translate
Sync `messages/en.json` and `messages/ja.json` for this repository. Use when the user asks to update translations, fill missing Japanese strings, or remove stale i18n keys. Run `bun run build` before reading translations, then add missing Japanese entries, fill empty values, remove stale keys, preserve key order from `en.json`, and keep placeholders, ICU syntax, and brand names unchanged.
Best use case
translate is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Sync `messages/en.json` and `messages/ja.json` for this repository. Use when the user asks to update translations, fill missing Japanese strings, or remove stale i18n keys. Run `bun run build` before reading translations, then add missing Japanese entries, fill empty values, remove stale keys, preserve key order from `en.json`, and keep placeholders, ICU syntax, and brand names unchanged.
Teams using translate should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/translate/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How translate Compares
| Feature / Agent | translate | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Sync `messages/en.json` and `messages/ja.json` for this repository. Use when the user asks to update translations, fill missing Japanese strings, or remove stale i18n keys. Run `bun run build` before reading translations, then add missing Japanese entries, fill empty values, remove stale keys, preserve key order from `en.json`, and keep placeholders, ICU syntax, and brand names unchanged.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
Sync translations between `messages/en.json` and `messages/ja.json`.
1. Run `bun run build` before reading the translation files so extracted messages are current.
2. Read `messages/en.json` and `messages/ja.json`.
3. Add any keys present in `en.json` but missing in `ja.json`.
4. Fill any `ja.json` values that are empty strings using natural Japanese.
5. Remove keys from `ja.json` that no longer exist in `en.json`.
6. Preserve the same key order as `en.json`.
7. Keep brand names untranslated.
8. Keep placeholders such as `{count}`, `{name}`, and `{date}` intact.
9. Keep ICU plural syntax intact.