claude-desktop-zh-localize

claude-desktop-zh-localize is a skill for Claude Code, Codex from javaht/claude-desktop-zh-cn. It costs 113 tokens per session (3,324 once invoked), scanned A, original, MIT.

A localization workflow for adding Simplified and Traditional Chinese translations to the Claude Desktop interface. It handles normal translation keys, text built directly into the interface, and changing text such as dates or counts.

In plain words
What is it for?
Use it when a user shares a Claude Desktop screenshot with English text or asks to update the Chinese interface for a newer version. It supports Chinese translations for macOS and Windows builds.
Why use it?
It helps find the right place for each untranslated phrase instead of applying a translation that only works in one part of the app. It also checks whether the added mappings match the interface text.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument.

Good fit Use it when a user shares a Claude Desktop screenshot with English text or asks to update the Chinese interface for a newer version. It supports Chinese translations for macOS and Windows builds.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/javaht/claude-desktop-zh-cn/claude-desktop-zh-localize
About the project

claude-desktop-zh-cn is a local patch that adds Simplified Chinese and two Traditional Chinese variants to the Claude Desktop interface. It is for Claude Desktop users on macOS, Windows, or Debian-based Linux installations who want a Chinese user interface. The catalogue entry is the patch's installation skill.

javaht/claude-desktop-zh-cn · 7,727 stars · on GitHub · javaht.github.io

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add javaht/claude-desktop-zh-cn --skill claude-desktop-zh-localize
Clone the repo
git clone --depth 1 https://github.com/javaht/claude-desktop-zh-cn

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for claude-desktop-zh-localize

README.md
[![agentmods](https://agentmods.dev/badge/skills/javaht/claude-desktop-zh-cn/claude-desktop-zh-localize/github.svg)](https://agentmods.dev/skills/javaht/claude-desktop-zh-cn/claude-desktop-zh-localize)
Your own site
<a href="https://agentmods.dev/skills/javaht/claude-desktop-zh-cn/claude-desktop-zh-localize"><img src="https://agentmods.dev/badge/skills/javaht/claude-desktop-zh-cn/claude-desktop-zh-localize/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for claude-desktop-zh-localize

Your own site · 80×15
<a href="https://agentmods.dev/skills/javaht/claude-desktop-zh-cn/claude-desktop-zh-localize"><img src="https://agentmods.dev/badge/skills/javaht/claude-desktop-zh-cn/claude-desktop-zh-localize.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 113 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,324 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00113 $0.03324
Opus 5.5 $0.00045 $0.01330
Sonnet 5.5 $0.00023 $0.00665
Haiku 4.5 $0.00011 $0.00332

Measured 6d ago against content hash 9be793edc9a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

claude-desktop-zh-localize scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/verify_mapping.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/claude-desktop-zh-localize/SKILL.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Desktop 中文补丁 · 汉化工作流

本项目是 Claude Desktop 的本地中文补丁。界面文本通过三层机制汉化,新增翻译时必须按目标文本的性质选择正确的层,三层全部落位后统一验证。

三层汉化机制

层 文件 作用范围
1. i18n 键值词表 resources/frontend-zh-{zh-CN,zh-TW,zh-HK}.json 走 react-intl 的标准组件。合并进应用的 zh-*.json,有 key 即原生显示中文
2. 硬编码词表 resources/frontend-hardcoded-zh-*.json([源文, 译文] 二元组列表) 未走 i18n 的前端 bundle 文本(安装时静态替换 JS),同时并入在线 DOM 翻译映射
3. DOM 动态正则 scripts/patch_claude_zh_cn.py 的 build_online_dom_translation_script() 中 G=[...] 数组;Windows 同款模板在 scripts/install_windows.ps1 动态文本:计数、日期、时间区间、带变量的句子。两个引擎必须同步修改

桌面壳层文本(极少)放 resources/desktop-zh-*.json。

工作流

第 1 步:定位 i18n key

在已安装应用的英文语言包中按值精确匹配(项目词表只保留当前版本存在的 key):

import json
en = json.load(open("/Applications/Claude.app/Contents/Resources/ion-dist/i18n/en-US.json"))
for text in ["Theme", "Chat font"]:
    print(text, {k for k, v in en.items() if v == text})
  • 精确匹配不到时用小写子串模糊搜索,并去前端 bundle(/Applications/Claude.app/Contents/Resources/ion-dist/assets/v1/*.js;新版 Claude 可能改名或换层级,安装脚本会自动探测,找不到时在 ion-dist 下递归搜含 index-*.js 的目录)里确认组件写法。
  • 截图里的文本往往是多个 DOM 节点拼出来的(链接前后各一个 text node),要分别找。

第 2 步:确定三地译文

zh-CN / zh-TW / zh-HK 各写一份,遵守下方术语表。同一个英文值若有多个 key,全部都要写。

第 3 步:写入词表

关键机制(实测踩坑后确认):配置窗口(配置第三方推理)和主窗口首页走 react-intl + 语言包 key,DOM 注入层对它们无效!因此每条翻译必须同时写入:

  1. frontend-zh-*.json(必须有 key——在 en-US.json 里按值反查;只写硬编码对在该窗口不生效);
  2. frontend-hardcoded-zh-*.json(覆盖在线 DOM 层与本地 bundle 静态替换)。

用脚本一次性更新三个 frontend-zh-*.json(dict,key: 译文)和三个 frontend-hardcoded-zh-*.json(list of [source, target])。硬编码词表注意:

  • 弯引号与直引号各写一条(can't 与 can't 是两个不同源串);
  • 链接前后拆分的文本节点,前导节点要写"带尾随空格"和"不带"两条,例如 "...within Anthropic's guidelines. Learn more" 的前半句 Claude will keep these in mind ... within 需单独成条;
  • 被 <code> 片段拆开的句子(如 "when enabled is true"):key 的译文直接含反引号整体翻译("当 `enabled` 为 true 时……"),DOM 层则需按静态分段逐段映射;
  • CSS 大写显示的标题(如页面显示 NETWORK PROXY)实际 key 值可能是 Network proxy,按 key 原值匹配;
  • 源文与译文相同的条目会被丢弃(见陷阱 1),不能"原样保留"。

Read the full file on GitHub · 127 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 6d ago Changed 9be793edc9a7
  2. 22d ago First seen · 127 lines · 113 tokens per session scan A d97145213b89

Subscribe to this mod's changes

claude-desktop-zh-localize is a skill published in the GitHub repository javaht/claude-desktop-zh-cn (7,727 stars, last pushed 5d ago), licensed MIT. It adds 113 tokens to every session and 3,324 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-26.

Related

Other skills, from other repositories

chinese-documentation

A Chinese technical-documentation style guide covering spacing, punctuation, numbers, terminology, and links when Chinese and English appear together.

jnMetaCode/superpowers-zh · 62 tokens

azure-ai-translation-text-py

Azure AI Text Translation SDK for real-time text translation, transliteration, language detection, and dictionary lookup. Use for translating text content in applications. Triggers: "text translation", "translator", "translate text", "transliterate", "TextTranslationClient".

microsoft/skills · 60 tokens

harden

Improve interface resilience through better error handling, i18n support, text overflow handling, and edge case management. Makes interfaces robust and production-ready. Use when the user asks to harden, make production-ready, handle edge cases, add error states, or fix overflow and i18n issues.

fengshao1227/ccg-workflow · 62 tokens

seedance-vocab-ja

This skill should be used when the user asks for Japanese Seedance 2.0 prompt wording, Japanese cinematic vocabulary, or translation of camera, lighting, action, VFX, audio, and production terms into Japanese.

Emily2040/seedance-2.0 · 50 tokens

asc-subscription-localization

Bulk-localize subscription, subscription-group, and in-app purchase display names across App Store locales using asc, including API 4.4.1 version-scoped v2 resources. Use when filling or updating subscription/IAP names and descriptions without App Store Connect UI work.

rorkai/app-store-connect-cli-skills · 60 tokens

docs-governance

Use when writing, restructuring, auditing, or reviewing Cherry Studio repository documentation, READMEs, JSDoc, comments, Agent instructions, or paired English/Chinese docs, including source-linked documentation impact checks.

CherryHQ/cherry-studio · 47 tokens