메뉴
Translate JSON dictionaries and MDX content files between locales with structural integrity, SEO/GEO-aware keyword adaptation, and native-quality output. Use when translating UI strings, blog posts, service pages, or any locale-specific content.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | translator |
| description | Translate JSON dictionaries and MDX content files between locales with structural integrity, SEO/GEO-aware keyword adaptation, and native-quality output. Use when translating UI strings, blog posts, service pages, or any locale-specific content. |
Translate web content between locales. Every translation must read like it was originally written in the target language while preserving exact file structure.
Dictionaries are nested JSON objects. Keys are typically camelCase.
{
"section": {
"subsection": {
"label": "Translate this value",
"heading": "And this one"
}
}
}
Preserve exactly:
Translate:
Do NOT translate:
"href": "/audit", "href": "https://...")"value": "44%")If the source has interpolation variables ({{variable}} or {variable}),
preserve them exactly in the translated string. Do not translate variable names.
After translating dictionary files:
python .claude/scripts/validate-json-structure.py <original.json> <translated.json>
For batch locale parity checks:
python .claude/scripts/dictionary-diff.py --source en --target de --dir dictionaries
MDX files use YAML frontmatter. Fields fall into two categories:
Translate these text fields:
| Field | Notes |
|---|---|
title | Optimize for target-language search intent (see section 3) |
description | Optimize for target-language search intent |
summary | Natural adaptation, not word-for-word |
tagline | Short, punchy — adapt to target language rhythm |
Do NOT translate metadata fields (copy byte-identical):
Date fields, author, image paths, tags, status, technical metadata, ordering fields, category slugs, URLs, and any field whose value is a machine-readable identifier rather than human-readable text.
Translate:
## stays ##)[text](url))Do NOT translate:
[translated text](original-url-unchanged)#, |, -, *, >)python .claude/scripts/validate-mdx-structure.py <original.mdx> <translated.mdx>
Do not mechanically translate keywords. Optimize for how the target audience actually searches.
Title and description optimization:
Structured content preservation (for AI engine citability):
Internal linking:
A native speaker of the target language should read the content and not suspect it was translated. No translationese. No awkward calques. No word-for-word mirroring of source language sentence structure.
Use consistent terminology across all files for the same locale. Do not translate a term one way in one section and another way elsewhere.
If the project has a terminology glossary (references/terminology-glossary.md),
follow it. If not, document terminology decisions in the translation report.
Each locale can have its own reference file at references/i18n-{code}.md
containing register, grammar rules, terminology table, and brand names.
Before translating, check for references/i18n-{locale}.md for the
target locale. If no file exists, create one and document all decisions.
When creating a new locale reference, determine:
When the user wants to optimize content for AI search engines, get cited by LLMs, or appear in AI-generated answers. Also use when the user mentions 'AI SEO,' 'AEO,' 'GEO,' 'LLMO,' 'answer engine optimization,' 'generative engine optimization,' 'LLM optimization,' 'AI Overviews,' 'optimize for ChatGPT,' 'optimize for Perplexity,' 'AI citations,' 'AI visibility,' 'zero-click search,' 'how do I show up in AI answers,' 'LLM mentions,' or 'optimize for Claude/Gemini.' Use this whenever someone wants their content to be cited or surfaced by AI assistants and AI search engines. For traditional technical and on-page SEO audits, see seo-audit. For structured data implementation, see schema-markup.
Open two files side by side in VSCodium diff view. Use when comparing original vs modified, before vs after, or any two files.
When the user wants to plan a content strategy, decide what content to create, or figure out what topics to cover. Also use when the user mentions "content strategy," "what should I write about," "content ideas," "blog strategy," "topic clusters," "content planning," "editorial calendar," "content marketing," "content roadmap," "what content should I create," "blog topics," "content pillars," or "I don't know what to write." Use this whenever someone needs help deciding what content to produce, not just writing it. For writing individual pieces, see copywriting. For SEO-specific audits, see seo-audit. For social media content specifically, see social-content.
When the user wants to write, rewrite, or improve marketing copy for any page — including homepage, landing pages, pricing pages, feature pages, about pages, or product pages. Also use when the user says "write copy for," "improve this copy," "rewrite this page," "marketing copy," "headline help," "CTA copy," "value proposition," "tagline," "subheadline," "hero section copy," "above the fold," "this copy is weak," "make this more compelling," or "help me describe my product." Use this whenever someone is working on website text that needs to persuade or convert. For email copy, see email-sequence. For popup copy, see popup-cro. For editing existing copy, see copy-editing.
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
First-run onboarding for a new project. Scans for unfilled {CONFIGURE:} placeholders, asks project-specific questions, fills them in, and logs decisions.