Agent skill

I18n Check

by zhimaAi in zhimaAi/ChatClaw

检查并补充前端和后端的i18n翻译文件。以中文(zh-CN)为基准,检查其他语言翻译文件是否缺少key,并补充缺失的key和对应的翻译值。对于日语(ja-JP)、韩语(ko-KR)、繁体中文(zh-TW),使用与非CJK语言对比的方式检测未翻译内容。

GPL-3.0Auto-check passedFrontend & Design

Install I18n Check

skills CLI
$ npx skills add zhimaAi/ChatClaw --skill i18n-check -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install zhimaAi/ChatClaw i18n-check --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/zhimaAi/ChatClaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.cursor/skills/i18n-check .claude/skills/i18n-check && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
i18n-check
GitHub stars
307
Token cost
~1.3k tokens
SKILL.md length
203 words
Files
22 (incl. scripts)
Skills in repo
2
Repo updated
First seen
Licence
GPL-3.0

At a glance

检查并补充前端和后端的i18n翻译文件。以中文(zh-CN)为基准,检查其他语言翻译文件是否缺少key,并补充缺失的key和对应的翻译值。对于日语(ja-JP)、韩语(ko-KR)、繁体中文(zh-TW),使用与非CJK语言对比的方式检测未翻译内容。

  • Works in 5 steps: 只在必要范围格式化翻译文件(建议从后端/英文开始) → 对比翻译差异(只读,不改文件) → 补全缺失的 key(使用中文作为占位符) → …
  • Tasks that involve Internationalization
  • SKILL.md covers 快速开始(推荐安全用法), 完整工作流程(推荐顺序), 脚本说明 and 文件位置, plus 1 more section
  • Runs Python scripts from its folder; calls python

What it does

I18n Check is an agent skill from zhimaAi/ChatClaw. 检查并补充前端和后端的i18n翻译文件。以中文(zh-CN)为基准,检查其他语言翻译文件是否缺少key,并补充缺失的key和对应的翻译值。对于日语(ja-JP)、韩语(ko-KR)、繁体中文(zh-TW),使用与非CJK语言对比的方式检测未翻译内容。

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 23 other files, including scripts (for example `scripts/apply_en_translations.py`, `scripts/auto_translate.py` and `scripts/batch_import.py`).

It sits in Frontend & Design, covering Internationalization. The repository describes itself as: ChatClaw: Get OpenClaw-like knowledge base personal AI agent in 5 mins. Sandbox-secured, ultra-small 30MB installer for macOS & Windows (install in 1 min). Connects to WhatsApp…. The licence is GPL-3.0.

When your agent uses it

  • Tasks that involve Internationalization

Example prompts

  • “/i18n-check”

Requirements

  • Python 3

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. 只在必要范围格式化翻译文件(建议从后端/英文开始)
  2. 对比翻译差异(只读,不改文件)
  3. 补全缺失的 key(使用中文作为占位符)
  4. AI 翻译(自动检测需要翻译的内容,不会直接改 TS/JSON 文件)
  5. CJK 语言翻译后检测(翻译完成后检查是否还有未翻译)

What it can do on your machine

Read from SKILL.md and the folder at commit 24cf232. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 18 files in scripts/ (Python, from the files we listed), which the agent can run.

    Shell commands in SKILL.md call:

    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

I18n Check loads about 1.3k tokens when it runs. Until then it costs about 34 tokens; SKILL.md has 203 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~34
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from zhimaAi/ChatClaw at commit 24cf232, republished under its GPL-3.0 licence (© zhimaAi). 203 words, ~1,294 tokens.

Download SKILL.mdSave it as .claude/skills/i18n-check/SKILL.md (or your agent's skills folder). This skill also uses 21 other files; get the full folder from GitHub.
name
i18n-check
description
检查并补充前端和后端的i18n翻译文件。以中文(zh-CN)为基准,检查其他语言翻译文件是否缺少key,并补充缺失的key和对应的翻译值。对于日语(ja-JP)、韩语(ko-KR)、繁体中文(zh-TW),使用与非CJK语言对比的方式检测未翻译内容。

i18n 翻译检查与补充

快速开始(推荐安全用法)

强制前提:先用 Git 保证当前工作区是干净的(或至少 locales 相关改动可回滚),再运行下面任何脚本。

  1. 只在必要范围格式化翻译文件(建议从后端/英文开始)

    • 后端 JSON 一般是纯英文,占位少,优先安全:
    bash
    python .cursor/skills/i18n-check/scripts/format_frontend.py
    python .cursor/skills/i18n-check/scripts/format_backend.py
    • format_frontend.py 会重写所有 frontend/src/locales/*.ts:
      • 仅做语法级重排与缩进,不再对字符做任何再编码;
      • 仍然建议:先只在当前分支本地运行,确认 diff 可接受后再提交。
  2. 对比翻译差异(只读,不改文件):

    bash
    python .cursor/skills/i18n-check/scripts/compare_frontend.py
    python .cursor/skills/i18n-check/scripts/compare_backend.py
  3. 补全缺失的 key(使用中文作为占位符)

    • 推荐做法:先只对英文和后端补全,再视情况扩展到其他语言。
    bash
    # 仅补前端英文(安全范围小)
    python .cursor/skills/i18n-check/scripts/fill_frontend.py --target en-US
    
    # 补全所有前端语言(会改动所有 locales,务必在 Git 干净时使用)
    python .cursor/skills/i18n-check/scripts/fill_frontend.py
    
    # 补全所有后端语言(JSON,风险相对可控)
    python .cursor/skills/i18n-check/scripts/fill_backend.py
  4. AI 翻译(自动检测需要翻译的内容,不会直接改 TS/JSON 文件)

    bash
    # 翻译特定语言
    python .cursor/skills/i18n-check/scripts/translate_with_ai.py --target en-US
    
    # 翻译所有语言(包括 CJK 语言)
    python .cursor/skills/i18n-check/scripts/translate_with_ai.py --all --cjk
  5. CJK 语言翻译后检测(翻译完成后检查是否还有未翻译)

    bash
    # 导出 CJK 语言未翻译内容到文本文件
    python .cursor/skills/i18n-check/scripts/export_translations.py --target ja-JP --cjk
    
    # 填充后检测 CJK 语言未翻译 key
    python .cursor/skills/i18n-check/scripts/fill_frontend.py --check-cjk

完整工作流程(推荐顺序)

bash
# Step 0: 确认 Git 状态
# - 确保 frontend/src/locales 和 internal/services/i18n/locales 内的改动都可回滚
# - 不要在未提交的重要改动上直接批量格式化/补全

# Step 1: 格式化(可选,但推荐先只在后端/英文上尝试)
python .cursor/skills/i18n-check/scripts/format_frontend.py
python .cursor/skills/i18n-check/scripts/format_backend.py

# Step 2: 对比(只读)
python .cursor/skills/i18n-check/scripts/compare_frontend.py
python .cursor/skills/i18n-check/scripts/compare_backend.py

# Step 3: 补全缺失 key(中文占位)
# 先补英文,再按需扩展其他语言
python .cursor/skills/i18n-check/scripts/fill_frontend.py --target en-US
python .cursor/skills/i18n-check/scripts/fill_backend.py

# Step 4: AI 翻译(前端 + 后端)
# 脚本会自动检测需要翻译的内容并生成翻译提示(只读,不改 TS/JSON)
python .cursor/skills/i18n-check/scripts/translate_with_ai.py --all
# 仅处理后端 JSON 时,可显式指定:
# python .cursor/skills/i18n-check/scripts/translate_with_ai.py --type backend --all

# Step 5: 翻译完成后检测 CJK 语言
# 对于 ja-JP, ko-KR, zh-TW,检测是否还有未翻译内容
python .cursor/skills/i18n-check/scripts/fill_frontend.py --check-cjk
python .cursor/skills/i18n-check/scripts/translate_with_ai.py --cjk

# Step 6: 导出未翻译内容到文本,统一翻译后再导入
python .cursor/skills/i18n-check/scripts/export_translations.py --target ja-JP --cjk
# 手动翻译文本文件中的内容
python .cursor/skills/i18n-check/scripts/import_translations.py --file translation_export_ja-JP.txt

脚本说明

脚本位置

所有脚本位于 .cursor/skills/i18n-check/scripts/ 目录:

脚本用途
format_frontend.py格式化前端 TS 翻译文件
compare_frontend.py对比前端翻译差异,支持 --cjk 检测 CJK 语言
fill_frontend.py补全前端缺失的 key,支持 --check-cjk 检测 CJK 未翻译
translate_with_ai.pyAI 翻译:自动检测需要翻译的内容并生成翻译提示,支持 --cjk
export_translations.py导出未翻译内容到文本文件,支持 --cjk
import_translations.py导入翻译结果
format_backend.py格式化后端 JSON 翻译文件
compare_backend.py对比后端翻译差异
fill_backend.py补全后端缺失的 key
使用示例

对比 CJK 语言

bash
# 对比特定 CJK 语言与英文
python compare_frontend.py --target ja-JP --cjk

# 对比所有 CJK 语言
python compare_frontend.py --cjk-only

填充 CJK 语言

bash
# 填充时使用 CJK 模式
python fill_frontend.py --cjk

# 检测 CJK 语言未翻译 key
python fill_frontend.py --check-cjk

AI 翻译脚本

bash
# 翻译特定语言
python translate_with_ai.py --type frontend --target en-US

# 翻译 CJK 语言
python translate_with_ai.py --target ja-JP --cjk

# 翻译所有语言(包括 CJK)
python translate_with_ai.py --all --cjk

导出翻译

bash
# 导出 CJK 语言未翻译内容
python export_translations.py --target ja-JP --cjk
翻译检测逻辑
  • 非 CJK 语言 (en-US, de-DE, fr-FR 等): 检测含有中文的 key,需要翻译
  • CJK 语言 (zh-TW, ja-JP, ko-KR): 检测与非 CJK 语言(如 en-US)相同的 key,需要翻译成对应语言
CJK 语言特殊处理

对于日语 (ja-JP)、韩语 (ko-KR)、繁体中文 (zh-TW),采用以下检测逻辑:

  1. 对比方式: 不以 zh-CN 为基准,而是与英语等非 CJK 语言对比
  2. 检测原理: 如果某个 key 在目标语言中的值与英语相同,说明该 key 未翻译
  3. 导出格式: 显示 baseline(中文) | reference(英语) | current(当前值),便于翻译
AI 翻译流程
  1. 运行 translate_with_ai.py 脚本
  2. 脚本会自动:
    • 读取目标语言文件
    • 检测需要翻译的中文内容(或 CJK 未翻译内容)
    • 生成 AI 翻译提示 (prompt)
  3. 将生成的提示复制给 AI 进行翻译
  4. AI 返回 JSON 格式的翻译结果
  5. 使用 import_translations.py 导入翻译结果

文件位置

类型目录格式基准文件CJK 基准文件
前端frontend/src/locales/TypeScript .tszh-CN.tsen-US.ts
后端internal/services/i18n/locales/JSON .jsonzh-CN.jsonen-US.json

注意事项

  • 保持 key 结构: 必须与基准文件完全一致,使用相同的嵌套层级
  • 不要删除任何内容: 只能添加缺失的 key,不能删除现有的 key
  • 变量占位符: 后端 JSON 使用 {{.xxx}} 格式,前端使用 {xxx} 格式,必须保留
  • 格式化后再对比: 每次对比前先运行格式化脚本,确保格式统一
  • CJK 语言处理: 繁体中文(zh-TW)、日语(ja-JP)、韩语(ko-KR)使用英语(en-US)作为基准文件进行对比和填充

© zhimaAi, GPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 21 other files (scripts) in .cursor/skills/i18n-check of zhimaAi/ChatClaw.

  • SKILL.md
  • scripts/__pycache__/fill_frontend.cpython-310.pyc
  • scripts/apply_en_translations.py
  • scripts/auto_translate.py
  • scripts/batch_import.py
  • scripts/compare_backend.py
  • scripts/compare_frontend.py
  • scripts/export_translations.py
  • scripts/fill_backend.py
  • scripts/fill_frontend.py
  • scripts/format_backend.py
  • scripts/format_frontend.py
  • scripts/generate_translation_prompts.py
  • scripts/get_cjk_translations.py
  • scripts/import_all_translations.py
  • scripts/import_bn_bd.py
  • scripts/import_cjk_translations.py
  • scripts/import_en_us.py
  • scripts/import_translations.py
  • … and 3 more

Open the folder on GitHubat commit 24cf232

Compare with similar skills

I18n Check next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

I18n Check compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
I18n Check this skillzhimaAi/ChatClaw307—~1.3kAutomated safety check: PassGPL-3.0
Impeccablebestofjs/bestofjs3.1k26 repos~2.6kAutomated safety check: PassMIT
Chatbox i18n Translatorchatboxai/chatbox42k—~508Automated safety check: PassGPL-3.0
Internationalization Workflow with i18niOfficeAI/AionUi33k1 repos~1.9kAutomated safety check: PassApache-2.0
Enforce Rules For I18nmoeru-ai/airi50k—~1.5kAutomated safety check: PassMIT
Claude Desktop Chinese Localizationjavaht/claude-desktop-zh-cn7.5k—~1.6kAutomated safety check: PassMIT

Similar skills

  • Impeccable

    bestofjs/bestofjs

    A skill your agent uses when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a…

    3.1k GitHub starsUsed in 26 repos~2.6k tokens
    Frontend & DesignAuto-check passed
  • Chatbox i18n Translator

    chatboxai/chatbox

    Translates new or changed i18n keys from a Chatbox Pro diff, staged changes or a commit range, writing the locale JSON files directly with a built-in glossary.

    42k GitHub stars~508 tokensUpdated 16 days ago
    Frontend & DesignAuto-check passed
  • Standards for keeping all user-facing text translatable: read the i18n config first, use namespaced keys, reuse shared strings and follow the key naming rules.

    33k GitHub starsUsed in 1 repo~1.9k tokens
    Frontend & DesignAuto-check passed
  • Review pending AIRI translations on Crowdin in a batch, then sync them into the repository.

    50k GitHub stars~1.5k tokensUpdated today
    Frontend & DesignAuto-check passed
  • Claude Desktop Chinese Localization

    javaht/claude-desktop-zh-cn

    Adds missing Simplified and Traditional Chinese translations to the Claude Desktop Chinese patch across three layers, then checks how many mappings actually hit.

    7.5k GitHub stars~1.6k tokensUpdated 5 days ago
    Frontend & DesignAuto-check passed
  • Taro UI Guide

    jd-opensource/taro-ui

    Guides installing, configuring, styling and using taro-ui (At* components) in Taro apps for WeChat, Alipay, H5 and React Native.

    4.7k GitHub stars~1.3k tokensUpdated 15 days ago
    Frontend & DesignAuto-check passed

More from zhimaAi/ChatClaw

  • Readme From DOCX

    zhimaAi/ChatClaw

    Update README and docs/readmes from Word docx (English and Chinese).

    307 GitHub stars~2k tokensUpdated 5 mo ago
    Auto-check passed

Questions about I18n Check

What does I18n Check do?

检查并补充前端和后端的i18n翻译文件。以中文(zh-CN)为基准,检查其他语言翻译文件是否缺少key,并补充缺失的key和对应的翻译值。对于日语(ja-JP)、韩语(ko-KR)、繁体中文(zh-TW),使用与非CJK语言对比的方式检测未翻译内容。. I18n Check is an agent skill from zhimaAi/ChatClaw.

When should I use I18n Check?

I18n Check fits situations like: tasks that involve Internationalization.

How do I install I18n Check in Claude Code?

Run `npx skills add zhimaAi/ChatClaw --skill i18n-check -a claude-code`. Or copy the skill folder (.cursor/skills/i18n-check in zhimaAi/ChatClaw) into .claude/skills/i18n-check in your project. Claude Code loads it when a task matches its description.

How do I install I18n Check in Codex?

Run `npx skills add zhimaAi/ChatClaw --skill i18n-check -a codex`. Or copy the skill folder (.cursor/skills/i18n-check in zhimaAi/ChatClaw) into .agents/skills/i18n-check in your project. Codex loads it when a task matches its description.

Can I use I18n Check in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add zhimaAi/ChatClaw --skill i18n-check -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/i18n-check, .gemini/skills/i18n-check, .github/skills/i18n-check and .opencode/skills/i18n-check in your project.

What does I18n Check need to run?

Going by SKILL.md and its folder, I18n Check needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.

Does I18n Check access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is I18n Check safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does I18n Check use?

I18n Check is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does I18n Check use?

About 1.3k tokens (SKILL.md is roughly 5.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to I18n Check?

Skills that share tags, products or a category with I18n Check: Impeccable (bestofjs/bestofjs, 3.1k stars), Chatbox i18n Translator (chatboxai/chatbox, 42k stars), Internationalization Workflow with i18n (iOfficeAI/AionUi, 33k stars) and Enforce Rules For I18n (moeru-ai/airi, 50k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains I18n Check?

zhimaAi (a GitHub organization) maintains it in zhimaAi/ChatClaw, which has 307 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on May 13, 2026.

Source: zhimaAi/ChatClaw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.