agentCLAWHUBUnverified

文曲·翻译

将 README、论文、源码注释、文档和英文文章等材料翻译成自然中文,供中文内容创作与阅读 使用。当用户要求“翻译一下”“把这段英文翻译成中文”或“译成中文”,或使用 "translate to Chinese", "translate this README", "translate this paper" 等英文表达时使用。 Skill: 文曲·翻译 Owner: gogoingai Summary: 将 README、论文、源码注释、文档和英文文章等材料翻译成自然中文,供中文内容创作与阅读 使用。当用户要求“翻译一下”“把这段英文翻译成中文”或“译成中文”,或使用 "translate to Chinese", "translate this README", "translate this paper" 等英文表达时使用。 Tags: latest:0.1.19 Version history: v0.1.19 | 2026-08-04T01:14:13.073Z | user v0.1.19 v0.1.17 | 2026-08-02T02:37:14.547Z | user v0.1.17 v0.1.16 | 2026-08-01T12:12:14.963Z | user 0.1.16: 运行时迁入 wenqu-cli,全技能版本同步 v0.1

OpenClaw

Rank

62

Safety

84

Downloads

961

Updated

Oct 12, 2026

Version

0.1.19

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 961 downloads reported by the source. Last updated 10/12/2026.

Avoid when

  • Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor
Clawhubvendor · observed Oct 12, 2026
Protocol compatibility
OpenClawcompatibility · observed Oct 12, 2026
Adoption signal
961 downloadsadoption · observed Oct 12, 2026
Latest release
0.1.19release · observed Aug 4, 2026
Handshake status
UNKNOWNsecurity

What changed

Newest first. Only changes that point at a source are listed.

Install and run

Setup complexity: low.

clawhub skill install s172babns2qv4nzkpmkvakeych8bbw9z:wenqu-translate
  1. Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.
  2. Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-gogoingai-wenqu-translate/snapshot"

Run-check

$0.02 USD

1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.

Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.

Documentation

CLAWHUB

44,902 characters of source documentation, loaded on request.

Extracted files

4 files captured from the source.

SKILL.md

---
name: wenqu-translate
description: >-
  将 README、论文、源码注释、文档和英文文章等材料翻译成自然中文,供中文内容创作与阅读
  使用。当用户要求“翻译一下”“把这段英文翻译成中文”或“译成中文”,或使用 "translate to
  Chinese", "translate this README", "translate this paper" 等英文表达时使用。
slug: wenqu-translate
displayName: 文曲·翻译
version: 0.1.19
summary: 英文材料(README、论文、源码注释、文档)翻译成自然中文,用于内容创作与阅读。
license: MIT
homepage: https://github.com/gogoingai/wenqu-skills
metadata:
  openclaw:
    homepage: https://github.com/gogoingai/wenqu-skills/tree/master/wenqu-translate
---

# 英文材料翻译 Skill

> 📦 项目仓库与源码:<https://github.com/gogoingai/wenqu-skills>

## 用户输入工具

当本技能需要用户确认选择、补充必要信息或授权有副作用的操作时:

1. 优先用运行时自带的用户输入工具,例如 `AskUserQuestion`、`request_user_input`、`clarify`、`ask_user` 或等价能力。
2. 若没有此类工具,使用带编号或字母选项的文本问答。
3. 同一决策阶段中彼此独立的问题可合并提问;后一个问题依赖前一回答时,按依赖顺序逐个问。
4. 已由用户当前指令、调用方或文章偏好提供的信息,不重复询问。
5. 文中出现的具体工具名均为示例;应替换为当前运行时的等价能力。

## 工具等价说明(非 Claude Code 环境)

`Skill`(调用 wenqu-review 做 R2 审查)是 Claude Code 工具名。其他 agent 没有该工具时,直接 Read `~/.agents/skills/wenqu-review/references/r2-translation.md` 内联执行。

## 触发识别

| 场景 | 入口 |
|------|------|
| 用户直接说"翻译一下"、给一段英文要求译成中文(单篇文章量级) | 独立触发,走下方"翻译流程" |
| wenqu-write Step 2 获取素材时源材料是英文 | 被调用,读者画像已由调用方提供,跳过下方"确认读者背景"这一步 |
| 源文档很长(约 4000 词以上)、要翻译多篇与整本书、需要 quick/normal/refined 多模式切换或分块并行翻译 | **超出本技能范围**,如实告知用户另寻专门的长文档翻译工具,不要硬凑 |

---

## 超出范围的情况

源文档词数明显超过 4000、需要 quick/normal/refined 多模式切换、分块并行翻译,或要翻译整本书/多篇文档时,**超出本技能范围**:如实告知用户“这个量级超出本技能范围,建议寻找专门的长文档翻译工具”,不要硬凑一份打折扣的翻译。本技能不依赖、也不主动推荐任何第三方技能。
---

## 翻译流程

→ 查 `references/translation-guide.md`(完整方法论:分析→翻译→自查,核心原则,注解密度规则,常见误译信号)

**独立触发时,先确认读者背景**(决定注解密度):没有调用方提供读者画像,用 `AskUserQuestion` 询问"目标读者的技术背景是?"(无背景、初级工程师、中级工程师、高级工程师),再进入翻译。

**翻译完成后,强制当场执行一次 R2,不等到全文写完**:用 `Skill` 工具调用 **wenqu-review**,指定只跑 R2(翻译腔审查);没有跨技能调用机制时直接 Read `~/.agents/skills/wenqu-review/references/r2-translation.md` 内联执行。这一步不可省略——Claude 系模型生成中文时容易出现翻译腔,尤其是刚读完英文源码、文档之后,译者很难察觉自己写出的翻译腔。

---

## 依赖

- `references/translation-guide.md` 完整自包含,覆盖单篇文章量级的翻译,不需任何外部依赖
- R2 审查依赖 **wenqu-review**(同仓库技能,随套件一起安装)

---

## 用户反馈与偏好持久化

本技能不修改自身仓库的 `references/translation-guide.md`,遇到新的误译模式或用户给出的持久化翻译偏好(专有名词是否保留英文、注解密度、直译信号判定……),改为写入**被翻译文章自身的**存储目录:`{项目根目录}/wenqu-skills/{文件名}/references/preferences.md`「翻译偏好」表(表结构见 wenqu-write 的 `references/planning/questionnaire.md`「写入 preferences.md」一节)。

**判定标准**:这条反馈下次译同一篇文章时还用得上吗?
- 是("agent 不要翻译成智能体,保留英文"这类持续适用的取舍)→ 当场往 `references/preferences.md`「翻译偏好」表里追加一行
- 否(这次这段话的临时改法)→ 不持久化

**每次翻译前先查这份文件**(被 wenqu-write 调用时通常已加载;独立触发时自己检查该文章的 `wenqu-skills/{文件名}/references/preferences.md` 是否存在),有已记录的偏好就照着做,不重复问用户。

_meta.json

{
  "ownerId": "kn7f83q4k2qj4an11r2mqyhy418bbg2n",
  "slug": "wenqu-translate",
  "version": "0.1.19",
  "publishedAt": 1785806053073
}

references/translation-guide.md

---
name: translation-guide
description: 英文材料(README、论文、源码注释、技术文章)翻译成中文的完整方法论:分析→翻译→自查。自包含,不依赖外部技能,专注单篇文章量级的翻译质量。
metadata:
  type: reference
---

# 英文材料翻译方法论

## 方法论:先分析,再翻译,不要拿到英文就直接下笔

### 第一步:分析

翻译前先花一点时间判断三件事,直接影响后面怎么翻:

1. **领域和语气**:这是源码注释(简洁、祈使句多)、README(说明性,带营销语气)、论文(严谨、被动语态多、术语密度高)还是技术文章(叙事性更强)?语气判断错了,语气会和原文不搭。
2. **目标读者的技术背景**:决定注解密度——见下方「注解密度跟着读者画像走」。
3. **高频术语**:扫一遍全文,找出反复出现的专有名词、术语,统一想好译法,避免同一个词在不同段落译得不一样。

### 第二步:翻译

按下方"核心原则"和"注解密度"规则,把内容重写成自然中文,不是逐句直译。

### 第三步:自查

翻译完立刻对照「常见误译信号」表自查一遍,再交给 wenqu-review 的 R2 做独立审查(见下方"和 R2 的关系",这一步不可省略)。

---

## 核心原则

- **重写而非直译**:把内容用自然、地道的中文重新表达,就像熟练的中文母语写手从头写的一样。自检标准:"这段话读起来像是用中文直接写的吗?"
- **准确性优先**:事实、数据、逻辑必须和原文完全一致,重写不能以牺牲准确性为代价
- **自然语序**:用中文习惯的语序,长句拆成自然的短句;比喻和习语按意思翻译,不逐词直译
- **术语一致**:同一个术语全篇统一译法;专有名词首次出现时用"中文译名(英文原文)"的格式标注
- **保留格式**:标题、加粗、斜体、图片、链接、代码块等 Markdown 格式原样保留
- **主动补充解释**:目标读者可能缺乏背景的术语、概念,用**加粗括号**补充解释,例如"(**解释**)";解释要精简,只在真正影响理解时才加

## 注解密度跟着读者画像走

**不要用固定的一套注解密度**——同一个术语,给初级工程师看要解释,给高级工程师看就是噪音。调用方(如 wenqu-write)已有读者画像时,直接复用:

| 读者技术背景(来自读者画像) | 注解策略 |
|---|---|
| 无背景、初级工程师 | 术语首次出现必须加中文解释,常见缩写也展开一次 |
| 中级工程师 | 只解释该领域专属术语,通用工程术语(如 API、缓存)不加注 |
| 高级工程师 | 只在术语有歧义或该项目特殊用法时才加注,其余保持简洁 |

被独立调用(没有调用方提供读者画像)时,直接问用户目标读者的技术背景,不要假设。

## 常见误译信号(翻译时就要避免,不要留到审查阶段才发现)

翻译时如果写出以下几种结构,说明还在直译英文语序,需要重新组织成中文表达:

| 直译信号 | 例子 | 改法 |
|---------|------|------|
| 介词结构堆砌 | "通过...来..."、"对...进行..." | 去掉介词短语,用动词直接表达 |
| 名词化动词 | "进行压缩"、"实现了...的功能" | 直接用动词:"压缩" |
| 被动语态过度 | "被...所决定"、"由...来完成" | 改主动语态 |

## 和 R2 的关系(强制,不可跳过)

这三类信号和 wenqu-review 的 R2(翻译腔审查)用的是**同一套判断标准**,但两者不能互相替代:

- **翻译时自查**(上表):省掉后续大部分返工,但译者很难察觉自己写出的翻译腔——这是认知盲区,不是态度问题
- **R2 独立审查**:翻译完成后**当场**(不等到全文写完)直接 Read `~/.agents/skills/wenqu-review/references/r2-translation.md` 内联执行一遍。Claude 系模型生成中文时本身容易出现翻译腔和奇怪表达,尤其是刚读完英文源码、文档之后——这一步是质量的主要防线,不是可选的收尾动作

## 不需要的东西

不需要分块翻译、多种翻译模式(quick/normal/refined)、子 agent 并行翻译、EXTEND.md 配置文件这类工程化机制——本技能处理的是单篇文章素材量级的翻译,用不上这套基础设施。源文档特别长(远超单次会话上下文)时才考虑分段处理,分段处理是次要的,翻译质量才是重点。

skill-card.md

## Description:

文曲·翻译 translates English README files, papers, code comments, documentation, and articles into natural Chinese for reading and content creation.

This skill is ready for commercial/non-commercial use.

## Publisher:

[gogoingai](https://clawhub.ai/user/gogoingai)

### License/Terms of Use:

MIT-0

## Use Case:

External users, developers, and content creators use this skill to translate single-article English materials into natural Chinese while preserving technical accuracy, terminology consistency, and Markdown structure.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: The skill relies on a companion wenqu-review R2 review step for translation-tone quality control.

Mitigation: Before use, confirm that the companion review skill is installed and trusted, or perform the documented R2 review inline.

Risk: The skill may write persistent per-article translation preferences into project files.

Mitigation: Review any preferences.md changes as normal repository edits before committing or reusing them.

## Reference(s):

- [Translation guide](references/translation-guide.md)
- [Project source](https://github.com/gogoingai/wenqu-skills/tree/master/wenqu-translate)
- [ClawHub skill page](https://clawhub.ai/gogoingai/skills/wenqu-translate)

## Skill Output:

**Output Type(s):** [text, markdown, guidance]

**Output Format:** [Natural Chinese prose, usually preserving the source Markdown structure]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [May ask for reader background before translation and may record per-article translation preferences as project changes.]

## Skill Version(s):

0.1.19 (source: server release metadata and skill frontmatter)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.
Github ReposUpdated 2d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW
Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW
Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW
Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular

OPENCLAW

Machine-readable data

The same record, as JSON, for agents and crawlers.

{
  "facts": [
    {
      "factKey": "vendor",
      "category": "vendor",
      "label": "Vendor",
      "value": "Clawhub",
      "href": "https://clawhub.ai/gogoingai/skills/wenqu-translate",
      "sourceUrl": "https://clawhub.ai/gogoingai/skills/wenqu-translate",
      "sourceType": "profile",
      "confidence": "medium",
      "observedAt": "2026-10-12T01:28:29.858Z",
      "isPublic": true
    },
    {
      "factKey": "protocols",
      "category": "compatibility",
      "label": "Protocol compatibility",
      "value": "OpenClaw",
      "href": "https://www.xpersona.co/api/v1/agents/clawhub-gogoingai-wenqu-translate/contract",
      "sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-gogoingai-wenqu-translate/contract",
      "sourceType": "contract",
      "confidence": "medium",
      "observedAt": "2026-10-12T01:28:29.858Z",
      "isPublic": true
    },
    {
      "factKey": "traction",
      "category": "adoption",
      "label": "Adoption signal",
      "value": "961 downloads",
      "href": "https://clawhub.ai/gogoingai/wenqu-translate",
      "sourceUrl": "https://clawhub.ai/gogoingai/wenqu-translate",
      "sourceType": "profile",
      "confidence": "medium",
      "observedAt": "2026-10-12T01:28:29.858Z",
      "isPublic": true
    },
    {
      "factKey": "latest_release",
      "category": "release",
      "label": "Latest release",
      "value": "0.1.19",
      "href": "https://clawhub.ai/gogoingai/wenqu-translate",
      "sourceUrl": "https://clawhub.ai/gogoingai/wenqu-translate",
      "sourceType": "release",
      "confidence": "medium",
      "observedAt": "2026-08-04T01:14:13.073Z",
      "isPublic": true
    },
    {
      "factKey": "handshake_status",
      "category": "security",
      "label": "Handshake status",
      "value": "UNKNOWN",
      "href": "https://www.xpersona.co/api/v1/agents/clawhub-gogoingai-wenqu-translate/trust",
      "sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-gogoingai-wenqu-translate/trust",
      "sourceType": "trust",
      "confidence": "medium",
      "observedAt": null,
      "isPublic": true
    }
  ],
  "events": [
    {
      "eventType": "release",
      "title": "Release 0.1.19",
      "description": "v0.1.19",
      "href": "https://clawhub.ai/gogoingai/wenqu-translate",
      "sourceUrl": "https://clawhub.ai/gogoingai/wenqu-translate",
      "sourceType": "release",
      "confidence": "medium",
      "observedAt": "2026-08-04T01:14:13.073Z",
      "isPublic": true
    }
  ]
}

Record generated Oct 12, 2026.

For crawlers

This page is free to read. The run-check above is the only paid part, and it answers HTTP 402 until it is paid. Everything else here is public.

  • One record, as JSON: card, facts, snapshot, contract, trust, changes, warnings, seen by, disagreements.
  • Every agent, one feed: /.well-known/ai-catalog.json
  • What this site sells, and the price: /.well-known/x402
  • Paid run-check: /api/v1/agents/clawhub-gogoingai-wenqu-translate/run-check

Sponsored

Ads related to 文曲·翻译 and adjacent AI workflows.