القائمة
Produce existing content in more languages — translated copy, re-generated voiceover in the same brand voice, per-language captions and publish packs. Use when the user says "make this in Spanish", "translate my ad", "localize for Thailand", "multi-language version".
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
| name | localize-content |
| description | Produce existing content in more languages — translated copy, re-generated voiceover in the same brand voice, per-language captions and publish packs. Use when the user says "make this in Spanish", "translate my ad", "localize for Thailand", "multi-language version". |
| allowed-tools | Bash Read Write Edit Glob Grep |
One piece of content, N markets. The visuals are already paid for — localization re-generates only the cheap layers: script, voiceover (~$0.01), captions (free), and copy. A $10 video becomes 3 markets for ~$0.10.
Ask once: which languages/markets? Then identify what the piece contains
(check its manifest — see /revise-content STEP 1):
| Layer | Localize how | Cost |
|---|---|---|
| Script / voiceover | translate → generateVoiceover per language | ~$0.01 each |
| On-screen captions (.srt) | generateCaptions from translated script | free |
| Caption/post copy + hashtags | translate + adapt (see STEP 2) | ~$0.001 |
| Text baked INTO the image/video | can't swap text in-place — flag it | see below |
Baked-in text warning: if the visual has burned-in text (headline on a thumbnail, text overlay in a scene), tell the user up front: that layer needs regeneration per language (
/revise-contentfor that piece, translated prompt). Get approval before this — it's the only expensive part.
Use generateText (or translate yourself if fluent) with instructions to:
brand.md — a warm-casual brand must stay
warm-casual in every language.restrictions (never_say lists apply in every language; add
market-specific legal terms if the user names any).Show the user each translation before generating audio. If they don't read the language, say what you adapted and why.
# Voiceover — SAME locked voice id from the asset registry for brand continuity
node workflows/cli.cjs generateVoiceover '{"script":"<translated script>","voiceName":"Kore","outputPath":".../es/voiceover.wav"}'
# Remix onto the existing video (local, free)
node workflows/cli.cjs mixVideoAudio '{"videoPath":".../final.mp4","voiceoverPath":".../es/voiceover.wav","musicPath":".../music.wav","outputPath":".../es/final-es.mp4"}'
# Captions from the translated script (local, free)
node workflows/cli.cjs generateCaptions '{"script":"<translated script>","totalDuration":30,"outputPath":".../es/captions.srt"}'
Check the voice supports the language (Gemini TTS is multilingual, but listen to the first output before batching the rest). Non-Latin scripts (Thai, Myanmar, Arabic…): confirm caption font/rendering — see the content-preflight edge-case checklist.
/package-content each localized cut into
output-contents/{piece}/publish/{lang}/{platform}/ with the translated
caption, localized hashtags, and link. Then report:
✅ LOCALIZED — summer-ad → ES, TH, MM
es/ final-es.mp4 + captions + IG/TikTok packs $0.011
th/ final-th.mp4 + captions + IG/TikTok packs $0.012
mm/ final-mm.mp4 + captions + FB pack $0.012
Flagged: thumbnail has baked-in English headline — regenerate per language? (~$0.07 each)
recordCost the spend. Save translated scripts alongside outputs so future
revisions localize from the same source.
<content-id>.pipeline.json in each language's folder BEFORE generating
(nodes = CLI commands — voiceover → mix → captions — {{node.data.field}} refs),
then node workflows/cli.cjs runPipeline @<file>. See workflows/pipelines/README.md.prompts.txt with the translated script (audio tags
included) and voice params; update it on every retry with a one-line RESULT note.MANDATORY pre-flight check that runs BEFORE any content plan or generation. Classifies the topic, verifies project/brand/product context, resolves the required reusable assets (characters, products, logos, voices) from the asset registry, and provides/generates whatever is missing — saving paths for reuse. Use whenever the user asks to plan a campaign, make a marketing plan, or create/generate any image, video, voiceover, or music.
Generate music using Gemini Lyria. Use for background music, jingles, intros, soundtracks, and complete songs WITH sung vocals — Lyria 3 sings your exact lyrics (8 languages, rap/sung delivery).
Generate images using Gemini 3 Image (Nano Banana). Use for thumbnails, carousels, infographics, social graphics, product photos.
Generate video content using Gemini Veo. Use when user asks to create video, TikTok ad, Instagram Reel, YouTube video, product video, explainer.
Generate voiceover audio using Gemini TTS. Use for narration, voiceovers, podcasts, multi-speaker dialogue.
Write the words — scroll-stopping hooks, framework-driven scripts, and platform-ready captions with hashtags. Use when the user needs hook ideas, a video/ad script, ad copy, post captions, or says "what should I post", "write a script", "give me hooks", "write the caption".