video-editor
Skill0 starsChanged 7 months agoMITView on GitHub
Автоматизация видео-продакшна — субтитры, монтаж, сборка проектов для Final Cut Pro. Активируется на: субтитры, subtitles, монтаж, видео, auto-subs, auto-cut, auto-assemble, FCPXML, Final Cut, footage, футажи.
- Installs packages
Files
Video Editor — автоматизация видео для Final Cut Pro
References
| Запрос | Файл |
| CLI entry points и конфигурация | references/package.json |
| Автосубтитры (исходный код) | references/auto-subs.js |
| Автомонтаж (исходный код) | references/auto-cut.js |
| Полная сборка (исходный код) | references/auto-assemble.js |
Что умеет
1. auto-subs — Автосубтитры
Видео → Whisper транскрипция → FCPXML субтитры + SRT файл
auto-subs video.mp4 # → video.fcpxml + video.srt
auto-subs video.mp4 --mode words # по словам
auto-subs video.mp4 --font "Montserrat" --size 80 --color "#FFD700"Опции:
--font <name>— шрифт (default: Arial Bold)--size <n>— размер (default: 72)--color <hex>— цвет текста (#FFFFFF)--stroke <hex>— обводка (#000000)--position <pos>— top/center/bottom (default: bottom)--mode <mode>— words/phrases (default: phrases)--max-words <n>— макс слов в фразе (default: 8)--lang <code>— язык Whisper (default: ru)--model <name>— модель Whisper: tiny/base/small/medium/large (default: small)
2. auto-cut — Автомонтаж
Папка футажей + аудиодорожка → FCPXML timeline с умным подбором
auto-cut --footage ./footage/ --audio voice.m4a -o timeline.fcpxml
auto-cut --footage ./footage/ --audio voice.m4a --manual # без LLMФутажи: видеофайлы + footage.md с описаниями:
## 001.mp4
Макс за компьютером, печатает код
## 002.mp4
Общий план офиса, камера панорамируетLLM подбирает футажи по смыслу аудио. --manual — round-robin.
3. auto-assemble — Полная сборка
Всё вместе: футажи + аудио + субтитры → один FCPXML
auto-assemble --footage ./footage/ --audio voice.m4a -o project.fcpxml
auto-assemble --footage ./f/ --audio v.m4a --no-subs --manual
auto-assemble --footage ./f/ --audio v.m4a --font "Montserrat" --font-size 64 --font-color "#FFD700"5 шагов внутри:
- Сканирует футажи + читает footage.md
- Транскрибирует аудио через Whisper
- LLM подбирает футажи по смыслу текста
- Генерирует субтитры + SRT
- Собирает FCPXML: видео на spine, аудио lane -1, субтитры lane 1
Структура таймлайна:
Spine (main): [footage1] [footage3] [footage2] ...
Lane -1: [========== аудиодорожка ===========]
Lane 1: [sub1] [sub2] [sub3] [sub4] ...Установка
# Зависимости (macOS)
brew install ffmpeg
pip install openai-whisper
# Video Factory CLI
cd video-factory && npm link
# Проверка
auto-subs --help
auto-assemble --helpWorkflow для агента
Просят "сделай субтитры":
- Спроси файл/путь к видео
auto-subs <файл>- Отдай .fcpxml + .srt
Просят "собери видео":
- Спроси папку футажей и аудио
- Проверь footage.md (если нет — помоги создать)
auto-assemble --footage <папка> --audio <файл>- Отдай project.fcpxml + .srt
Просят описать футажи (footage.md):
## filename.mp4
Краткое описание: кто, что делает, план (крупный/общий)Требования
- Node.js 18+
- Whisper CLI (OpenAI)
- ffmpeg / ffprobe
- Final Cut Pro 10.8+ (FCPXML 1.11)
- OpenClaw (опционально, для LLM-подбора)
Other versions17 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 17
- jtydhr88/ComfyTV★ 1.1ksame name
- ckorhonen/claude-skills★ 17same name
- coopersimson96/ai-content-system★ 17same name
- EverythingAI-Pro/ai-video-editor★ 16same name
- Isaac-Flath/agent-starter-skills★ 8same name
- darker2016/WorkbuddySkillGroups4DSH★ 6same name
- EmersonBraun/skills★ 4same name
- kevinaimonster/skill-hub★ 4same name
- tyler-berggren/tb-claude-kit★ 2same name
- X33834/awesome-skillkit★ 2same name
7 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
Used alongsideProjects with it also use brainstorm.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
nicodianskSkillbrainstorm
Use when starting creative work - creating features, building components, adding functionality, or modifying behavior. Explores requirements through Socratic dialogue before any implementation.
Also in 3 projects that use this
In this repository35 other files it gives its agents.
- agent-architectSkill
- agent-memorySkill
- audience-lensSkill
- carouselSkill
- constructor-opsSkill
- content-repurposerSkill
- copywritingSkill
- customer-researchSkill
- editingSkill
- headlinesSkill
- heygenSkill
- learning-processorSkill
- memory-systemSkill
- nano-banana-pro-promptsSkill
- nano-bananaSkill
- openclaw-opsSkill
- personal-unpackingSkill
- prompt-engineerSkill
- reelsSkill
- selling-meaningsSkill
- seo-blog-writerSkill
- shared-learningsSkill
- skill-creatorSkill
- skill-securitySkill
- soul-masterySkill
- storytellingSkill
- swipefileSkill
- telegram-adminSkill
- telegramSkill
- text-postsSkill
- threadsSkill
- timelapse-creatorSkill
- tone-of-voiceSkill
- veo-videoSkill
- youtubeSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

