One-command multilingual blog creation. Writes a blog post, translates it into user-specified languages, applies cultural adaptation, and emits hreflang tags, sitemap entries, and a CMS-ready language map. The complete write-to-publish pipeline for international content. Orchestrates blog-write, blo

Blog Multilingual, One Command International Publishing Bundled paths below use host Markdown substitution of ${CLAUDE SKILL DIR} ; it is not an exported shell variable. Resolve them before execution, quote paths, and refuse nonabsolute overrides. Pass blog reference root resolved from ${CLAUDE SKILL DIR}/../blog/references , blog template root from ${CLAUDE SKILL DIR}/../blog/templates , and needed sibling roots to agents. Read the main reference orchestration details.md before loading project context; pass only its helper fenced output to downstream agents. The flagship multilingual orchestrator. Combines blog writing, translation, cultural adaptation, and full international SEO into a single command. Produces publication ready blog posts in every target language with hreflang tags, localized JSON LD schema, and CMS integration metadata. Adapted from claude blog multilingual by Chris Mueller (AI Marketing Hub Pro Hub Challenge submission, March 2026, scored 85/100 Proficient). Original repository: no longer available as of 2026 10 12 This port removes the original curl bash installer and credential handling flagged in the audit, integrates as core skills, and uses the shared cultural adaptation reference under blog translate/references/ . Dependencies Invoked internally by this orchestrator: Component Source Required blog write claude blog (this plugin) Yes blog translate claude blog (this plugin) Yes blog localize claude blog (this plugin) Yes (when localize is on, default) seo hreflang claude seo (sibling plugin) No, falls back to a self contained generator If seo hreflang is not installed, the orchestrator emits hreflang tags using its own minimal generator (Phase 5 below) and notes the limitation in the delivery summary. Hreflang validation in that case is structural only, not the deeper validation seo hreflang provides. Command Syntax Argument Required Default Description <topic Yes required Blog topic or working title languages Yes required Comma separated Google compatible hreflang tags (e.g. de,fr,es MX,ja,pt BR ; see the code rules in Phase 1) source No en Source language to write the original in no localize No off Skip cultural adaptation (translation only) format No auto Output format: md , mdx , or html If languages is missing, ask the user once before running anything: "Which languages should the blog be published in? Provide hreflang tags separated by commas (e.g., de,fr,es MX,ja,pt BR ). The post will be written in <source first, then translated." Workflow Phase 1: Configuration 1. Parse arguments. Extract topic, target languages, source, format. 2. Validate each language code with the shared multilingual locale rules used by blog translate , blog localize , and blog locale audit : ISO 639 1 language in lowercase, optional ISO 15924 script in title case, optional ISO 3166 1 Alpha 2 region in uppercase. Google's localized versions documentation (https://developers.google.com/search/docs/specialty/international/localized versions, read 2026 10 12) allows a language code by itself ( de is valid hreflang), but never a region by itself. This pipeline is stricter for translation quality: language only codes are accepted only for unambiguous editorial markets ( de , fr , ja , and the source language). es , pt , and zh (and any language spanning materially different markets or scripts) need a region or script ( es ES , es MX , pt BR , pt PT , zh Hans , zh Hant ) or an explicit neutral mode the user requests. If the user passes a bare es , pt , or zh , ask once which market they mean. The hreflang value emitted in Phase 5 is exactly the normalized code the user supplied. 3. Detect output format from the project (frontmatter convention, file extensions, framework hints) or use format . 4. Resolve source language. If a target language equals source , drop it from the translation list with a notice. 5. Create the output directory inside the current working directory: Keep all output inside the project root; do not write outside the cwd. Progress: Phase 1: Configuration complete, [N] languages selected ([codes]) Phase 2: Write Original Blog Invoke the blog write sub skill (route through /blog write so all existing rules apply: template auto selection, sourced statistics, citation capsules, Article schema priority, FAQPage only as an entity signal when visible FAQ content exists, internal link zones, charts, image embedding). Pass the topic and any blog write parameters surfaced by the user. Save the original to multilingual/{source lang}/{slug}.{ext} . Progress: Phase 2: Original written, multilingual/{source lang}/{slug}.{ext} Phase 3: Translate to All Target Languages For each target language, invoke blog translate : Input: the original blog post produced in Phase 2. Target: the specific language code. Mode: orchestrated. Put the literal line Mode: orchestrated at the top of the invocation. In orchestrated mode blog translate skips its own delivery contract (see its Phase 7); this orchestrator runs it once in Phase 6. Run targets in parallel where the runtime supports it (one Task per language) to reduce wall clock time. Save translations to multilingual/{lang}/{localized slug}.{ext} . Progress: Phase 3: Translating to [lang] ([X]/[N]) per language, then Phase 3: All translations complete . Phase 4: Cultural Adaptation If no localize is NOT set, invoke blog localize for every translated post: Input: the translated blog post. Locale: the target language or region code. Mode: orchestrated. Put the literal line Mode: orchestrated at the top of the invocation. In orchestrated mode blog localize skips its own delivery contract; this orchestrator runs it once in Phase 6. Run in parallel. Apply the localized output only after resolving the generated path inside multilingual/ , rejecting symlinks, and creating a backup when overwriting. The localizer swaps brand examples, adapts CTAs, substitutes legal references, and adjusts formality. See ${CLAUDE SKILL DIR}/../blog localize/SKILL.md for the full adaptation pass. Progress: Phase 4: Cultural adaptation complete for [N] languages . Phase 5: International SEO Generation Generate three artifacts plus localized schema. If the seo hreflang skill from claude seo is installed, delegate validation to it. Otherwise use the self contained generator below. 5a. Hreflang Tags (HTML) Copy paste ready tags for <head : Rules (mirrored from seo hreflang ): Every page references all alternates including itself (self referencing). Every href , including x default , is a fully qualified absolute https://... URL. x default points to the unmatched language fallback, such as a global language selector or default market page. It does not have to be the source language version. All URLs use the same protocol (HTTPS) and trailing slash convention. Bidirectional: every relationship is reciprocal. Save to multilingual/hreflang tags.html . 5b. Hreflang Sitemap Fragment Generate one <url block per locale. Every block must contain the identical complete set of <xhtml:link alternates for every locale, plus self and optional x default , using fully qualified https://... URLs. Save to multilingual/hreflang sitemap.xml . 5c. Hreflang Map (JSON) Machine readable mapping for CMS integration: hreflang is exactly the normalized code the user supplied (here de ); locale records the cultural profile used, which may be more specific. Save to multilingual/hreflang map.json . 5d. Localized Article Schema (Required) Attach or update Article/BlogPosting JSON LD on every language version with inLanguage and translationOfWork fields: Use the existing /blog schema sub skill for richer schema on each version. For the internal schema heuristic, Article or BlogPosting earns 2 points, Person earns 1, and either Organization or BreadcrumbList earns 1. This is not a Google requirement. Include both Organization and BreadcrumbList when the visible site data supports them. FAQPage is optional and only for visible FAQ content as an entity signal, not a Google rich result target. Phase 6: Final Locale Delivery Contract (exactly one run per locale) This is the ONLY delivery contract run for each target locale. blog translate and blog localize ran in orchestrated mode and skipped theirs (each carries the sentence "When invoked by blog multilingual (orchestrated mode), skip the delivery contract; blog multilingual runs it once per locale on the final text." and the line "Orchestrated mode is signaled by the literal line Mode: orchestrated at the top of the invocation."), so the full five gate sequence runs once, on the final localized text (or on the translation when no localize is set). The source locale keeps the successful /blog write review. Do not start this phase until the last translation or localization change for the locale is saved. For each target locale, run the canonical sequence independently: 1. Resolve BLOG SCRIPT DIR="${CLAUDE BLOG SCRIPTS DIR: ${CLAUDE SKILL DIR}/../../scripts}" and reject it unless absolute. Never resolve helpers from the current project's scripts/ directory. 2. Visuals: create multilingual/{lang}/delivery/{localized slug}/ as the isolated artifact directory and copy the final locale source into it under its lowercase localized slug. Resolve every draft marker ( [INTERNAL LINK , [IMAGE , [CHART ): none may remain. Reuse the source hero by copying it as hero.<ext ; a new locale specific hero is a paid call and needs the blog image cost and consent gate first. 3. Render: python3 "$BLOG SCRIPT DIR/blog render.py" md <locale file out dir <locale delivery dir . 4. Init nonce: python3 "$BLOG SCRIPT DIR/blog preflight.py" draft <locale delivery dir init review nonce . 5. Review: pass only the printed nonce to a fresh blog reviewer invocation against the rendered locale HTML. The reviewer returns text; save it verbatim to <locale delivery dir /review.md . 6. Gates: python3 "$BLOG SCRIPT DIR/blog preflight.py" draft <locale delivery dir strict slug <localized slug . 7. Loop: after ANY change to the locale file, hero, HTML, or PDF, re render, re init the nonce, and re review. Maximum 3 iterations per locale. Mark the locale passed only at 90+/100, zero P0, matching nonce, final BLOCKING: false , and all other gates. A failed locale remains draft blocked ; keep successful locales and report the failed locale's diagnostic without calling the whole set complete. Phase 7: Delivery Summary Cross References When Run To regenerate or reword the source /blog write <topic To translate one existing file only /blog translate <file to <codes To deepen cultural fit on one file /blog localize <file locale <code To audit a multilingual directory /blog locale audit <directory For deeper hreflang validation /seo hreflang <directory (claude seo, optional) Error Handling Scenario Action blog write missing Error: "This skill requires blog write . Reinstall claude blog." One translation fails Complete the rest, report partial results, suggest a retry command Source language equals a target Skip that target, log a notice Bare es , pt , or zh target Ask which market ( es ES , es MX , pt BR , pt PT , zh Hans , zh Hant ) or require an explicit neutral mode 10 or more target languages Stop before writing. Explain scaled content abuse risk and require reviewed batches of at most 9 target languages seo hreflang not installed Use the self contained generator, note it

blog-multilingual