
Fallback candidate
Primary fit
Local desktop
Trust label
Prototype first
Install path
Command ready
Use when
Evidence
review first
Implementation path
Trust profile
Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.
GitHub adoption
INFO106 GitHub stars
Stars/forks activity
CHECK106 stars, 5 forks; issue activity unavailable in current metadata
Recent maintenance
PASS5d since push
License clarity
PASSMIT
Good signals
Review before install
Recommended action
Run only in a sandbox and compare close alternatives before using it for real work.
Quality profile
Solid option that is likely worth shortlisting for production workflows.
Workflow fit
Operate local tools
I need my agent to operate local files and desktop apps in a repeatable workflow.
Search private knowledge
I need my agent to build a RAG workflow over documents and retrieve reliable context.
Investigate faster
I need my agent to research a topic, compare sources, and produce a concise report.
Workflow fit
Ingest, retrieve, and cite
A workflow for document-heavy agents that ingest files, create searchable knowledge, retrieve relevant context, and answer with grounded sources.
Find, compare, and synthesize
A workflow for agents that gather sources, compare claims, summarize long material, and draft useful research briefs.
Turn skills into distribution
A workflow for turning newly indexed skills into SEO briefs, social drafts, comparison pages, and reusable publishing workflows.
Alternative shortlist
Similar skills that may fit this task.
Run multimodal agents that operate desktop interfaces
Connect agents to hundreds of workflow automations
利用AI大模型,一键生成高清短视频 Generate short videos with one click using AI LLM.
Alternative firmware for ESP8266 and ESP32 based devices with easy configuration using webUI, OTA updates, automation using timers or rules, expandability and entirely local control over MQTT, HTTP, Serial or KNX. Full documentation at
--- name: en-zh-translation-polish description: >- Translates English into idiomatic, translationese-free Chinese, optionally as an English-Chinese bilingual version pairing each source paragraph with its translation. Use when the user wants to 翻译成中文 / 英译汉, 去翻译腔/润色译文 (remove translationese, polish a draft), or produce a 中英对照/英中对照 bilingual rendering. Not for Chinese-to-English, pure Chinese writing polish, or single-word lookups. license: MIT version: 1.0.0 tags: [translation, chinese, english-to-chinese, 英译汉, 润色, 中英对照, localization] allowed-tools: Read Write Edit Bash ---
# 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。 ```bash 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 以**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。
### 阶段 6 — 中文标点规范化 ★(机械执行,落盘后必跑) 中文译文里的标点必须是中文全角,不能残留英文半角(译者最易忽略,逐字凭眼力一定会漏)。规则: - `, : ; ? !` → `,:;?!`;句末用 `。`;并列用顿号 `、`;破折号 `——`;省略号 `……`。 - 圆括号 `( )` → 全角 `( )`:**仅当紧邻中文字符时才转**(包裹中文内容、含人名/术语原文注,如 "道德受体地位(moral patienthood)");纯英文括注(如电影演职 `(Harold D. Schuster, 1937)`)保持半角。 - 双引号统一为中文全角 `" "`(内层 `' '`);直角引号 `「」`、`『』` 一并归一为 `" "` / `' '`。
**以下一律保持半角,绝不转:** ① 英文原文 blockquote(`> ` 行)整段不动;② Markdown 链接 `[文字](url)` 的括号与 URL;③ 中文行内嵌入的整句/词组英文,其内部标点——如被引用的英文原句 `…one nation under God, indivisible, …`;④ 数字/缩写/版本号里的点:`4.3`、`Word 2010`、`A.I.`、`L. M.`;⑤ 代码/公式块。
判定原理:**逗号类与圆括号都只在紧邻中文字符(前或后)时才转**;有方向的引号(“”「」‘’『』)按方向直接映射,只有歧义的直双引号 `"` 才靠交替判定开闭。落盘后跑下面脚本机械归一并自检(`残留` 必须为 0):
```bash python3 - "<名称> 翻译(中英对照).md" <<'PY' import re, sys src = sys.argv[1] lines = open(src, encoding='utf-8').read().split('\n') CJK_EXTRA = set('“”‘’·—…《》〈〉「」『』【】、。,!?;:()') def is_cjk(c): if not c: return False o = ord(c) return (0x3400<=o<=0x9fff) or (0x3000<=o<=0x303f) or (0xff00<=o<=0xffef) or (c in CJK_EXTRA) SMAP = {',':',', ';':';', ':':':', '?':'?', '!':'!', '(':'(', ')':')'} OPEN2 = '“「'; CLOSE2 = '”」'; OPEN1 = '‘『'; CLOSE1 = '’』' LINK = re.compile(r'\[[^\]]*\]\([^)]*\)') def fix(line): store=[] line = LINK.sub(lambda m: store.append(m.group(0)) or '\x00%d\x00'%(len(store)-1), line) out=[]; sop=True # 有方向引号直接映射; 仅歧义直双引号 " 靠交替定开闭 for c in line: if c == '"': out.append('“' if sop else '”'); sop = not sop elif c in OPEN2: out.append('“') elif c in CLOSE2: out.append('”') elif c in OPEN1: out.append('‘') elif c in CLOSE1: out.append('’') else: out.append(c) ch=out; n=len(ch) for i,c in enumerate(ch): # 逗号类 + 圆括号: 紧邻中文才转全角 if c in SMAP and (is_cjk(ch[i-1] if i else '') or is_cjk(ch[i+1] if i+1<n else '')): ch[i]=SMAP[c] line=''.join(ch) return re.sub('\x00(\\d+)\x00', lambda m: store[int(m.group(1))], line) def skip(ln): s=ln.strip(); return s=='' or ln.lstrip().startswith('>') or s=='---' res=[ln if skip(ln) else fix(ln) for ln in lines] open(src,'w',encoding='utf-8').write('\n'.join(res)) def residual(ln): t = LINK.sub('', ln) # 排除 markdown 链接内的括号/标点, 免误报 return sum(1 for m in re.finditer(r'[,;:?!()]', t) if is_cjk(t[m.start()-1] if m.start() else '') or is_cjk(t[m.start()+1] if m.start()+1<len(t) else '')) bad=sum(residual(ln) for ln in res if not skip(ln)) print('残留:', bad) PY ``` 聊天里直接给的小段对照(未落盘)同样要手动套用上述规则。
### 阶段 7 — 输出英中对照 按下方格式逐段配对;成篇则写文件;给用户附一句“档位判定 + 主要润色取舍”。
## 英中对照输出格式
**按段落配对**:英文原段作为 blockquote,紧接中文译文。
```markdown > It is a truth universally acknowledged that a single man in possession of a > good fortune must be in want of a wife.
凡是有钱的单身汉,总想娶位太太,这是一条举世公认的真理。 ```
规则: - 中文译文用中文全角标点;半角标点只留给英文原文、链接、行内英文词句、数字缩写、代码(详见阶段 6,落盘后用脚本自检)。 - 只清理提取噪声(接回断行连字符、删页眉页脚页码),**不要**从中文反推英文。 - 标题作中文 `##`/`###`,不加 blockquote;可选地把英文标题作为上一行 blockquote。 - 不该被脚本删掉、需保留进全中文版的东西(图片、表格、标题块)**不要** blockquote。 - 公式/代码用共享代码块,不按语言重复。
## 润色边界 ★(防止方法论被用过头)
叶子南本人警告的两个反模式,务必守住: - **不要过度归化**:别为了“地道”抹掉原文该保留的风格、术语精度、文化标记。西化是一个**连续体**,可接受度随文本价值变化——硬文本/永久价值文本能容纳更多异化(见 `reference/translationese-symptoms.md` 第七节)。 - **不要堆砌四字成语**:音韵节奏是手段不是目的,为文字而文字会显得卖弄、失真。 - 拿不准“该改到多狠”时,回到阶段 0 的档位:**自由度越低,越克制**。
## 示例
输入(英文):
``` The confidence that the West would remain a dominant force in the 21st century is giving way to a sense of foreboding. ```
输出(英中对照;阶段 0 判定:偏硬/政论,自由度≈3,准确优先、克制音韵):
> The confidence that the West would remain a dominant force in the 21st century is giving way to a sense of foreboding.
西方曾笃信自己将在 21 世纪稳居主导地位,如今这份自信,正让位于一种隐隐的不祥之感。
## 致谢与许可
本 skill 的代码、提示词与组织方式以 **MIT 许可**发布,可自由使用、修改、再分发。
方法论与判例蒸馏、转述自叶子南《高级英汉翻译理论与实践》(第4版,清华大学出版社,2020),在此谨致谢忱。`reference/` 三张表中的少量引文系评注与教学目的的简短摘引,著作权归原作者与出版社所有;本 skill 仅为方法工具,不能替代原著,建议系统学习者购买正版。
Source provenance
Decision snapshot
recent repository activity
Audit
Install and adoption review
Agent-proven evidence
Outcome reports after resolve, review, install, and one narrow run.
No agent outcome data yet. The first agent run can report success, setup needs, risk blocks, failure, or not-relevant through /api/agent/outcome.
Install
Free and open source. Review the report before installing into production agents.
Growth loop
Scenario-led draft for en-zh-translation-polish, ready for a manual X post.
For a repeatable workflow, this is a skill worth shortlisting before another blank prompt. en-zh-translation-polish: >- 106 stars https://www.openagentskill.com/skills/horacelubfa-en-zh-translation-polish?ref=x
Listing + install path for en-zh-translation-polish: https://www.openagentskill.com/skills/horacelubfa-en-zh-translation-polish?ref=x Install: npx skills add HoraceLuBFA/en-zh-translation-polish --skill en-zh-translation-polish
Listing source
This listing was indexed from public sources and is not marked official until a maintainer claim is approved.
Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals.
Claim this skillOwner claim
This Registry indexed listing is attributed to HoraceLuBFA but is not marked official yet. Claim it to add a verified owner signal and make future launch, install, and audit updates easier to trust.
Creator backlink kit
Show the canonical listing, current trust and audit signals, and real Agent-Proven evidence where developers evaluate the repository.
[](https://www.openagentskill.com/skills/horacelubfa-en-zh-translation-polish?ref=github&utm_source=github&utm_medium=referral&utm_campaign=creator_badge)
[](https://www.openagentskill.com/skills/horacelubfa-en-zh-translation-polish?ref=github&utm_source=github&utm_medium=referral&utm_campaign=creator_badge)
[](https://www.openagentskill.com/skills/horacelubfa-en-zh-translation-polish/audit)
[](https://www.openagentskill.com/skills/horacelubfa-en-zh-translation-polish?ref=github&utm_source=github&utm_medium=referral&utm_campaign=creator_badge)HoraceLuBFA
@horacelubfa
Share whether this skill looks useful for your agent workflow. Aggregated feedback improves rankings over time.
Sandbox only
UI-TARS Desktop
Run multimodal agents that operate desktop interfaces
37.0K Starsn8n
Connect agents to hundreds of workflow automations
194.1K StarsMoneyPrinterTurbo
利用AI大模型,一键生成高清短视频 Generate short videos with one click using AI LLM.
88.5K StarsTasmota
Alternative firmware for ESP8266 and ESP32 based devices with easy configuration using webUI, OTA updates, automation using timers or rules, expandability and entirely local control over MQTT, HTTP, Serial or KNX. Full documentation at
24.7K StarsSandbox only
Install targets
Codex install prompt
Install the "en-zh-translation-polish" agent skill from https://github.com/HoraceLuBFA/en-zh-translation-polish/blob/main/SKILL.md. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: >- After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {"event_id":"install_<unique-id>","skill_slug":"horacelubfa-en-zh-translation-polish","task":"Install en-zh-translation-polish","agent":"codex","outcome":"success","install_used":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.Supply asset profile
Deep research, source comparison, literature review, RAG, knowledge search, and reports.
Scenario
RAG and knowledge
I need my agent to build a RAG workflow over documents and retrieve reliable context.
Agent fit
Claude Code + CLI + Codex
Codex, Claude Code, Cursor, CLI, or custom agents.
Install
Ready
npx skills add HoraceLuBFA/en-zh-translation-polish --skill en-zh-translation-polish
Maintenance
fresh
5d since push
Risk
Needs review
Quality score needs review
GitHub quality
106
71/100 Quality · 76/100 Trust
Coverage tags
Review notes
Quality score needs review · Stars/forks activity: 106 stars, 5 forks; issue activity unavailable in current metadata
Agent adoption scorecard
These scores combine public repository metadata, OpenAgentSkill review signals, maintenance freshness, and install readiness. They are a shortlist signal, not a replacement for human review.
Quality
StrongSolid option that is likely worth shortlisting for production workflows.
Trust
Sandbox onlyUseful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.
Audit
Needs reviewA machine-readable review of install readiness, security metadata, maintenance, and adoption risk.
OpenAgentSkill Trust Score v5
Run only in a sandbox and compare close alternatives before using it for real work.
Stars
106 GitHub stars
Repo activity
106 stars, 5 forks
Maintenance
5d since push
License
MIT
Install
npx skills add HoraceLuBFA/en-zh-translation-polish --skill en-zh-translation-polish
Install safety
Agent-readable metadata
Use this block or the embedded JSON to decide whether an agent should install this skill, choose an alternative, or ask for human review first.
Suited tasks
Suited agents
Install decision
Trust and risk
Outcome loop
Install command
npx skills add HoraceLuBFA/en-zh-translation-polish --skill en-zh-translation-polishDo not use when
Agent safety v2
Sparse or mixed signals. Useful for discovery, but not for autonomous installation.
Test manually in an isolated workspace and compare against safer alternatives.
high
Skill metadata references terminal, CLI, shell, subprocess, or command execution workflows.
medium
Skill likely fetches remote pages, APIs, repositories, or external services.
medium
Skill may read or write project files, documents, generated artifacts, or local workspace state.
Agent resolve plan
The Resolve API returns the selected skill, alternatives, safety policy, audit notes, install target, and copy-paste prompt an agent can follow without scraping this page.
Open JSON
/api/agent/resolve?task=Use%20en-zh-translation-polish%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Resolve text
/api/agent/resolve?task=Use%20en-zh-translation-polish%20for%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text
Install handoff
/api/skills/horacelubfa-en-zh-translation-polish/install
Agent should check
Copy prompt
Task: Use en-zh-translation-polish in this workspace.
Resolve first: https://www.openagentskill.com/api/agent/resolve?task=Use%20en-zh-translation-polish%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Review install handoff: https://www.openagentskill.com/api/skills/horacelubfa-en-zh-translation-polish/install
Install command: npx skills add HoraceLuBFA/en-zh-translation-polish --skill en-zh-translation-polish
Before running it, summarize audit warnings, required permissions, and the fallback skill if install is risky.Agent handoff
Use the public install endpoint to fetch the command, safety checklist, target prompts, and canonical links for this skill.
Install handoff
/api/skills/horacelubfa-en-zh-translation-polish/install
LLM text format
/api/skills/horacelubfa-en-zh-translation-polish/install?format=text
Find alternatives
/api/skills/search?q=en-zh-translation-polish&limit=3
Agent prompt
Use en-zh-translation-polish for this task. Review https://www.openagentskill.com/api/skills/horacelubfa-en-zh-translation-polish/install, then install with: npx skills add HoraceLuBFA/en-zh-translation-polish --skill en-zh-translation-polishRegistry metadata
This page exposes the same decision, trust, audit, use-case, and install signals through the Registry API, so agents can rank this skill without scraping the UI.
Manifest
/api/registry/manifest/horacelubfa-en-zh-translation-polish
LLM text
/api/registry/manifest/horacelubfa-en-zh-translation-polish?format=text
Install alias
/api/registry/install/horacelubfa-en-zh-translation-polish
Recommend
/api/registry/recommend?task=Use%20en-zh-translation-polish%20in%20an%20agent%20workflow&limit=3
Agent fit
Local desktop
Use-case tags
Platforms
Claude Code
Audit report
A machine-readable review of install readiness, security metadata, maintenance, and adoption risk.
Agent decision cockpit
Prototype with this skill first; keep a fallback candidate ready.
Role in stack
Fallback candidate
Primary fit
Local desktop
Trust label
Prototype first
Install path
Command ready
Use when
Evidence
review first
Implementation path
Trust profile
Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.
GitHub adoption
INFO106 GitHub stars
Stars/forks activity
CHECK106 stars, 5 forks; issue activity unavailable in current metadata
Recent maintenance
PASS5d since push
License clarity
PASSMIT
Good signals
Review before install
Recommended action
Run only in a sandbox and compare close alternatives before using it for real work.
Quality profile
Solid option that is likely worth shortlisting for production workflows.
Workflow fit
Operate local tools
I need my agent to operate local files and desktop apps in a repeatable workflow.
Search private knowledge
I need my agent to build a RAG workflow over documents and retrieve reliable context.
Investigate faster
I need my agent to research a topic, compare sources, and produce a concise report.
Workflow fit
Ingest, retrieve, and cite
A workflow for document-heavy agents that ingest files, create searchable knowledge, retrieve relevant context, and answer with grounded sources.
Find, compare, and synthesize
A workflow for agents that gather sources, compare claims, summarize long material, and draft useful research briefs.
Turn skills into distribution
A workflow for turning newly indexed skills into SEO briefs, social drafts, comparison pages, and reusable publishing workflows.
Alternative shortlist
Similar skills that may fit this task.
Run multimodal agents that operate desktop interfaces
Connect agents to hundreds of workflow automations
利用AI大模型,一键生成高清短视频 Generate short videos with one click using AI LLM.
Alternative firmware for ESP8266 and ESP32 based devices with easy configuration using webUI, OTA updates, automation using timers or rules, expandability and entirely local control over MQTT, HTTP, Serial or KNX. Full documentation at
--- name: en-zh-translation-polish description: >- Translates English into idiomatic, translationese-free Chinese, optionally as an English-Chinese bilingual version pairing each source paragraph with its translation. Use when the user wants to 翻译成中文 / 英译汉, 去翻译腔/润色译文 (remove translationese, polish a draft), or produce a 中英对照/英中对照 bilingual rendering. Not for Chinese-to-English, pure Chinese writing polish, or single-word lookups. license: MIT version: 1.0.0 tags: [translation, chinese, english-to-chinese, 英译汉, 润色, 中英对照, localization] allowed-tools: Read Write Edit Bash ---
# 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。 ```bash 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 以**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。
### 阶段 6 — 中文标点规范化 ★(机械执行,落盘后必跑) 中文译文里的标点必须是中文全角,不能残留英文半角(译者最易忽略,逐字凭眼力一定会漏)。规则: - `, : ; ? !` → `,:;?!`;句末用 `。`;并列用顿号 `、`;破折号 `——`;省略号 `……`。 - 圆括号 `( )` → 全角 `( )`:**仅当紧邻中文字符时才转**(包裹中文内容、含人名/术语原文注,如 "道德受体地位(moral patienthood)");纯英文括注(如电影演职 `(Harold D. Schuster, 1937)`)保持半角。 - 双引号统一为中文全角 `" "`(内层 `' '`);直角引号 `「」`、`『』` 一并归一为 `" "` / `' '`。
**以下一律保持半角,绝不转:** ① 英文原文 blockquote(`> ` 行)整段不动;② Markdown 链接 `[文字](url)` 的括号与 URL;③ 中文行内嵌入的整句/词组英文,其内部标点——如被引用的英文原句 `…one nation under God, indivisible, …`;④ 数字/缩写/版本号里的点:`4.3`、`Word 2010`、`A.I.`、`L. M.`;⑤ 代码/公式块。
判定原理:**逗号类与圆括号都只在紧邻中文字符(前或后)时才转**;有方向的引号(“”「」‘’『』)按方向直接映射,只有歧义的直双引号 `"` 才靠交替判定开闭。落盘后跑下面脚本机械归一并自检(`残留` 必须为 0):
```bash python3 - "<名称> 翻译(中英对照).md" <<'PY' import re, sys src = sys.argv[1] lines = open(src, encoding='utf-8').read().split('\n') CJK_EXTRA = set('“”‘’·—…《》〈〉「」『』【】、。,!?;:()') def is_cjk(c): if not c: return False o = ord(c) return (0x3400<=o<=0x9fff) or (0x3000<=o<=0x303f) or (0xff00<=o<=0xffef) or (c in CJK_EXTRA) SMAP = {',':',', ';':';', ':':':', '?':'?', '!':'!', '(':'(', ')':')'} OPEN2 = '“「'; CLOSE2 = '”」'; OPEN1 = '‘『'; CLOSE1 = '’』' LINK = re.compile(r'\[[^\]]*\]\([^)]*\)') def fix(line): store=[] line = LINK.sub(lambda m: store.append(m.group(0)) or '\x00%d\x00'%(len(store)-1), line) out=[]; sop=True # 有方向引号直接映射; 仅歧义直双引号 " 靠交替定开闭 for c in line: if c == '"': out.append('“' if sop else '”'); sop = not sop elif c in OPEN2: out.append('“') elif c in CLOSE2: out.append('”') elif c in OPEN1: out.append('‘') elif c in CLOSE1: out.append('’') else: out.append(c) ch=out; n=len(ch) for i,c in enumerate(ch): # 逗号类 + 圆括号: 紧邻中文才转全角 if c in SMAP and (is_cjk(ch[i-1] if i else '') or is_cjk(ch[i+1] if i+1<n else '')): ch[i]=SMAP[c] line=''.join(ch) return re.sub('\x00(\\d+)\x00', lambda m: store[int(m.group(1))], line) def skip(ln): s=ln.strip(); return s=='' or ln.lstrip().startswith('>') or s=='---' res=[ln if skip(ln) else fix(ln) for ln in lines] open(src,'w',encoding='utf-8').write('\n'.join(res)) def residual(ln): t = LINK.sub('', ln) # 排除 markdown 链接内的括号/标点, 免误报 return sum(1 for m in re.finditer(r'[,;:?!()]', t) if is_cjk(t[m.start()-1] if m.start() else '') or is_cjk(t[m.start()+1] if m.start()+1<len(t) else '')) bad=sum(residual(ln) for ln in res if not skip(ln)) print('残留:', bad) PY ``` 聊天里直接给的小段对照(未落盘)同样要手动套用上述规则。
### 阶段 7 — 输出英中对照 按下方格式逐段配对;成篇则写文件;给用户附一句“档位判定 + 主要润色取舍”。
## 英中对照输出格式
**按段落配对**:英文原段作为 blockquote,紧接中文译文。
```markdown > It is a truth universally acknowledged that a single man in possession of a > good fortune must be in want of a wife.
凡是有钱的单身汉,总想娶位太太,这是一条举世公认的真理。 ```
规则: - 中文译文用中文全角标点;半角标点只留给英文原文、链接、行内英文词句、数字缩写、代码(详见阶段 6,落盘后用脚本自检)。 - 只清理提取噪声(接回断行连字符、删页眉页脚页码),**不要**从中文反推英文。 - 标题作中文 `##`/`###`,不加 blockquote;可选地把英文标题作为上一行 blockquote。 - 不该被脚本删掉、需保留进全中文版的东西(图片、表格、标题块)**不要** blockquote。 - 公式/代码用共享代码块,不按语言重复。
## 润色边界 ★(防止方法论被用过头)
叶子南本人警告的两个反模式,务必守住: - **不要过度归化**:别为了“地道”抹掉原文该保留的风格、术语精度、文化标记。西化是一个**连续体**,可接受度随文本价值变化——硬文本/永久价值文本能容纳更多异化(见 `reference/translationese-symptoms.md` 第七节)。 - **不要堆砌四字成语**:音韵节奏是手段不是目的,为文字而文字会显得卖弄、失真。 - 拿不准“该改到多狠”时,回到阶段 0 的档位:**自由度越低,越克制**。
## 示例
输入(英文):
``` The confidence that the West would remain a dominant force in the 21st century is giving way to a sense of foreboding. ```
输出(英中对照;阶段 0 判定:偏硬/政论,自由度≈3,准确优先、克制音韵):
> The confidence that the West would remain a dominant force in the 21st century is giving way to a sense of foreboding.
西方曾笃信自己将在 21 世纪稳居主导地位,如今这份自信,正让位于一种隐隐的不祥之感。
## 致谢与许可
本 skill 的代码、提示词与组织方式以 **MIT 许可**发布,可自由使用、修改、再分发。
方法论与判例蒸馏、转述自叶子南《高级英汉翻译理论与实践》(第4版,清华大学出版社,2020),在此谨致谢忱。`reference/` 三张表中的少量引文系评注与教学目的的简短摘引,著作权归原作者与出版社所有;本 skill 仅为方法工具,不能替代原著,建议系统学习者购买正版。
Source provenance
Decision snapshot
recent repository activity
Audit
Install and adoption review
Agent-proven evidence
Outcome reports after resolve, review, install, and one narrow run.
No agent outcome data yet. The first agent run can report success, setup needs, risk blocks, failure, or not-relevant through /api/agent/outcome.
Install
Free and open source. Review the report before installing into production agents.
Growth loop
Scenario-led draft for en-zh-translation-polish, ready for a manual X post.
For a repeatable workflow, this is a skill worth shortlisting before another blank prompt. en-zh-translation-polish: >- 106 stars https://www.openagentskill.com/skills/horacelubfa-en-zh-translation-polish?ref=x
Listing + install path for en-zh-translation-polish: https://www.openagentskill.com/skills/horacelubfa-en-zh-translation-polish?ref=x Install: npx skills add HoraceLuBFA/en-zh-translation-polish --skill en-zh-translation-polish
Listing source
This listing was indexed from public sources and is not marked official until a maintainer claim is approved.
Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals.
Claim this skillOwner claim
This Registry indexed listing is attributed to HoraceLuBFA but is not marked official yet. Claim it to add a verified owner signal and make future launch, install, and audit updates easier to trust.
Creator backlink kit
Show the canonical listing, current trust and audit signals, and real Agent-Proven evidence where developers evaluate the repository.
[](https://www.openagentskill.com/skills/horacelubfa-en-zh-translation-polish?ref=github&utm_source=github&utm_medium=referral&utm_campaign=creator_badge)
[](https://www.openagentskill.com/skills/horacelubfa-en-zh-translation-polish?ref=github&utm_source=github&utm_medium=referral&utm_campaign=creator_badge)
[](https://www.openagentskill.com/skills/horacelubfa-en-zh-translation-polish/audit)
[](https://www.openagentskill.com/skills/horacelubfa-en-zh-translation-polish?ref=github&utm_source=github&utm_medium=referral&utm_campaign=creator_badge)HoraceLuBFA
@horacelubfa
Share whether this skill looks useful for your agent workflow. Aggregated feedback improves rankings over time.
Sandbox only
UI-TARS Desktop
Run multimodal agents that operate desktop interfaces
37.0K Starsn8n
Connect agents to hundreds of workflow automations
194.1K StarsMoneyPrinterTurbo
利用AI大模型,一键生成高清短视频 Generate short videos with one click using AI LLM.
88.5K StarsTasmota
Alternative firmware for ESP8266 and ESP32 based devices with easy configuration using webUI, OTA updates, automation using timers or rules, expandability and entirely local control over MQTT, HTTP, Serial or KNX. Full documentation at
24.7K StarsSandbox only
Install targets
Codex install prompt
Install the "en-zh-translation-polish" agent skill from https://github.com/HoraceLuBFA/en-zh-translation-polish/blob/main/SKILL.md. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: >- After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {"event_id":"install_<unique-id>","skill_slug":"horacelubfa-en-zh-translation-polish","task":"Install en-zh-translation-polish","agent":"codex","outcome":"success","install_used":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.Supply asset profile
Deep research, source comparison, literature review, RAG, knowledge search, and reports.
Scenario
RAG and knowledge
I need my agent to build a RAG workflow over documents and retrieve reliable context.
Agent fit
Claude Code + CLI + Codex
Codex, Claude Code, Cursor, CLI, or custom agents.
Install
Ready
npx skills add HoraceLuBFA/en-zh-translation-polish --skill en-zh-translation-polish
Maintenance
fresh
5d since push
Risk
Needs review
Quality score needs review
GitHub quality
106
71/100 Quality · 76/100 Trust
Coverage tags
Review notes
Quality score needs review · Stars/forks activity: 106 stars, 5 forks; issue activity unavailable in current metadata
Agent adoption scorecard
These scores combine public repository metadata, OpenAgentSkill review signals, maintenance freshness, and install readiness. They are a shortlist signal, not a replacement for human review.
Quality
StrongSolid option that is likely worth shortlisting for production workflows.
Trust
Sandbox onlyUseful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.
Audit
Needs reviewA machine-readable review of install readiness, security metadata, maintenance, and adoption risk.
OpenAgentSkill Trust Score v5
Run only in a sandbox and compare close alternatives before using it for real work.
Stars
106 GitHub stars
Repo activity
106 stars, 5 forks
Maintenance
5d since push
License
MIT
Install
npx skills add HoraceLuBFA/en-zh-translation-polish --skill en-zh-translation-polish
Install safety
Agent-readable metadata
Use this block or the embedded JSON to decide whether an agent should install this skill, choose an alternative, or ask for human review first.
Suited tasks
Suited agents
Install decision
Trust and risk
Outcome loop
Install command
npx skills add HoraceLuBFA/en-zh-translation-polish --skill en-zh-translation-polishDo not use when
Agent safety v2
Sparse or mixed signals. Useful for discovery, but not for autonomous installation.
Test manually in an isolated workspace and compare against safer alternatives.
high
Skill metadata references terminal, CLI, shell, subprocess, or command execution workflows.
medium
Skill likely fetches remote pages, APIs, repositories, or external services.
medium
Skill may read or write project files, documents, generated artifacts, or local workspace state.
Agent resolve plan
The Resolve API returns the selected skill, alternatives, safety policy, audit notes, install target, and copy-paste prompt an agent can follow without scraping this page.
Open JSON
/api/agent/resolve?task=Use%20en-zh-translation-polish%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Resolve text
/api/agent/resolve?task=Use%20en-zh-translation-polish%20for%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text
Install handoff
/api/skills/horacelubfa-en-zh-translation-polish/install
Agent should check
Copy prompt
Task: Use en-zh-translation-polish in this workspace.
Resolve first: https://www.openagentskill.com/api/agent/resolve?task=Use%20en-zh-translation-polish%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Review install handoff: https://www.openagentskill.com/api/skills/horacelubfa-en-zh-translation-polish/install
Install command: npx skills add HoraceLuBFA/en-zh-translation-polish --skill en-zh-translation-polish
Before running it, summarize audit warnings, required permissions, and the fallback skill if install is risky.Agent handoff
Use the public install endpoint to fetch the command, safety checklist, target prompts, and canonical links for this skill.
Install handoff
/api/skills/horacelubfa-en-zh-translation-polish/install
LLM text format
/api/skills/horacelubfa-en-zh-translation-polish/install?format=text
Find alternatives
/api/skills/search?q=en-zh-translation-polish&limit=3
Agent prompt
Use en-zh-translation-polish for this task. Review https://www.openagentskill.com/api/skills/horacelubfa-en-zh-translation-polish/install, then install with: npx skills add HoraceLuBFA/en-zh-translation-polish --skill en-zh-translation-polishRegistry metadata
This page exposes the same decision, trust, audit, use-case, and install signals through the Registry API, so agents can rank this skill without scraping the UI.
Manifest
/api/registry/manifest/horacelubfa-en-zh-translation-polish
LLM text
/api/registry/manifest/horacelubfa-en-zh-translation-polish?format=text
Install alias
/api/registry/install/horacelubfa-en-zh-translation-polish
Recommend
/api/registry/recommend?task=Use%20en-zh-translation-polish%20in%20an%20agent%20workflow&limit=3
Agent fit
Local desktop
Use-case tags
Platforms
Claude Code
Audit report
A machine-readable review of install readiness, security metadata, maintenance, and adoption risk.
Agent decision cockpit
Prototype with this skill first; keep a fallback candidate ready.
Role in stack
Fallback candidate
Primary fit
Local desktop
Trust label
Prototype first
Install path
Command ready
Use when
Evidence
review first
Implementation path
Trust profile
Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.
GitHub adoption
INFO106 GitHub stars
Stars/forks activity
CHECK106 stars, 5 forks; issue activity unavailable in current metadata
Recent maintenance
PASS5d since push
License clarity
PASSMIT
Good signals
Review before install
Recommended action
Run only in a sandbox and compare close alternatives before using it for real work.
Quality profile
Solid option that is likely worth shortlisting for production workflows.
Workflow fit
Operate local tools
I need my agent to operate local files and desktop apps in a repeatable workflow.
Search private knowledge
I need my agent to build a RAG workflow over documents and retrieve reliable context.
Investigate faster
I need my agent to research a topic, compare sources, and produce a concise report.
Workflow fit
Ingest, retrieve, and cite
A workflow for document-heavy agents that ingest files, create searchable knowledge, retrieve relevant context, and answer with grounded sources.
Find, compare, and synthesize
A workflow for agents that gather sources, compare claims, summarize long material, and draft useful research briefs.
Turn skills into distribution
A workflow for turning newly indexed skills into SEO briefs, social drafts, comparison pages, and reusable publishing workflows.
Alternative shortlist
Similar skills that may fit this task.
Run multimodal agents that operate desktop interfaces
Connect agents to hundreds of workflow automations
利用AI大模型,一键生成高清短视频 Generate short videos with one click using AI LLM.
Alternative firmware for ESP8266 and ESP32 based devices with easy configuration using webUI, OTA updates, automation using timers or rules, expandability and entirely local control over MQTT, HTTP, Serial or KNX. Full documentation at
--- name: en-zh-translation-polish description: >- Translates English into idiomatic, translationese-free Chinese, optionally as an English-Chinese bilingual version pairing each source paragraph with its translation. Use when the user wants to 翻译成中文 / 英译汉, 去翻译腔/润色译文 (remove translationese, polish a draft), or produce a 中英对照/英中对照 bilingual rendering. Not for Chinese-to-English, pure Chinese writing polish, or single-word lookups. license: MIT version: 1.0.0 tags: [translation, chinese, english-to-chinese, 英译汉, 润色, 中英对照, localization] allowed-tools: Read Write Edit Bash ---
# 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。 ```bash 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 以**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。
### 阶段 6 — 中文标点规范化 ★(机械执行,落盘后必跑) 中文译文里的标点必须是中文全角,不能残留英文半角(译者最易忽略,逐字凭眼力一定会漏)。规则: - `, : ; ? !` → `,:;?!`;句末用 `。`;并列用顿号 `、`;破折号 `——`;省略号 `……`。 - 圆括号 `( )` → 全角 `( )`:**仅当紧邻中文字符时才转**(包裹中文内容、含人名/术语原文注,如 "道德受体地位(moral patienthood)");纯英文括注(如电影演职 `(Harold D. Schuster, 1937)`)保持半角。 - 双引号统一为中文全角 `" "`(内层 `' '`);直角引号 `「」`、`『』` 一并归一为 `" "` / `' '`。
**以下一律保持半角,绝不转:** ① 英文原文 blockquote(`> ` 行)整段不动;② Markdown 链接 `[文字](url)` 的括号与 URL;③ 中文行内嵌入的整句/词组英文,其内部标点——如被引用的英文原句 `…one nation under God, indivisible, …`;④ 数字/缩写/版本号里的点:`4.3`、`Word 2010`、`A.I.`、`L. M.`;⑤ 代码/公式块。
判定原理:**逗号类与圆括号都只在紧邻中文字符(前或后)时才转**;有方向的引号(“”「」‘’『』)按方向直接映射,只有歧义的直双引号 `"` 才靠交替判定开闭。落盘后跑下面脚本机械归一并自检(`残留` 必须为 0):
```bash python3 - "<名称> 翻译(中英对照).md" <<'PY' import re, sys src = sys.argv[1] lines = open(src, encoding='utf-8').read().split('\n') CJK_EXTRA = set('“”‘’·—…《》〈〉「」『』【】、。,!?;:()') def is_cjk(c): if not c: return False o = ord(c) return (0x3400<=o<=0x9fff) or (0x3000<=o<=0x303f) or (0xff00<=o<=0xffef) or (c in CJK_EXTRA) SMAP = {',':',', ';':';', ':':':', '?':'?', '!':'!', '(':'(', ')':')'} OPEN2 = '“「'; CLOSE2 = '”」'; OPEN1 = '‘『'; CLOSE1 = '’』' LINK = re.compile(r'\[[^\]]*\]\([^)]*\)') def fix(line): store=[] line = LINK.sub(lambda m: store.append(m.group(0)) or '\x00%d\x00'%(len(store)-1), line) out=[]; sop=True # 有方向引号直接映射; 仅歧义直双引号 " 靠交替定开闭 for c in line: if c == '"': out.append('“' if sop else '”'); sop = not sop elif c in OPEN2: out.append('“') elif c in CLOSE2: out.append('”') elif c in OPEN1: out.append('‘') elif c in CLOSE1: out.append('’') else: out.append(c) ch=out; n=len(ch) for i,c in enumerate(ch): # 逗号类 + 圆括号: 紧邻中文才转全角 if c in SMAP and (is_cjk(ch[i-1] if i else '') or is_cjk(ch[i+1] if i+1<n else '')): ch[i]=SMAP[c] line=''.join(ch) return re.sub('\x00(\\d+)\x00', lambda m: store[int(m.group(1))], line) def skip(ln): s=ln.strip(); return s=='' or ln.lstrip().startswith('>') or s=='---' res=[ln if skip(ln) else fix(ln) for ln in lines] open(src,'w',encoding='utf-8').write('\n'.join(res)) def residual(ln): t = LINK.sub('', ln) # 排除 markdown 链接内的括号/标点, 免误报 return sum(1 for m in re.finditer(r'[,;:?!()]', t) if is_cjk(t[m.start()-1] if m.start() else '') or is_cjk(t[m.start()+1] if m.start()+1<len(t) else '')) bad=sum(residual(ln) for ln in res if not skip(ln)) print('残留:', bad) PY ``` 聊天里直接给的小段对照(未落盘)同样要手动套用上述规则。
### 阶段 7 — 输出英中对照 按下方格式逐段配对;成篇则写文件;给用户附一句“档位判定 + 主要润色取舍”。
## 英中对照输出格式
**按段落配对**:英文原段作为 blockquote,紧接中文译文。
```markdown > It is a truth universally acknowledged that a single man in possession of a > good fortune must be in want of a wife.
凡是有钱的单身汉,总想娶位太太,这是一条举世公认的真理。 ```
规则: - 中文译文用中文全角标点;半角标点只留给英文原文、链接、行内英文词句、数字缩写、代码(详见阶段 6,落盘后用脚本自检)。 - 只清理提取噪声(接回断行连字符、删页眉页脚页码),**不要**从中文反推英文。 - 标题作中文 `##`/`###`,不加 blockquote;可选地把英文标题作为上一行 blockquote。 - 不该被脚本删掉、需保留进全中文版的东西(图片、表格、标题块)**不要** blockquote。 - 公式/代码用共享代码块,不按语言重复。
## 润色边界 ★(防止方法论被用过头)
叶子南本人警告的两个反模式,务必守住: - **不要过度归化**:别为了“地道”抹掉原文该保留的风格、术语精度、文化标记。西化是一个**连续体**,可接受度随文本价值变化——硬文本/永久价值文本能容纳更多异化(见 `reference/translationese-symptoms.md` 第七节)。 - **不要堆砌四字成语**:音韵节奏是手段不是目的,为文字而文字会显得卖弄、失真。 - 拿不准“该改到多狠”时,回到阶段 0 的档位:**自由度越低,越克制**。
## 示例
输入(英文):
``` The confidence that the West would remain a dominant force in the 21st century is giving way to a sense of foreboding. ```
输出(英中对照;阶段 0 判定:偏硬/政论,自由度≈3,准确优先、克制音韵):
> The confidence that the West would remain a dominant force in the 21st century is giving way to a sense of foreboding.
西方曾笃信自己将在 21 世纪稳居主导地位,如今这份自信,正让位于一种隐隐的不祥之感。
## 致谢与许可
本 skill 的代码、提示词与组织方式以 **MIT 许可**发布,可自由使用、修改、再分发。
方法论与判例蒸馏、转述自叶子南《高级英汉翻译理论与实践》(第4版,清华大学出版社,2020),在此谨致谢忱。`reference/` 三张表中的少量引文系评注与教学目的的简短摘引,著作权归原作者与出版社所有;本 skill 仅为方法工具,不能替代原著,建议系统学习者购买正版。
Source provenance
Decision snapshot
recent repository activity
Audit
Install and adoption review
Agent-proven evidence
Outcome reports after resolve, review, install, and one narrow run.
No agent outcome data yet. The first agent run can report success, setup needs, risk blocks, failure, or not-relevant through /api/agent/outcome.
Install
Free and open source. Review the report before installing into production agents.
Growth loop
Scenario-led draft for en-zh-translation-polish, ready for a manual X post.
For a repeatable workflow, this is a skill worth shortlisting before another blank prompt. en-zh-translation-polish: >- 106 stars https://www.openagentskill.com/skills/horacelubfa-en-zh-translation-polish?ref=x
Listing + install path for en-zh-translation-polish: https://www.openagentskill.com/skills/horacelubfa-en-zh-translation-polish?ref=x Install: npx skills add HoraceLuBFA/en-zh-translation-polish --skill en-zh-translation-polish
Listing source
This listing was indexed from public sources and is not marked official until a maintainer claim is approved.
Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals.
Claim this skillOwner claim
This Registry indexed listing is attributed to HoraceLuBFA but is not marked official yet. Claim it to add a verified owner signal and make future launch, install, and audit updates easier to trust.
Creator backlink kit
Show the canonical listing, current trust and audit signals, and real Agent-Proven evidence where developers evaluate the repository.
[](https://www.openagentskill.com/skills/horacelubfa-en-zh-translation-polish?ref=github&utm_source=github&utm_medium=referral&utm_campaign=creator_badge)
[](https://www.openagentskill.com/skills/horacelubfa-en-zh-translation-polish?ref=github&utm_source=github&utm_medium=referral&utm_campaign=creator_badge)
[](https://www.openagentskill.com/skills/horacelubfa-en-zh-translation-polish/audit)
[](https://www.openagentskill.com/skills/horacelubfa-en-zh-translation-polish?ref=github&utm_source=github&utm_medium=referral&utm_campaign=creator_badge)HoraceLuBFA
@horacelubfa
Share whether this skill looks useful for your agent workflow. Aggregated feedback improves rankings over time.
Sandbox only
UI-TARS Desktop
Run multimodal agents that operate desktop interfaces
37.0K Starsn8n
Connect agents to hundreds of workflow automations
194.1K StarsMoneyPrinterTurbo
利用AI大模型,一键生成高清短视频 Generate short videos with one click using AI LLM.
88.5K StarsTasmota
Alternative firmware for ESP8266 and ESP32 based devices with easy configuration using webUI, OTA updates, automation using timers or rules, expandability and entirely local control over MQTT, HTTP, Serial or KNX. Full documentation at
24.7K StarsSandbox only
Install targets
Codex install prompt
Install the "en-zh-translation-polish" agent skill from https://github.com/HoraceLuBFA/en-zh-translation-polish/blob/main/SKILL.md. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: >- After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {"event_id":"install_<unique-id>","skill_slug":"horacelubfa-en-zh-translation-polish","task":"Install en-zh-translation-polish","agent":"codex","outcome":"success","install_used":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.Supply asset profile
Deep research, source comparison, literature review, RAG, knowledge search, and reports.
Scenario
RAG and knowledge
I need my agent to build a RAG workflow over documents and retrieve reliable context.
Agent fit
Claude Code + CLI + Codex
Codex, Claude Code, Cursor, CLI, or custom agents.
Install
Ready
npx skills add HoraceLuBFA/en-zh-translation-polish --skill en-zh-translation-polish
Maintenance
fresh
5d since push
Risk
Needs review
Quality score needs review
GitHub quality
106
71/100 Quality · 76/100 Trust
Coverage tags
Review notes
Quality score needs review · Stars/forks activity: 106 stars, 5 forks; issue activity unavailable in current metadata
Agent adoption scorecard
These scores combine public repository metadata, OpenAgentSkill review signals, maintenance freshness, and install readiness. They are a shortlist signal, not a replacement for human review.
Quality
StrongSolid option that is likely worth shortlisting for production workflows.
Trust
Sandbox onlyUseful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.
Audit
Needs reviewA machine-readable review of install readiness, security metadata, maintenance, and adoption risk.
OpenAgentSkill Trust Score v5
Run only in a sandbox and compare close alternatives before using it for real work.
Stars
106 GitHub stars
Repo activity
106 stars, 5 forks
Maintenance
5d since push
License
MIT
Install
npx skills add HoraceLuBFA/en-zh-translation-polish --skill en-zh-translation-polish
Install safety
Agent-readable metadata
Use this block or the embedded JSON to decide whether an agent should install this skill, choose an alternative, or ask for human review first.
Suited tasks
Suited agents
Install decision
Trust and risk
Outcome loop
Install command
npx skills add HoraceLuBFA/en-zh-translation-polish --skill en-zh-translation-polishDo not use when
Agent safety v2
Sparse or mixed signals. Useful for discovery, but not for autonomous installation.
Test manually in an isolated workspace and compare against safer alternatives.
high
Skill metadata references terminal, CLI, shell, subprocess, or command execution workflows.
medium
Skill likely fetches remote pages, APIs, repositories, or external services.
medium
Skill may read or write project files, documents, generated artifacts, or local workspace state.
Agent resolve plan
The Resolve API returns the selected skill, alternatives, safety policy, audit notes, install target, and copy-paste prompt an agent can follow without scraping this page.
Open JSON
/api/agent/resolve?task=Use%20en-zh-translation-polish%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Resolve text
/api/agent/resolve?task=Use%20en-zh-translation-polish%20for%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text
Install handoff
/api/skills/horacelubfa-en-zh-translation-polish/install
Agent should check
Copy prompt
Task: Use en-zh-translation-polish in this workspace.
Resolve first: https://www.openagentskill.com/api/agent/resolve?task=Use%20en-zh-translation-polish%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Review install handoff: https://www.openagentskill.com/api/skills/horacelubfa-en-zh-translation-polish/install
Install command: npx skills add HoraceLuBFA/en-zh-translation-polish --skill en-zh-translation-polish
Before running it, summarize audit warnings, required permissions, and the fallback skill if install is risky.Agent handoff
Use the public install endpoint to fetch the command, safety checklist, target prompts, and canonical links for this skill.
Install handoff
/api/skills/horacelubfa-en-zh-translation-polish/install
LLM text format
/api/skills/horacelubfa-en-zh-translation-polish/install?format=text
Find alternatives
/api/skills/search?q=en-zh-translation-polish&limit=3
Agent prompt
Use en-zh-translation-polish for this task. Review https://www.openagentskill.com/api/skills/horacelubfa-en-zh-translation-polish/install, then install with: npx skills add HoraceLuBFA/en-zh-translation-polish --skill en-zh-translation-polishRegistry metadata
This page exposes the same decision, trust, audit, use-case, and install signals through the Registry API, so agents can rank this skill without scraping the UI.
Manifest
/api/registry/manifest/horacelubfa-en-zh-translation-polish
LLM text
/api/registry/manifest/horacelubfa-en-zh-translation-polish?format=text
Install alias
/api/registry/install/horacelubfa-en-zh-translation-polish
Recommend
/api/registry/recommend?task=Use%20en-zh-translation-polish%20in%20an%20agent%20workflow&limit=3
Agent fit
Local desktop
Use-case tags
Platforms
Claude Code
Audit report
A machine-readable review of install readiness, security metadata, maintenance, and adoption risk.
Agent decision cockpit
Prototype with this skill first; keep a fallback candidate ready.
Role in stack
Fallback candidate
Primary fit
Local desktop
Trust label
Prototype first
Install path
Command ready
Use when
Evidence
review first
Implementation path
Trust profile
Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.
GitHub adoption
INFO106 GitHub stars
Stars/forks activity
CHECK106 stars, 5 forks; issue activity unavailable in current metadata
Recent maintenance
PASS5d since push
License clarity
PASSMIT
Good signals
Review before install
Recommended action
Run only in a sandbox and compare close alternatives before using it for real work.
Quality profile
Solid option that is likely worth shortlisting for production workflows.
Workflow fit
Operate local tools
I need my agent to operate local files and desktop apps in a repeatable workflow.
Search private knowledge
I need my agent to build a RAG workflow over documents and retrieve reliable context.
Investigate faster
I need my agent to research a topic, compare sources, and produce a concise report.
Workflow fit
Ingest, retrieve, and cite
A workflow for document-heavy agents that ingest files, create searchable knowledge, retrieve relevant context, and answer with grounded sources.
Find, compare, and synthesize
A workflow for agents that gather sources, compare claims, summarize long material, and draft useful research briefs.
Turn skills into distribution
A workflow for turning newly indexed skills into SEO briefs, social drafts, comparison pages, and reusable publishing workflows.
Alternative shortlist
Similar skills that may fit this task.
Run multimodal agents that operate desktop interfaces
Connect agents to hundreds of workflow automations
利用AI大模型,一键生成高清短视频 Generate short videos with one click using AI LLM.
Alternative firmware for ESP8266 and ESP32 based devices with easy configuration using webUI, OTA updates, automation using timers or rules, expandability and entirely local control over MQTT, HTTP, Serial or KNX. Full documentation at
--- name: en-zh-translation-polish description: >- Translates English into idiomatic, translationese-free Chinese, optionally as an English-Chinese bilingual version pairing each source paragraph with its translation. Use when the user wants to 翻译成中文 / 英译汉, 去翻译腔/润色译文 (remove translationese, polish a draft), or produce a 中英对照/英中对照 bilingual rendering. Not for Chinese-to-English, pure Chinese writing polish, or single-word lookups. license: MIT version: 1.0.0 tags: [translation, chinese, english-to-chinese, 英译汉, 润色, 中英对照, localization] allowed-tools: Read Write Edit Bash ---
# 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。 ```bash 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 以**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。
### 阶段 6 — 中文标点规范化 ★(机械执行,落盘后必跑) 中文译文里的标点必须是中文全角,不能残留英文半角(译者最易忽略,逐字凭眼力一定会漏)。规则: - `, : ; ? !` → `,:;?!`;句末用 `。`;并列用顿号 `、`;破折号 `——`;省略号 `……`。 - 圆括号 `( )` → 全角 `( )`:**仅当紧邻中文字符时才转**(包裹中文内容、含人名/术语原文注,如 "道德受体地位(moral patienthood)");纯英文括注(如电影演职 `(Harold D. Schuster, 1937)`)保持半角。 - 双引号统一为中文全角 `" "`(内层 `' '`);直角引号 `「」`、`『』` 一并归一为 `" "` / `' '`。
**以下一律保持半角,绝不转:** ① 英文原文 blockquote(`> ` 行)整段不动;② Markdown 链接 `[文字](url)` 的括号与 URL;③ 中文行内嵌入的整句/词组英文,其内部标点——如被引用的英文原句 `…one nation under God, indivisible, …`;④ 数字/缩写/版本号里的点:`4.3`、`Word 2010`、`A.I.`、`L. M.`;⑤ 代码/公式块。
判定原理:**逗号类与圆括号都只在紧邻中文字符(前或后)时才转**;有方向的引号(“”「」‘’『』)按方向直接映射,只有歧义的直双引号 `"` 才靠交替判定开闭。落盘后跑下面脚本机械归一并自检(`残留` 必须为 0):
```bash python3 - "<名称> 翻译(中英对照).md" <<'PY' import re, sys src = sys.argv[1] lines = open(src, encoding='utf-8').read().split('\n') CJK_EXTRA = set('“”‘’·—…《》〈〉「」『』【】、。,!?;:()') def is_cjk(c): if not c: return False o = ord(c) return (0x3400<=o<=0x9fff) or (0x3000<=o<=0x303f) or (0xff00<=o<=0xffef) or (c in CJK_EXTRA) SMAP = {',':',', ';':';', ':':':', '?':'?', '!':'!', '(':'(', ')':')'} OPEN2 = '“「'; CLOSE2 = '”」'; OPEN1 = '‘『'; CLOSE1 = '’』' LINK = re.compile(r'\[[^\]]*\]\([^)]*\)') def fix(line): store=[] line = LINK.sub(lambda m: store.append(m.group(0)) or '\x00%d\x00'%(len(store)-1), line) out=[]; sop=True # 有方向引号直接映射; 仅歧义直双引号 " 靠交替定开闭 for c in line: if c == '"': out.append('“' if sop else '”'); sop = not sop elif c in OPEN2: out.append('“') elif c in CLOSE2: out.append('”') elif c in OPEN1: out.append('‘') elif c in CLOSE1: out.append('’') else: out.append(c) ch=out; n=len(ch) for i,c in enumerate(ch): # 逗号类 + 圆括号: 紧邻中文才转全角 if c in SMAP and (is_cjk(ch[i-1] if i else '') or is_cjk(ch[i+1] if i+1<n else '')): ch[i]=SMAP[c] line=''.join(ch) return re.sub('\x00(\\d+)\x00', lambda m: store[int(m.group(1))], line) def skip(ln): s=ln.strip(); return s=='' or ln.lstrip().startswith('>') or s=='---' res=[ln if skip(ln) else fix(ln) for ln in lines] open(src,'w',encoding='utf-8').write('\n'.join(res)) def residual(ln): t = LINK.sub('', ln) # 排除 markdown 链接内的括号/标点, 免误报 return sum(1 for m in re.finditer(r'[,;:?!()]', t) if is_cjk(t[m.start()-1] if m.start() else '') or is_cjk(t[m.start()+1] if m.start()+1<len(t) else '')) bad=sum(residual(ln) for ln in res if not skip(ln)) print('残留:', bad) PY ``` 聊天里直接给的小段对照(未落盘)同样要手动套用上述规则。
### 阶段 7 — 输出英中对照 按下方格式逐段配对;成篇则写文件;给用户附一句“档位判定 + 主要润色取舍”。
## 英中对照输出格式
**按段落配对**:英文原段作为 blockquote,紧接中文译文。
```markdown > It is a truth universally acknowledged that a single man in possession of a > good fortune must be in want of a wife.
凡是有钱的单身汉,总想娶位太太,这是一条举世公认的真理。 ```
规则: - 中文译文用中文全角标点;半角标点只留给英文原文、链接、行内英文词句、数字缩写、代码(详见阶段 6,落盘后用脚本自检)。 - 只清理提取噪声(接回断行连字符、删页眉页脚页码),**不要**从中文反推英文。 - 标题作中文 `##`/`###`,不加 blockquote;可选地把英文标题作为上一行 blockquote。 - 不该被脚本删掉、需保留进全中文版的东西(图片、表格、标题块)**不要** blockquote。 - 公式/代码用共享代码块,不按语言重复。
## 润色边界 ★(防止方法论被用过头)
叶子南本人警告的两个反模式,务必守住: - **不要过度归化**:别为了“地道”抹掉原文该保留的风格、术语精度、文化标记。西化是一个**连续体**,可接受度随文本价值变化——硬文本/永久价值文本能容纳更多异化(见 `reference/translationese-symptoms.md` 第七节)。 - **不要堆砌四字成语**:音韵节奏是手段不是目的,为文字而文字会显得卖弄、失真。 - 拿不准“该改到多狠”时,回到阶段 0 的档位:**自由度越低,越克制**。
## 示例
输入(英文):
``` The confidence that the West would remain a dominant force in the 21st century is giving way to a sense of foreboding. ```
输出(英中对照;阶段 0 判定:偏硬/政论,自由度≈3,准确优先、克制音韵):
> The confidence that the West would remain a dominant force in the 21st century is giving way to a sense of foreboding.
西方曾笃信自己将在 21 世纪稳居主导地位,如今这份自信,正让位于一种隐隐的不祥之感。
## 致谢与许可
本 skill 的代码、提示词与组织方式以 **MIT 许可**发布,可自由使用、修改、再分发。
方法论与判例蒸馏、转述自叶子南《高级英汉翻译理论与实践》(第4版,清华大学出版社,2020),在此谨致谢忱。`reference/` 三张表中的少量引文系评注与教学目的的简短摘引,著作权归原作者与出版社所有;本 skill 仅为方法工具,不能替代原著,建议系统学习者购买正版。
Source provenance
Decision snapshot
recent repository activity
Audit
Install and adoption review
Agent-proven evidence
Outcome reports after resolve, review, install, and one narrow run.
No agent outcome data yet. The first agent run can report success, setup needs, risk blocks, failure, or not-relevant through /api/agent/outcome.
Install
Free and open source. Review the report before installing into production agents.
Growth loop
Scenario-led draft for en-zh-translation-polish, ready for a manual X post.
For a repeatable workflow, this is a skill worth shortlisting before another blank prompt. en-zh-translation-polish: >- 106 stars https://www.openagentskill.com/skills/horacelubfa-en-zh-translation-polish?ref=x
Listing + install path for en-zh-translation-polish: https://www.openagentskill.com/skills/horacelubfa-en-zh-translation-polish?ref=x Install: npx skills add HoraceLuBFA/en-zh-translation-polish --skill en-zh-translation-polish
Listing source
This listing was indexed from public sources and is not marked official until a maintainer claim is approved.
Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals.
Claim this skillOwner claim
This Registry indexed listing is attributed to HoraceLuBFA but is not marked official yet. Claim it to add a verified owner signal and make future launch, install, and audit updates easier to trust.
Creator backlink kit
Show the canonical listing, current trust and audit signals, and real Agent-Proven evidence where developers evaluate the repository.
[](https://www.openagentskill.com/skills/horacelubfa-en-zh-translation-polish?ref=github&utm_source=github&utm_medium=referral&utm_campaign=creator_badge)
[](https://www.openagentskill.com/skills/horacelubfa-en-zh-translation-polish?ref=github&utm_source=github&utm_medium=referral&utm_campaign=creator_badge)
[](https://www.openagentskill.com/skills/horacelubfa-en-zh-translation-polish/audit)
[](https://www.openagentskill.com/skills/horacelubfa-en-zh-translation-polish?ref=github&utm_source=github&utm_medium=referral&utm_campaign=creator_badge)HoraceLuBFA
@horacelubfa
Share whether this skill looks useful for your agent workflow. Aggregated feedback improves rankings over time.
Sandbox only
UI-TARS Desktop
Run multimodal agents that operate desktop interfaces
37.0K Starsn8n
Connect agents to hundreds of workflow automations
194.1K StarsMoneyPrinterTurbo
利用AI大模型,一键生成高清短视频 Generate short videos with one click using AI LLM.
88.5K StarsTasmota
Alternative firmware for ESP8266 and ESP32 based devices with easy configuration using webUI, OTA updates, automation using timers or rules, expandability and entirely local control over MQTT, HTTP, Serial or KNX. Full documentation at
24.7K StarsPermission surface
shell or command execution
Agent outcomes
No agent outcome data yet
Docs
Usable metadata, review docs
Risk summary
Install readiness
Permission surface
shell or command execution
Agent outcomes
No agent outcome data yet
Docs
Usable metadata, review docs
Risk summary
Install readiness
Permission surface
shell or command execution
Agent outcomes
No agent outcome data yet
Docs
Usable metadata, review docs
Risk summary
Install readiness
Permission surface
shell or command execution
Agent outcomes
No agent outcome data yet
Docs
Usable metadata, review docs
Risk summary
Install readiness