Translate
Translate replaces expensive full-model translation runs by extracting empty msgstr entries from Lingui catalogs, chunking them, and dispatching Haiku subagents to translate each batch. Results merge back deterministically into your locale files with zero model overhead in the write path. Use this when you need to fill missing translations after adding new UI strings.
Translate fills missing .po catalog translations using cost-efficient Haiku subagents instead of the main model.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-07-28
Translate fills missing .po catalog translations using cost-efficient Haiku subagents instead of the main model. Translate replaces expensive full-model translation runs by extracting empty msgstr entries from Lingui catalogs, chunking them, and dispatching Haiku subagents to translate each batch. Results merge back deterministically into your locale files with zero model overhead in the write path. Use this when you need to fill missing translations after adding new UI strings.
Use it when
- Yes.
- Translate is designed with context preservation as a core principle (weighted at 0.15).
Install
crbnos/carbon/translate · repository language: TypeScript
generated, unverified - the skill's exact subdirectory could not be determined; check the repository on GitHub
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
What does Translate do?
Translate is a skill that efficiently fills missing translations in your Lingui catalogs by extracting empty msgstr entries, chunking them into batches, and dispatching Haiku subagents to translate each group. Results merge back deterministically into your locale files with zero model overhead in the write path, making it ideal for filling gaps after adding new UI strings.
Can Translate handle code or technical documentation?
Yes. Translate supports translating code comments and technical documentation as one of its core intents (weighted at 0.25). The skill preserves meaning and context during translation, ensuring technical accuracy and formatting integrity across your documentation and codebase.
How does Translate preserve meaning and context?
Translate is designed with context preservation as a core principle (weighted at 0.15). By chunking translations and using Haiku subagents, the skill maintains semantic accuracy and formatting. Results merge deterministically back into locale files, ensuring no loss of meaning or structure during the translation process.
Can I translate text between languages with Translate?
Translate specializes in converting text from one language to another (its highest-weighted intent at 0.35). It works by extracting untranslated entries from Lingui catalogs and dispatching them for translation, making it efficient for multilingual content creation and updates.
Does Translate support batch processing of documents?
Yes. Translate includes batch processing capability (weighted at 0.05) for translating multiple documents across languages. The skill chunks batches of untranslated strings and processes them through Haiku subagents, then merges results back into your locale files deterministically.
What makes Translate efficient compared to full-model translation?
Translate replaces expensive full-model translation runs by extracting only empty msgstr entries from Lingui catalogs and dispatching lightweight Haiku subagents. This approach eliminates model overhead in the write path—you only pay for actual translation work, not redundant processing of already-translated content.
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Convert text from one language to another”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
Master multi-language game development by wrapping user-facing strings with tr(), organizing translations in CSV or PO files, and switching locales at runtime through TranslationServer. This skill covers semantic key strategies, automatic Control node translation, pluralization handling, and right-to-left text support for global audiences.
Odoo i18n handles the full translation lifecycle for Odoo 14-19 modules: extracting translatable strings from Python, XML, and JavaScript into .pot templates and language-specific .po files, validating syntax and format specifiers, and managing RTL layouts for Arabic and other right-to-left languages. It includes tools for gap analysis, encoding checks, and deployment troubleshooting.
This skill covers implementing internationalization in React and vanilla JavaScript applications using Lingui. You'll learn the standard workflow—marking messages with macros, extracting and translating catalogs, then compiling and activating locales—plus patterns for pluralization, date/number formatting, and dynamic locale switching. Best practices include choosing the right macro for your context and leveraging the ESLint plugin to catch common mistakes.
This skill walks you through converting an i18next-based project to Lingui, from installing dependencies and configuring build tools through rewriting React components and translation strings. It addresses namespace mapping, plural form restructuring, and catalog format changes, then shows how to extract and compile your messages for production.
Manage translations across multiple locales in Lingui catalogs without altering source keys or compiled outputs. The skill enforces preservation of placeholders, ICU syntax, and technical terminology while providing verification scripts to catch missing translations and ensure consistency.
Software Localisation guides you through implementing internationalisation and localisation across modern web frameworks. It covers library selection (react-i18next, react-intl, vue-i18n, @angular/localize, next-intl), ICU message formatting, character encoding standards, and CI/CD workflows to prevent mixed-language regressions.