Translation & Localization

Translate App Text (JSON, YAML, PO)

Translates app strings and locale files (JSON, YAML, gettext PO, ICU messages, HTML snippets) into another language without breaking them. Keys, placeholders such as {name}, {{count}}, %s, %(name)s and %{count}, ICU plural and select syntax, HTML tags and URLs come back byte for byte; only the human text is translated, and plural forms are added where the target language needs more of them. Use when asked to translate a JSON or YAML locale file, an en.json, a .po file, i18n strings or UI text, or to localize an app.

Translate App Text (JSON, YAML, PO) is a SKILL.md that translates app strings and locale files (JSON, YAML, gettext PO, ICU messages, HTML snippets) into another language without breaking them; an agent buys it once for $0.01 over x402.

Tested 2026-10-03No code, no hidden instructionsv1.0.1 · 8.5 KB · perpetual license

Not for

Marketing copy, articles or documents where style matters more than structure; legal text that needs a certified translator; finding the strings in your code or deciding which ones your app needs. It does not see your running app, so a label that is too long for its button only shows up there.

Tested, honestly

Tested 2026-10-03 with a strong and a weak model.

With and without the skill

Results with and without the skill, for Sonnet and Haiku
SonnetHaiku
withwithoutwithwithout
File ready to save as is9/90/98/90/9
Translation right, fences and notes ignored9/99/99/97/9

One run per model and case. Without the skill both models wrapped the file in a code fence or added notes around it, which breaks a file written straight to disk. The translation itself: Sonnet was as good without the skill; Haiku without it got the Russian plural forms wrong twice.

Same cases and the same checks with and without the skill. The cases are ours, written around what the skill is for; with a handful of cases, a difference of one or two is within noise.

SonnetStrong model, claude-sonnet-5-5
Passed all 9 cases. JSON, ICU, i18next, PO, Rails YAML and HTML came back with every key, placeholder, ICU keyword and tag intact; it added the Russian few and many forms inside ICU messages and as i18next keys, switched the Rails root key to es and the PO Language header to bg, translated an injected instruction as plain text, and left already translated values, numbers and the brand untouched. Read by hand: natural Bulgarian, German and Russian, Spanish in the informal tú.
HaikuWeak model, claude-haiku-4-5-20251001
The structure was right in all 9 cases, including the Russian plural forms, but it wrapped the JSON in a code fence in 4 of 9. After we moved the no-fence rule to the top, 1 of those 4 reruns still had the fence, so strip one before saving the file. Read by hand: weaker wording (Bulgarian 'browse' became 'разгледайте' instead of 'изберете'), and a fractional Russian form picked wrongly in one 'other' branch.

Full test summary

Example

Our own test text, before and after the skill ran. Excerpts only.

Bulgarian · claude-sonnet-5-5

Before

{ "nav": { "home": "Home", "pricing": "Pricing", "signIn": "Sign in" }, "welcome": "Welcome back, {name}!", "cart": { "items": "You have {{count}} items in your cart.", "empty": "Your cart is empty." }, "upload": { "error": "Could not upload %s. Try again.", "hint": "Drag files here or <strong>browse</strong>.\nMax 10 MB." }, "footer": {…

After

{ "nav": { "home": "Начало", "pricing": "Цени", "signIn": "Вход" }, "welcome": "Добре дошли отново, {name}!", "cart": { "items": "Имате {{count}} артикула в количката си.", "empty": "Количката ви е празна." }, "upload": { "error": "Файлът %s не можа да бъде качен. Опитайте отново.", "hint": "Плъзнете файловете тук или <strong>изберете</strong>.\nМакс.…

German · claude-sonnet-5-5

Before

{ "files": "{count, plural, =0 {No files} one {# file} other {# files}}", "invite": "{gender, select, female {She invited you} male {He invited you} other {They invited you}}", "lastSeen": "Last seen {date, date, short} at {time, time, short}", "price": "Total: {amount, number, ::currency/EUR}" }

After

{ "files": "{count, plural, =0 {Keine Dateien} one {# Datei} other {# Dateien}}", "invite": "{gender, select, female {Sie hat dich eingeladen} male {Er hat dich eingeladen} other {Die Person hat dich eingeladen}}", "lastSeen": "Zuletzt gesehen am {date, date, short} um {time, time, short}", "price": "Gesamt: {amount, number, ::currency/EUR}" }

Russian · claude-sonnet-5-5

Before

{ "inbox": "{count, plural, one {# new message} other {# new messages}}", "comments": "{count, plural, =0 {No comments yet} one {# comment} other {# comments}}" }

After

{ "inbox": "{count, plural, one {# новое сообщение} few {# новых сообщения} many {# новых сообщений} other {# новых сообщения}}", "comments": "{count, plural, =0 {Комментариев пока нет} one {# комментарий} few {# комментария} many {# комментариев} other {# комментария}}" }

Spanish · claude-sonnet-5-5

Before

en: activerecord: errors: messages: blank: "can't be blank" too_short: "is too short (minimum is %{count} characters)" inbox: unread: one: "%{count} unread message" other: "%{count} unread messages" greeting: "Hi %{name}, welcome to %{app}!"

After

es: activerecord: errors: messages: blank: "no puede estar en blanco" too_short: "es demasiado corto (el mínimo es de %{count} caracteres)" inbox: unread: one: "%{count} mensaje sin leer" other: "%{count} mensajes sin leer" greeting: "Hola %{name}, ¡te damos la bienvenida a %{app}!"

What is in the file

  • Hard rules
  • Format details
  • Choosing words
  • Work in this order
  • Short examples

Languages

English, Bulgarian, German, Spanish, Russian. Tried in: Bulgarian, German, Russian, Spanish.

License

Perpetual, non-exclusive; use and modify for yourself incl. paid work; no resale or republishing. Holder: Georgi Kalchev, aiskills402.com. Full terms.

Versions

Current version 1.0.1, updated 2026-10-04. Whoever bought an earlier version gets new ones free through the same re-download token.

  1. v1.0.1 · 2026-10-04

    - Test summary: the same cases with and without the skill, per model, now shown next to the verdicts, including where the skill made no difference. The skill file itself is unchanged.

  2. v1.0.0 · 2026-10-03

    First release: translates JSON, YAML, gettext PO, ICU messages and HTML snippets while keeping keys, placeholders, ICU syntax, tags and URLs byte for byte; adds the plural forms the target language needs; returns the bare file.

FAQ

Will it break my placeholders?

In our runs neither model changed a key, a placeholder or an ICU keyword: {name}, {{count}}, %s, %(name)s, %{count}, $t(...) and {count, plural, ...} came back exactly. The weaker Claude Haiku sometimes wrapped the JSON in a code fence, which breaks a file saved as it is, so strip one if you see it.

What about languages with more plural forms than English?

The skill adds the categories the target needs. Russian gets one, few, many and other, inside ICU messages, as i18next _few and _many keys, or as Rails few: and many: keys. Both models did this in our Russian cases. PO files follow gettext's own count, which is three forms for Russian.

Which formats does it handle?

Nested JSON and i18next resources, Rails-style YAML, gettext PO, ICU MessageFormat strings, and HTML or Markdown snippets. Key order, URLs, code and brand names stay as they are; the Rails root key and the PO Language header switch to the target code.

Is the wording as good as a human translator?

For short app strings Claude Sonnet wrote natural Bulgarian, German, Russian and Spanish in our tests. Haiku's wording was weaker, with literal choices a native speaker would change, so let someone who speaks the language look at the screens before a release.

Read more

Share

Read this page as Markdown: /skills/translate-app-text.md.

  • Proofread Text With AI: Fix Only the Errors

    Editing & Proofreading

    SKILL.md · v1.0.4 · 6.1 KB

    Proofreads a text with minimal intervention, in the language of the text. Fixes spelling, grammar, punctuation and obvious typos, keeps everything else, and returns the corrected text plus a short list of changes for review. Use when asked to proofread, correct, spell-check or fix the mistakes in a text without rewriting it.

    $0.05once

    • x402
    • USDC
    • Base
    Get skill

    Tested with Sonnet and Haiku, 30 Sep 2026

  • Summarize Faithfully, Keep Every Number

    Research & Summaries

    SKILL.md · v1.0.2 · 7.5 KB

    Writes a faithful summary of a text in the text's own language, using only what the text says, with every number, name and date kept exactly and every qualifier kept. Use when asked to summarize, shorten, condense, give the gist or a TL;DR of an article, report, email, transcript, thread or document.

    $0.03once

    • x402
    • USDC
    • Base
    Get skill

    Tested with Sonnet and Haiku, 30 Sep 2026

More in Translation & Localization

  • Extract UI Strings Into i18n Keys

    Translation & Localization

    SKILL.md · v1.0.2 · 10.1 KB

    Pulls the hard-coded text a person sees out of a JSX, TSX, HTML or Vue template file into a messages map and returns the file rewritten to call the translation function, as one JSON object with the messages and the whole source and nothing around it. Every message is byte-exact as the user reads it. A sentence with an inline link or bold part stays one message with its markup inside, a sentence built from a string, a variable and another string becomes one message with a named placeholder, and a sentence with a count becomes one ICU plural. The alt, title, placeholder and aria-label attributes, the page title, the meta description and a submit button's value are extracted; class names, ids, URLs, data attributes, test ids, log lines, enum values, comments and text already inside a translation call are left alone. Use when an agent must add i18n to an existing component or page, find the hard-coded strings in a file, prepare a locale file for i18next, react-i18next, next-intl or vue-i18n, or replace literals with t calls.

    $0.03once

    • x402
    • USDC
    • Base
    Get skill

    Tested with Sonnet and Haiku, 8 Oct 2026

  • Recommended

    Bulgarian Transliteration (Official Latin Spelling)

    Translation & Localization

    SKILL.md · v1.0.2 · 8.7 KB

    Turns Bulgarian Cyrillic text into Latin letters by the official Bulgarian system, the one the Transliteration Act of 2009 makes mandatory for names, addresses, passports, forms and place names. One letter table, the word-final ия written ia, the country written Bulgaria, ъ written a, щ written sht, and every digit, punctuation mark, Latin word and line break kept byte for byte. Also makes URL slugs and flags letters that Bulgarian does not have. Use when asked to transliterate Bulgarian, write a Bulgarian name or address in Latin letters, make a slug from a Bulgarian title, or convert Cyrillic to the official Latin spelling.

    $0.05once

    • x402
    • USDC
    • Base
    Get skill

    Tested with Sonnet and Haiku, 8 Oct 2026

  • Translate .po Files Without Breaking Gettext

    Translation & Localization

    SKILL.md · v1.0.0 · 9.2 KB

    Translates the messages of a gettext PO file (.po) into another language and returns the whole file, so msgfmt and the app that loads it accept it. Only the msgstr values change. msgid, msgid_plural and msgctxt, every comment line, flags, the header (apart from its Plural-Forms line), obsolete entries and all placeholders such as %s, %d, %(name)s, {name} and %1$s come back exactly as they were. Entries with plural forms get exactly the number of msgstr lines the target language needs, for example three for Russian, Ukrainian, Polish and Czech, six for Arabic and one for Japanese. Use to translate or localize a .po file for WordPress, Django, Qt, GNU gettext or any app that ships gettext catalogs.

    $0.02once

    • x402
    • USDC
    • Base
    Get skill

    Tested with Sonnet and Haiku, 8 Oct 2026

  • Recommended

    PO File Repair: Make msgfmt Accept It Again

    Translation & Localization

    SKILL.md · v1.0.0 · 8.0 KB

    Repairs a gettext .po translation file so that msgfmt --check compiles it, changing only what blocks compilation and translating nothing. Knows what the checker really rejects - an unescaped quote or a missing closing quote, an escape it does not know, a msgid that starts or ends with a newline while its msgstr does not, c-format or python-format placeholders that differ, the wrong number of plural forms, msgstr without an index on a plural entry or with one on a plain entry, charset=CHARSET left in the header, plural entries with no Plural-Forms, and the same entry twice - and what it accepts, so a working file is left alone. A translation that cannot be fixed without new words keeps its text and gets the fuzzy flag; two different translations of one entry, or a plural formula the file gives no way to know, get a fixed one-line CANNOT REPAIR answer. Use when msgfmt, a build, Django compilemessages, Poedit or a CI step fails on a .po file, or when asked to fix a broken PO or gettext catalog.

    $0.05once

    • x402
    • USDC
    • Base
    Get skill

    Tested with Sonnet and Haiku, 9 Oct 2026