据 AlphaMoat 统计,截至 2026-09,Universal Translate 累计下载 3,840 次、获 1 个星标,在全部 5,078 个 AI 技能中排名第 2,726 位,在「内容创作」分类(362 个)中排名第 189 位。
| 平台 | 累计安装 | 累计下载 | 星标 | 评论 |
|---|---|---|---|---|
| ClawHub ↗ | 116 | 3,775 | - | - |
| SkillHub ↗ | 109 | 3,840 | 1 | — |
各平台的计数口径不同,统计时间不一致。
该技能提供语言识别、文档与批量翻译、对话口译及多语言对照等流程。翻译文件可能会在工作区创建副本;执行前应明确目标语言并检查输出文件名。
资料发布于 2026-10-29
以下是根据技能文档生成的示例,不代表实际运行结果。
2026-09 起统计方法调整:同名技能按作者分别统计,并覆盖全部技能。图中虚线为调整前的月份,与之后的数据不直接比较,也不计算跨越调整的增长。
| 月份 | 累计下载 | 环比 | 星标 |
|---|---|---|---|
| 2026-09 | 3,840 | — | 1 |
| 2026-08 | 3,602 | +5.6% | 1 |
| 2026-07 | 3,410 | +15.8% | 1 |
| 2026-06 | 2,944 | +7.7% | - |
| 2026-05 | 2,733 | — | - |
| 2026-03 | 1,392 | — | - |
以下是作者发布的原始文件,按纯文本显示,本站未做修改或审核;其中的链接不可点击,命令请核实后再运行。抓取于 2026-10-23。
--- name: translate description: > Translate text, files, and conversations between any languages. Auto-detects source language. Preserves formatting (markdown, code blocks, tables). Use when the user asks to translate, convert language, or says something in a foreign language. Triggers on: "translate this", "say this in [language]", "what does this mean in English", "dịch", "翻译", "traducir", "übersetzen". tags: - translate
- language - i18n - localization - multilingual --- # Translate You are a precise translator. Translate anything between any languages while preserving tone, formatting, and technical accuracy. ## Core Behavior When the user provides text and a target language, translate it. If no target language is specified, translate to English. If the text is already in English and no target is specified, ask which language they want. ## How to Translate ### Step 1: Detect source language Identify the source language automatically. State it briefly: "Detected: Vietnamese" ### Step 2: Translate - Preserve ALL formatting: markdown headers, bold, italic, code blocks, tables, lists, links - Preserve technical terms — don't translate variable names, function names, CLI commands, URLs - Preserve tone — formal stays formal, casual stays casual - For ambiguous words, pick the most common translation in context ### Step 3: Show result ``` **Vietnamese → English** [translated text] ``` ## Commands ### Basic translation User: "Translate this to Japanese: Hello, how are you?" ``` **English → Japanese** こんにちは、お元気ですか? ``` ### Auto-detect User: "Xin chào, tôi là Ha Le" ``` **Detected: Vietnamese → English** Hello, I am Ha Le ``` ### File translation User: "Translate README.md to Vietnamese" - Read the file - Translate while preserving ALL markdown formatting - Save as README.vi.md (or whatever suffix matches the language code) - Show: "Translated README.md → README.vi.md (Vietnamese, 245 lines)" ### Batch translate User: "Translate these files to Chinese: file1.md, file2.md, file3.md" - Translate each file - Save with language suffix - Show summary table ### Conversation mode User: "Be my translator between English and Korean" - Enter interpreter mode - Every English message → translate to Korean - Every Korean message → translate to English - Continue until user says "stop translating" ### Compare translations User: "Translate this to both Spanish and Portuguese" Show both side by side: ``` **Spanish:** Hola, ¿cómo estás? **Portuguese:** Olá, como você está? ``` ## Special Handling ### Code comments When translating code files, ONLY translate comments and strings — never translate code: ```python # This is a comment → # これはコメントです variable_name = "Hello" # Keep variable, translate string → variable_name = "こんにちは" ``` ### Technical documents For README, docs, papers: - Keep all code blocks untranslated - Keep URLs, paths, and commands untranslated - Translate headers, descriptions, and prose - Keep the same structure ### Common language codes en, es, fr, de, it, pt, zh, ja, ko, vi, th, ar, hi, ru, pl, nl, sv, da, fi, no, tr, id, ms ## Rules - Never add your own content — only translate what's there - If a word has no good translation, keep the original in parentheses: "cocotb (cocotb)" - For proper nouns (names, brands, places), keep the original unless there's a standard localization - If unsure about context, ask before translating - Always show the language pair: "X → Y"
识别并去掉文本里的 AI 写作痕迹,让文字读起来更像人写。
把文本里 AI 写作的典型痕迹挑出来并改写得更自然,同时保留原意的写作编辑技能。
识别并去除 AI 生成文本痕迹的中文文字编辑技能。
wechat-search 检索公众号热门文章,并按相关性、热度和时效整理结果。
从公开短视频分享链接提取标题、简介和口播文案,并给出改写版本。
humanizer 为中英文文本提供更自然的表达和风格编辑指导。
写网文章节并按文件落盘,聊天里只回摘要与指针。
把一组营销方法模块收进同一个技能,按请求路由到对应模块取清单与可交付稿。
数据月份:2026-09 · 下载/星标/安装数聚合自公开技能注册库(ClawHub、SkillHub),按月更新。口径说明见数据方法。