{"id":"cd93b61b-9ce7-4763-8556-15d3cb2fc498","shortId":"ncwPwz","kind":"skill","title":"blog-translate","tagline":"Translate existing blog posts into one or more target languages with SEO-optimized localization. Produces native-quality translations that preserve markdown structure, frontmatter, schema JSON-LD, image and chart embeds, and citation capsules. Localizes keywords, meta tags, numbe","description":"# Blog Translate, SEO-Optimized Blog Translation\n\nTranslates an existing blog post into one or more target languages. Unlike\ngeneric translation, this skill produces SEO-optimized, publication-ready\ncontent with localized keywords, meta tags, and culturally correct\nformatting.\n\n> Adapted from `claude-blog-multilingual` by Chris Mueller (Pro Hub Challenge,\n> March 2026). Original: https://github.com/Chriss54/multilingual-int\n\n## Key References\n\nLoad on demand:\n\n- `references/translation-rules.md`, format preservation, number/date/currency\n  formats per locale, quote handling, quality criteria.\n- `references/cultural-adaptation.md`, cultural profiles per locale (DACH,\n  Francophone, Hispanic, Japanese, custom). This file is shared with\n  `blog-localize` (do not duplicate).\n\n## Workflow\n\n### Phase 1: Input Parsing\n\n1. Read the source file (markdown, MDX, or HTML).\n2. Auto-detect source language. Order of preference:\n   - Frontmatter `lang` field.\n   - HTML `lang` attribute.\n   - Content analysis (script, common stop words).\n3. Parse target languages from `--to` as comma-separated ISO 639-1 codes\n   (`de,fr,es,ja,pt-BR`). If `--to` is missing, ask the user once: \"Which\n   languages should I translate to? Provide ISO 639-1 codes (e.g., de, fr,\n   es, ja, pt-BR).\"\n4. Validate every code. Reject invalid ones with a suggestion (`jp` becomes\n   \"Did you mean `ja` for Japanese?\"). If a target equals the source\n   language, skip it with a notice.\n\n### Phase 2: Content Analysis\n\nExtract the translatable surface:\n\n- Frontmatter: `title`, `description`, `tags`, `author` (only when\n  translatable, e.g. role labels, not personal names).\n- All headings (H1, H2, H3).\n- Body paragraphs.\n- Image `alt` text and `<figcaption>` content.\n- Chart `<text>` and `<tspan>` content; preserve every SVG attribute (`x`,\n  `y`, `font-size`, `fill`, `transform`).\n- FAQ questions and answers.\n- Citation capsule text.\n- Key Takeaways or summary box.\n- CTA text.\n- Internal-link zone anchor text.\n\nPreserve unchanged:\n\n- Markdown and HTML structure, tags, attributes.\n- Image URLs, link URLs, frontmatter keys.\n- Code blocks (translate inline comments only when meaningful).\n- Internal-link zone markers (`[INTERNAL-LINK: ...]`).\n- Source organization names in citations (Gartner, McKinsey, etc.).\n- Person names.\n- Schema JSON-LD blocks (translate only the user-facing string values).\n\nIdentify the primary and secondary keywords for Phase 3.\n\n### Phase 3: Keyword Localization\n\nFor each target language:\n\n1. Decide whether the source keyword is the established term in the target\n   market. If yes (e.g., \"Content Marketing\" stays in German), keep it.\n2. If a local equivalent has real search behavior, swap to it.\n3. Apply the same logic to secondary keywords.\n4. Record the mapping. The translator agent uses it to update title, meta\n   description, and H2 headings consistently.\n\n### Phase 4: Translation\n\nSpawn the `blog-translator` agent (via Task) for each target language with:\n\n- The source content.\n- The keyword localization map from Phase 3.\n- The target language code.\n- Pointers to `references/translation-rules.md` and the cultural profile in\n  `references/cultural-adaptation.md` if one exists for the target locale.\n\nRun agents in parallel when translating into multiple languages.\n\nThe agent returns the fully translated post in the same format as the input.\n\n### Phase 5: Post-Processing\n\nFor each translated version:\n\n1. Add or update locale frontmatter:\n   ```yaml\n   lang: \"de\"\n   translatedFrom: \"en\"\n   translatedDate: \"YYYY-MM-DD\"\n   slug: \"wie-man-ki-slop-vermeidet\"\n   ```\n2. Verify structural integrity:\n   - Same number of H2 and H3 sections as the original.\n   - All images present with translated alt text.\n   - All SVG charts present with translated text labels (length-adjusted:\n     DE +30%, FR +15%, JA -20%, others see `references/translation-rules.md`).\n   - FAQ count matches.\n   - Citation capsules present in each H2.\n3. Save translated files:\n   ```\n   translations/\n     {lang}/{localized-slug}.{ext}\n   ```\n   When invoked from `blog-multilingual`, save into\n   `multilingual/{lang}/{localized-slug}.{ext}` instead.\n\n### Phase 6: Translation-Quality Guardrails\n\nScan the output for machine-translation artifacts before reporting done:\n\n- Literal idioms (English idioms transliterated, not adapted).\n- Unnatural word order (SOV translated as SVO into a non-SVO language, or\n  the reverse).\n- Mixed-language sentences (other than established loanwords).\n- Number, date, or currency strings still in source format.\n- Frontmatter strings still in the source language.\n\nFlag every issue inline (file path, line number, fix suggestion). The\ntranslator agent should re-pass any flagged passage before delivery.\n\n### Phase 7: Delivery\n\n```\n## Translation complete: [Original title]\n\n### Source\n- Language: [source]\n- File: [source path]\n\n### Translations\n| Language | File | Keywords adapted | Status |\n|----------|------|------------------|--------|\n| de | translations/de/{slug}.md | [N] | ok |\n| fr | translations/fr/{slug}.md | [N] | ok |\n\n### Quality checks\n- Structural integrity: pass / fail per language\n- Meta tags localized: pass / fail per language\n- Numbers, dates, currencies formatted per locale: pass / fail\n- Keywords localized: [N] keywords adapted\n- Machine-translation artifacts flagged: [N] (see notes above)\n\n### Next steps\n- Run `/blog localize <file> --locale <code>` for cultural deep-adaptation.\n- Run `/blog locale-audit translations/` to verify completeness.\n- Use `/blog multilingual` to combine write, translate, localize, hreflang\n  in one command.\n```\n\n## Error Handling\n\n| Scenario | Action |\n|----------|--------|\n| Unsupported language code | Suggest the correct ISO 639-1 code |\n| Source equals a target | Skip with \"Source is already in [lang]\" |\n| File not found | Report error with suggested path |\n| Translator agent timeout | Retry once, then report partial results |\n| Binary or non-text file | Report error, suggest correct file |\n\n## Cross-References\n\n- Next step (cultural depth): `/blog localize <file> --locale <code>`\n- QA sweep across all language versions: `/blog locale-audit <directory>`\n- One-command pipeline: `/blog multilingual <topic> --languages <codes>`","tags":["blog","translate","claude","agricidaniel","agent-skills","ai-citations","ai-content","ai-marketing","ai-marketing-hub","blog-writing","claude-code","claude-code-skill"],"capabilities":["skill","source-agricidaniel","skill-blog-translate","topic-agent-skills","topic-ai-citations","topic-ai-content","topic-ai-marketing","topic-ai-marketing-hub","topic-blog","topic-blog-writing","topic-claude-code","topic-claude-code-skill","topic-claude-plugin","topic-claude-skill","topic-content-creation"],"categories":["claude-blog"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/AgriciDaniel/claude-blog/blog-translate","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add AgriciDaniel/claude-blog","source_repo":"https://github.com/AgriciDaniel/claude-blog","install_from":"skills.sh"}},"qualityScore":"0.700","qualityRationale":"deterministic score 0.70 from registry signals: · indexed on github topic:agent-skills · 753 github stars · SKILL.md body (6,243 chars)","verified":false,"liveness":"unknown","lastLivenessCheck":null,"agentReviews":{"count":0,"score_avg":null,"cost_usd_avg":null,"success_rate":null,"latency_p50_ms":null,"narrative_summary":null,"summary_updated_at":null},"enrichmentModel":"deterministic:skill-github:v1","enrichmentVersion":1,"enrichedAt":"2026-05-18T18:53:31.683Z","embedding":null,"createdAt":"2026-05-18T12:54:54.718Z","updatedAt":"2026-05-18T18:53:31.683Z","lastSeenAt":"2026-05-18T18:53:31.683Z","tsv":"'+15':589 '+30':587 '-1':187,213,827 '-20':591 '/blog':786,795,804,875,884,892 '/chriss54/multilingual-int':102 '1':142,145,391,531 '2':154,254,415,554 '2026':98 '3':175,382,384,427,478,604 '4':223,435,454 '5':523 '6':630 '639':186,212,826 '7':716 'across':880 'action':818 'adapt':85,652,732,773,793 'add':532 'adjust':585 'agent':441,461,500,509,705,849 'alreadi':837 'alt':283,573 'analysi':170,256 'anchor':319 'answer':304 'appli':428 'artifact':642,777 'ask':200 'attribut':168,293,328 'audit':798,887 'author':265 'auto':156 'auto-detect':155 'becom':234 'behavior':423 'binari':857 'block':336,365 'blog':2,6,45,50,55,89,135,459,618 'blog-loc':134 'blog-multilingu':617 'blog-transl':1,458 'bodi':280 'box':312 'br':195,222 'capsul':39,306,599 'challeng':96 'chart':35,287,577 'check':747 'chris':92 'citat':38,305,355,598 'claud':88 'claude-blog-multilingu':87 'code':188,214,226,335,482,821,828 'combin':807 'comma':183 'comma-separ':182 'command':814,890 'comment':339 'common':172 'complet':719,802 'consist':452 'content':75,169,255,286,289,408,471 'correct':83,824,866 'count':596 'criteria':118 'cross':869 'cross-refer':868 'cta':313 'cultur':82,120,488,790,873 'currenc':680,763 'custom':128 'dach':124 'date':678,762 'dd':546 'de':189,216,539,586,734 'decid':392 'deep':792 'deep-adapt':791 'deliveri':714,717 'demand':107 'depth':874 'descript':263,448 'detect':157 'done':645 'duplic':139 'e.g':215,269,407 'emb':36 'en':541 'english':648 'equal':244,830 'equival':419 'error':815,844,864 'es':191,218 'establish':399,675 'etc':358 'everi':225,291,694 'exist':5,54,494 'ext':613,627 'extract':257 'face':371 'fail':751,758,768 'faq':301,595 'field':165 'file':130,149,607,697,725,730,840,862,867 'fill':299 'fix':701 'flag':693,711,778 'font':297 'font-siz':296 'format':84,109,112,518,685,764 'found':842 'fr':190,217,588,740 'francophon':125 'frontmatt':28,163,261,333,536,686 'fulli':512 'gartner':356 'generic':64 'german':412 'github.com':101 'github.com/chriss54/multilingual-int':100 'guardrail':634 'h1':277 'h2':278,450,561,603 'h3':279,563 'handl':116,816 'head':276,451 'hispan':126 'hreflang':811 'html':153,166,325 'hub':95 'identifi':374 'idiom':647,649 'imag':33,282,329,569 'inlin':338,696 'input':143,521 'instead':628 'integr':557,749 'intern':316,344,349 'internal-link':315,343,348 'invalid':228 'invok':615 'iso':185,211,825 'issu':695 'ja':192,219,238,590 'japanes':127,240 'jp':233 'json':31,363 'json-ld':30,362 'keep':413 'key':103,308,334 'keyword':41,78,379,385,396,434,473,731,769,772 'ki':551 'label':271,582 'lang':164,167,538,609,623,839 'languag':13,62,159,178,205,247,390,467,481,507,665,671,692,723,729,753,760,820,882,894 'ld':32,364 'length':584 'length-adjust':583 'line':699 'link':317,331,345,350 'liter':646 'load':105 'loanword':676 'local':18,40,77,114,123,136,386,418,474,498,535,611,625,756,766,770,787,788,797,810,876,877,886 'locale-audit':796,885 'localized-slug':610,624 'logic':431 'machin':640,775 'machine-transl':639,774 'man':550 'map':438,475 'march':97 'markdown':26,150,323 'marker':347 'market':404,409 'match':597 'mckinsey':357 'md':737,743 'mdx':151 'mean':237 'meaning':342 'meta':42,79,447,754 'miss':199 'mix':670 'mixed-languag':669 'mm':545 'mueller':93 'multilingu':90,619,622,805,893 'multipl':506 'n':738,744,771,779 'name':274,353,360 'nativ':21 'native-qu':20 'next':783,871 'non':663,860 'non-svo':662 'non-text':859 'note':781 'notic':252 'numb':44 'number':559,677,700,761 'number/date/currency':111 'ok':739,745 'one':9,58,229,493,813,889 'one-command':888 'optim':17,49,71 'order':160,655 'organ':352 'origin':99,567,720 'other':592 'output':637 'paragraph':281 'parallel':502 'pars':144,176 'partial':855 'pass':709,750,757,767 'passag':712 'path':698,727,847 'per':113,122,752,759,765 'person':273,359 'phase':141,253,381,383,453,477,522,629,715 'pipelin':891 'pointer':483 'post':7,56,514,525 'post-process':524 'prefer':162 'present':570,578,600 'preserv':25,110,290,321 'primari':376 'pro':94 'process':526 'produc':19,68 'profil':121,489 'provid':210 'pt':194,221 'pt-br':193,220 'public':73 'publication-readi':72 'qa':878 'qualiti':22,117,633,746 'question':302 'quot':115 're':708 're-pass':707 'read':146 'readi':74 'real':421 'record':436 'refer':104,870 'references/cultural-adaptation.md':119,491 'references/translation-rules.md':108,485,594 'reject':227 'report':644,843,854,863 'result':856 'retri':851 'return':510 'revers':668 'role':270 'run':499,785,794 'save':605,620 'scan':635 'scenario':817 'schema':29,361 'script':171 'search':422 'secondari':378,433 'section':564 'see':593,780 'sentenc':672 'seo':16,48,70 'seo-optim':15,47,69 'separ':184 'share':132 'size':298 'skill':67 'skill-blog-translate' 'skip':248,833 'slop':552 'slug':547,612,626,736,742 'sourc':148,158,246,351,395,470,684,691,722,724,726,829,835 'source-agricidaniel' 'sov':656 'spawn':456 'status':733 'stay':410 'step':784,872 'still':682,688 'stop':173 'string':372,681,687 'structur':27,326,556,748 'suggest':232,702,822,846,865 'summari':311 'surfac':260 'svg':292,576 'svo':659,664 'swap':424 'sweep':879 'tag':43,80,264,327,755 'takeaway':309 'target':12,61,177,243,389,403,466,480,497,832 'task':463 'term':400 'text':284,307,314,320,574,581,861 'timeout':850 'titl':262,446,721 'topic-agent-skills' 'topic-ai-citations' 'topic-ai-content' 'topic-ai-marketing' 'topic-ai-marketing-hub' 'topic-blog' 'topic-blog-writing' 'topic-claude-code' 'topic-claude-code-skill' 'topic-claude-plugin' 'topic-claude-skill' 'topic-content-creation' 'transform':300 'translat':3,4,23,46,51,52,65,208,259,268,337,366,440,455,460,504,513,529,572,580,606,608,632,641,657,704,718,728,776,799,809,848 'translatedd':542 'translatedfrom':540 'translation-qu':631 'translations/de':735 'translations/fr':741 'transliter':650 'unchang':322 'unlik':63 'unnatur':653 'unsupport':819 'updat':445,534 'url':330,332 'use':442,803 'user':202,370 'user-fac':369 'valid':224 'valu':373 'verifi':555,801 'vermeidet':553 'version':530,883 'via':462 'whether':393 'wie':549 'wie-man-ki-slop-vermeidet':548 'word':174,654 'workflow':140 'write':808 'x':294 'y':295 'yaml':537 'yes':406 'yyyi':544 'yyyy-mm-dd':543 'zone':318,346","prices":[{"id":"c037d6bf-47b5-42fb-b9cb-30a7306f900a","listingId":"cd93b61b-9ce7-4763-8556-15d3cb2fc498","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"AgriciDaniel","category":"claude-blog","install_from":"skills.sh"},"createdAt":"2026-05-18T12:54:54.718Z"}],"sources":[{"listingId":"cd93b61b-9ce7-4763-8556-15d3cb2fc498","source":"github","sourceId":"AgriciDaniel/claude-blog/blog-translate","sourceUrl":"https://github.com/AgriciDaniel/claude-blog/tree/main/skills/blog-translate","isPrimary":false,"firstSeenAt":"2026-05-18T12:54:54.718Z","lastSeenAt":"2026-05-18T18:53:31.683Z"}],"details":{"listingId":"cd93b61b-9ce7-4763-8556-15d3cb2fc498","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"AgriciDaniel","slug":"blog-translate","github":{"repo":"AgriciDaniel/claude-blog","stars":753,"topics":["agent-skills","ai","ai-citations","ai-content","ai-marketing","ai-marketing-hub","blog","blog-writing","claude-code","claude-code-skill","claude-plugin","claude-skill","content-creation","content-optimization","content-strategy","eeat","geo","multilingual","open-source","seo"],"license":"mit","html_url":"https://github.com/AgriciDaniel/claude-blog","pushed_at":"2026-05-15T04:45:18Z","description":"Claude Code blog skill suite: 30 sub-skills, 5 agents, 5-gate v1.9.0 Blog Delivery Contract, dual-optimized for Google rankings and AI citations. Active development at AI-Marketing-Hub/claude-blog (AI Marketing Hub Pro community); public releases ship here.","skill_md_sha":"3843c82f1e7438083252b8b48500501de97a6fbd","skill_md_path":"skills/blog-translate/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/AgriciDaniel/claude-blog/tree/main/skills/blog-translate"},"layout":"multi","source":"github","category":"claude-blog","frontmatter":{"name":"blog-translate","license":"MIT","description":"Translate existing blog posts into one or more target languages with SEO-optimized localization. Produces native-quality translations that preserve markdown structure, frontmatter, schema JSON-LD, image and chart embeds, and citation capsules. Localizes keywords, meta tags, numbers, dates, currencies, and quote styles per locale. Flags machine-translation artifacts for review. Run BEFORE blog-localize: this handles language conversion; localize handles cultural adaptation after translation completes. Use when user says \"translate blog\", \"blog translate\", \"uebersetzen\", \"traduire\", \"traducir\", \"translate post\", \"blog auf Deutsch\", \"blog en espanol\".","compatibility":"Standalone within claude-blog. Invoked by blog-multilingual."},"skills_sh_url":"https://skills.sh/AgriciDaniel/claude-blog/blog-translate"},"updatedAt":"2026-05-18T18:53:31.683Z"}}