layer-localization — скилл для Claude Code: локализация медиа
Скилл layer-localization для Claude Code локализует видео и изображения для разных языков. Он включается при подготовке озвучки, субтитров или экранного текста из одного утверждённого мастер-файла.
MIT 1 100 установок ★ 10 обновлён 2026-09-30
npx skills add layerai/skills --skill layer-localization -a claude-codeЧто делает layer-localization
Скилл помогает подготовить языковые версии видео и изображений на основе одного утверждённого исходника. Он подбирает маршрут для дубляжа, озвучки переведённого текста, вшитых субтитров или замены надписей в графике. Для каждого языка создаётся отдельная версия; переводы нужно получить от пользователя или его локализационного подрядчика. Самостоятельный перевод помечается как черновик.
Перед первым запуском нужно оценить стоимость всей языковой матрицы и применить порог в 20 CU к общей сумме. Список языков, доступные пресеты и поведение модели проверяются через get_base_model. Генерацию и расчёт выполняет скилл layer; для точной надписи на изображении нужен layer-typography, а для правки видеотаймлайна — layer-video-timeline.
Дубляж может сохранить длину ролика или менять её вместе с синхронизацией губ. Второй вариант не подходит ролику с фиксированной длительностью. Для озвучки язык можно задать явно, а текстовые блоки следует проверять на переполнение и корректное отображение письменности; пустые квадраты означают, что шрифт не содержит нужных знаков.
Какие задачи решает
- подготовить дубляж видео для другого языка
- озвучить переведённый текст для рекламного ролика
- вшить субтитры для отдельной языковой версии
- заменить надпись на изображении для другого рынка
- исправить переполнение текста или пустые квадраты в шрифте
Примеры запросов агенту
- Подготовь дубляж этого ролика на немецкий, сохранив его длительность.
- Сделай озвучку на другом языке по этому переведённому тексту.
- Замени текст на изображении для каждой языковой версии.
Как установить layer-localization
1Через Skills CLI (Vercel)
npx skills add layerai/skills --skill layer-localization -a claude-code2Вручную: положить файлы
~/.claude/skills/layer-localization/SKILL.mdПапка скилла целиком; для одного проекта — .claude/skills/layer-localization/
1Через Skills CLI (Vercel)
npx skills add layerai/skills --skill layer-localization -a codex2Вручную: положить файлы
.agents/skills/layer-localization/SKILL.mdДля всех проектов — ~/.agents/skills/
1Через Skills CLI (Vercel)
npx skills add layerai/skills --skill layer-localization -a cursor2Вручную: положить файлы
.cursor/skills/layer-localization/SKILL.mdCursor читает и .agents/skills/, и .claude/skills/
1GitHub CLI
gh skill install layerai/skills plugins/layer/skills/layer-localization2Вручную: положить файлы
.github/skills/layer-localization/SKILL.md1Через Skills CLI (Vercel)
npx skills add layerai/skills --skill layer-localization -a gemini-cli2Командой платформы
gemini skills install https://github.com/layerai/skills --path plugins/layer/skills/layer-localizationВручную: положить файлы
.devin/skills/layer-localization/SKILL.mdСтарый путь .windsurf/skills/ тоже читается
Через Skills CLI (Vercel)
npx skills add layerai/skills --skill layer-localization -a opencodeClaude.ai
Упакуйте папку в zip и загрузите в Settings → Capabilities → Skills
По шагам, с командами для каждой платформы: Как установить скилл в Claude Code: пять способов
Вопросы о layer-localization
Как установить layer-localization в Claude Code?
Выполни npx skills add layerai/skills --skill layer-localization -a claude-code. Файл скилла находится по пути ~/.claude/skills/layer-localization/SKILL.md.
Что делает layer-localization?
Помогает выпускать языковые версии видео и изображений: создавать дубляж и озвучку, вшивать субтитры и заменять текст в графике.
Какие ещё скиллы нужны для работы layer-localization?
Генерацию и расчёт выполняет layer. Для точного текста на изображении нужен layer-typography, а для монтажа таймлайна — layer-video-timeline.
Исходный текст
SKILL.md · MIT
--- name: layer-localization description: "Use when one approved Layer asset must ship in several languages: dubbing a trailer or ad, voice-over in another language, burned-in subtitles or captions per market, or translating text that appears in an image, end card, store screenshot, or UI. Also when a dub drifts out of sync, translated copy no longer fits, or a font shows empty boxes for another script. Keywords: localisation, localization, dubbing, translation, subtitles, captions, voice-over, multilingual, markets, CJK, RTL." license: MIT --- # Layer Localization ## Overview Localisation is one master multiplied by a list of languages. Every language version comes from the approved master, never from another language's version: a German cut made from the French cut carries the French cut's defects into German. Layer covers three layers of an asset: - **Voice**: dub an existing video, or speak a translated script with text to speech. - **Captions**: burn subtitles into a video. - **Text in images**: replace words in the art, or letter a clean plate per language. Generation mechanics, the estimate gate and polling are in the `layer` skill. Setting exact type is `layer-typography`, and cutting finished videos is `layer-video-timeline`. If a sibling skill named here is missing from your available skills, ask the user to install it (`npx skills add layerai/skills --skill <name>`); unattended, proceed from tool schemas and flag the gap. ## Quick reference | Job | Route | | ------------------------------------- | --------------------------------------------------------------------------- | | Dub a voiced video | `use_case: "dub_video"`, `target_language` from the model's `dub_languages` | | New voice-over from a translated line | `use_case: "text_to_speech"`, `speech_language` from `speech_languages` | | Burn in captions | `use_case: "video_subtitle"`, `subtitle_preset` from `subtitle_presets` | | Change words baked into an image | `use_case: "edit_text"` | | Exact text per language on clean art | `render_text`, then `compose_image` (`layer-typography`) | Every route is a `list_base_models` filter except the last, which is two deterministic tools that spend no Creative Units. Read `get_base_model` on the chosen model before the first run: the language lists, presets and behaviour below live in its capabilities. ## Plan the matrix first Before any run, write down assets by languages: each master `file_id`, each language's code, and an empty cell for each output `file_id`. Languages are ISO 639-1 codes (`de`, `ja`, `pt`), which name a language, not a market. If the user needs Brazilian rather than European Portuguese, say that a code alone may not distinguish them and check the model's list. Get approved translations from the user or their localisation vendor. If you translate copy yourself, label it a draft for review: store copy, legal lines and character names are the user's call. Price the whole matrix before the first run, and apply the 20 CU gate to the total. Pricing reads the files, so pass each source to the estimate. Text to speech is priced per character, so each language's script is its own estimate. When in doubt whether two languages price apart, estimate one call per language. ## Voice **Dubbing** keeps the original performance and changes its language. `target_language` is required on dub models and must be one of the codes in `dub_languages`. Dub models differ in one decision that matters more than voice quality: - Some leave the picture and its length exactly as they are. Choose these when the dub goes back over an existing edit, a timeline, or a fixed-length ad slot. - Others re-sync the lips and may lengthen or shorten the clip to the new language's pace. Choose these for an on-screen presenter, never for a clip that must keep its length. The tool schema currently names ElevenLabs Dubbing for the first behaviour and HeyGen models for the second; confirm with `get_base_model`, since the catalogue changes. **Text to speech** suits a fresh voice-over from a translated script. Leave `speech_language` unset and the model guesses from the text; set it when lines are short or full of names and loanwords, which are exactly what a model reads in the wrong language. `text_normalization` controls how numbers and dates are read, which differs by language. Reuse the same voice choices across a language's lines so the character does not change voice mid-campaign. Translated speech runs longer. German and French lines often outgrow the English, and a 15-second slot does not stretch. Shorten the line, not the pacing: a small speed nudge is fine, a crammed read is not. ## Captions Filter for `use_case: "video_subtitle"`. Spell `subtitle_preset` exactly as one of the model's `subtitle_presets`: any other name is quoted at the default style and then refused at launch. Presets listed under `subtitle_dynamic_presets` animate word by word and bill at a higher rate, so pass the same preset to the estimate. `subtitle_alignment`, `subtitle_color` and `subtitle_secondary_color` apply only where the capabilities report them. The schema takes no caption text, so caption each language's dub rather than the master, and confirm in `get_base_model` that the model captions that language. For a dub or caption run, attach the source video in the guidance slot `get_base_model` lists for the model; do not assume one. Burned-in captions make one file per language, so keep the master without captions. Move captions to the top when the lower third carries a CTA, gameplay UI or a lower-third title. ## Text in images The cheapest localisation is art with no words baked in. Generate the master clean and letter each language with `render_text` and `compose_image`. Copy burned into a video frame, such as an end card, is out of reach of image tools. Ask for the text-free end card first. Failing that, cover the end-card span on a `render_video_timeline` edit (`layer-video-timeline`): an image or solid item over the old copy, and a text item set in the language's font with `font_file_id`. - **Script coverage.** A Latin brand font usually has no CJK, Cyrillic, Thai or Arabic glyphs, and missing glyphs render as empty boxes. Pick a family that covers the script (a Google Fonts family name in `font_family` works) and look at every render. - **Direction and shaping.** For right-to-left and joined scripts, check visually that letters join and run in the right direction. If they do not, report it rather than ship it. - **Expansion.** Size the text box for the longest language and render every language into the same box. When `render_text` refuses copy with the size it needs, shorten the copy or lower `font_size` consistently across the set, so one market's title is not visibly smaller. When the words are already baked in, run an `edit_text` model on the master with the exact replacement string quoted. Check it letter by letter. If it fails, remove the text once to a clean plate (an `erase_object` or `inpainting` model) and letter the plate per language. ## Worked example "Localise our 15-second 9:16 trailer and its end card into German, Japanese and Portuguese." 1. Matrix: trailer and end card masters by `de`, `ja`, `pt`. Ask whether Portuguese means Brazil, and for approved translations of the end card's two lines. 2. `list_base_models` with `use_case: "dub_video"`; `get_base_model` on candidates. The trailer must stay 15 seconds, so pick one that keeps picture and length, and confirm all three codes are in its `dub_languages`. 3. Estimate all three dubs with the trailer attached. The end cards need no estimate: they are deterministic. Present the total; above 20 CUs wait for an explicit yes. 4. `execute_forge` per language with `target_language`; poll each with `get_forge_run` at `poll_interval_seconds`. Watch each dub against the picture. 5. End card: the master has no text, so `render_text` each language into one shared box, the Japanese with a family that covers kana and kanji, then `compose_image` onto the master. 6. Fill the matrix with every output `file_id` and hand it over. ## Common mistakes - Localising from another language's version instead of the master. - A lip-resyncing dub dropped into a fixed-length edit, which then runs long or short. - Estimating one language and assuming the rest cost the same. - A brand font that lacks the script, shipped with empty boxes. - Letting each language shrink its own font size until its copy fits. - Translating store or legal copy and presenting it as final. - Burning captions into the only copy of the master.
© layerai · MIT · layerai/skills