agentsclimarketplace

Readme bilingual

Skill nicaijimi/readme-bilingual

Install
npx -y skills add nicaijimi/readme-bilingual

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Generate a high-quality bilingual (Chinese/English) README from a single-language source. Not just translation — adapts idioms, explains culture-specific references, and follows technical writing conventions in both languages. Trigger when the user asks to create a Chinese or English version of their README, docs, or any technical text.

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

8.2 KB, as published. Nobody here has run it

README Bilingual Generator (技术文档中英双语生成器)

Generate a high-quality bilingual README from a single-language source. This is NOT machine translation — it's cultural and technical adaptation for the target audience.

What Makes This Different From Translation

Machine TranslationThis Skill
Translates wordsAdapts meaning for the target audience
"微信小程序" → "WeChat applet"→ "WeChat Mini Program (a lightweight app within WeChat)"
"科学上网" → "scientific internet access"→ (flagged as potentially sensitive, suggests neutral alternative)
Preserves sentence structureRestructures to natural target-language conventions
Loses Chinese-specific contextAdds brief explanations for non-Chinese readers

Workflow

Step 1: Detect Source Language and Direction

Read the input and determine:

  • Is it primarily in Chinese? → Generate English version
  • Is it primarily in English? → Generate Chinese version
  • Mixed? → Ask the user which direction they want

Step 2: Run the Adaptation Pipeline

When generating Chinese → English:

  1. Translate terminology consistently. Use standard English equivalents:

    • 小程序 → Mini Program (capitalized, with brief explanation on first use)
    • 云开发 → CloudBase (WeChat Cloud Development)
    • 微信支付 → WeChat Pay
    • 支付宝 → Alipay
    • 抖音 → Douyin (TikTok's Chinese counterpart)
    • 企业微信 → WeCom (WeChat Work)
  2. Explain China-specific context. Non-Chinese readers won't know:

    • What WeChat Mini Programs are → add 1-sentence explanation on first mention
    • Why something needs ICP filing → add brief note
    • What 备案 means → "ICP filing (required for hosting in mainland China)"
  3. Adapt sentence structure to natural English.

    • Chinese topic-comment → English subject-verb-object
    • Chinese paratactic clauses → English hypotactic (explicit connectors)
    • Chinese implicit logic → English explicit transitions (therefore, however, because)
  4. Adjust tone. Chinese technical docs can be more formal; English readers expect directness:

    • "本文档旨在介绍..." → "This guide covers..."
    • "欢迎使用本项目" → "## Overview" (no welcome needed in English README)
  5. Preserve unmodified:

    • All code blocks, inline code, file paths, URLs, API endpoints
    • Version numbers, dates, technical identifiers
    • Shell commands and command output

When generating English → Chinese:

Apply the full chinese-doc-optimizer pipeline plus:

  1. Don't over-translate. Keep these in English:

    • Well-known tech terms: API, SDK, CLI, npm, Git, React, Vue, Docker
    • Company/product names: GitHub, Vercel, Stripe
    • File extensions: .json, .ts, .js
  2. Add spaces around English in Chinese text. 使用 React 构建 not 使用React构建

  3. Translate idiomatic expressions naturally.

    • "batteries included" → "开箱即用"
    • "under the hood" → "底层实现"
    • "quickstart" → "快速开始"
    • "Gotchas" → "常见问题/注意事项"
  4. Add China-specific context when relevant.

    • If the tool uses services blocked in China (Google APIs, OpenAI), add a note
    • If there's a Chinese mirror or alternative, mention it

Step 3: Format the Bilingual Output

Generate the output in this structure:

# Project Name (中文名)

[English version first, then Chinese]

---

## English

[Complete English README]

---

## 中文

[Complete Chinese README]

Or, if the user prefers side-by-side sections:

For each section, present both languages:

## Installation | 安装

[English instructions]

[中文说明]

Default to the stacked format unless the user requests side-by-side.

Step 4: Add a Language Switcher Badge (Optional)

If the user is generating for a GitHub repo, suggest adding shields.io badges:

[![README English](https://img.shields.io/badge/README-English-blue)](README.md)
[![README 中文](https://img.shields.io/badge/README-中文-red)](README.zh.md)

Terminology Table (Chinese ↔ English)

中国互联网生态专有词汇

中文EnglishAdd Context?
微信小程序WeChat Mini Program✅ Explain: "lightweight apps that run inside WeChat"
公众号Official Account / WeChat Public Account
微信支付WeChat Pay
支付宝Alipay
企业微信WeCom (WeChat Work)
飞书Feishu (Lark)✅ Note: "Lark" is the international version
钉钉DingTalk
备案 / ICP备案ICP Filing✅ Explain requirement
域名备案Domain ICP Filing
科学上网(Flagged — suggest neutral alternative like "国际网络访问")N/A
云开发CloudBase / Cloud DevelopmentDepends on platform
小程序云开发WeChat CloudBase
微信开发者工具WeChat DevTools
审核/提审App Review / Submit for Review
微信开放平台WeChat Open Platform
微信公众平台WeChat Official Accounts Platform
腾讯云Tencent Cloud
阿里云Alibaba Cloud / Aliyun
华为云Huawei Cloud
抖音Douyin (TikTok's Chinese counterpart)
小红书Xiaohongshu / RED
B站Bilibili
知乎Zhihu
稀土掘金Juejin (rare earth)
开源中国OSChina / Gitee
码云Gitee

通用技术词汇

中文 (Common but awkward)✅ Better ChineseEnglish
安装指南 / 如何安装安装 / 快速开始Installation / Quickstart
运行此项目本地运行 / 启动Getting Started / Running Locally
我们提供以下功能...功能:/ 支持:Features
如何贡献代码参与贡献Contributing
常见问题解答常见问题 / FAQFAQ
更新日志更新日志 / CHANGELOGChangelog
协议 / 许可证开源许可License

Anti-Patterns (Never Do This)

  • ❌ Do NOT remove any code blocks, inline code, URLs, file paths, or shell commands
  • ❌ Do NOT change the meaning of any technical statement
  • ❌ Do NOT remove sections that "don't apply to the target audience" — translate everything
  • ❌ Do NOT use machine-translation patterns like "关于这个 API 的详细说明" → use "API 文档" or "接口说明"
  • ❌ Do NOT translate well-known tech terms that are standard in both languages (API, URL, JSON, npm, Git)
  • ❌ Do NOT add content that wasn't in the original (no feature suggestions, no additional warnings unless they're China-specific safety notes)
  • ❌ For China-specific content warnings: DO add brief, neutral notes (e.g., "Note: this service requires ICP filing to host in mainland China") — but don't editorialize

Quality Checklist

Before outputting, verify:

  • All code blocks are identical to the source (including indentation and comments)
  • All URLs and file paths are preserved exactly
  • Terminology is consistent throughout (same Chinese term → same English term every time)
  • China-specific references include brief explanations for non-Chinese readers
  • The target language version reads as if it was originally written in that language
  • No markdown syntax is broken (headings, links, tables, code fences)
  • First mention of a China-specific platform (WeChat, Alipay, DingTalk) includes context

Gives 0 of the 12 instructions most readme changelog skills give

Counted across 471 of the 478 authors here whose files we hold, read 2026-08-06

  • follow the Keep a Changelog formatin 31 of 471, across 26 files
  • omit empty sectionsin 21 of 471
  • Run from the git repository rootin 20 of 471, across 7 files
  • save output directly to CHANGELOG.mdin 20 of 471, across 7 files
  • Group commits into logical categoriesin 19 of 471, across 6 files
  • Review the generated changelog before publishingin 19 of 471, across 6 files
  • Apply changelog guidelines and brand voicein 18 of 471, across 5 files
  • Exclude internal commits like refactoring and testsin 18 of 471, across 5 files
  • Specify date ranges for focused changelogsin 17 of 471, across 4 files
  • Convert technical commits into customer languagein 17 of 471, across 4 files
  • group commits by conventional commit typein 14 of 471
  • insert new entry below unreleased sectionin 14 of 471

Said here and by no other author read

  • detect the primary source language
  • adapt cultural and technical context for the target audience
  • explain china-specific context on first mention
  • restructure sentences to natural target-language conventions
  • preserve all code paths urls and identifiers unmodified
  • keep well-known technical terms untranslated

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.