editing-skills — плагин для Claude Code: монтаж видео
Плагин editing-skills для Claude Code собирает вертикальные ролики из разговорных видео и фотоматериалов. Шесть сценариев привязывают графику и подписи к словам, ещё пять оформляют ролик в фотографическом стиле.
MIT ★ 94 обновлён 2026-10-30
/plugin marketplace add artemnovitckii/claude-editing-skills
/plugin install editing-skills@claude-editing-skillsЧто делает editing-skills
Плагин монтирует короткие вертикальные видео по одному из одиннадцати сценариев: шесть оформляют речь ведущего графикой и подписями, пять используют фотографические шаблоны. Для первых шести нужен ключ Groq API для расшифровки речи; пять фотошаблонов работают без ключа. Рендер идёт на локальном компьютере.
Нужны macOS или Linux, ffmpeg, Node.js 22+ и Python 3.9+. Установка создаёт Python-окружение, загружает GSAP и подготавливает HyperFrames; модели для вырезания ведущего скачиваются при запуске настройки с --cutout. После обработки рядом с исходным видео появляются готовый ролик и лист кадров для проверки. Исходные шесть сценариев требуют GROQ_API_KEY.
Какие задачи решает
- оформить разговорный ролик титрами и графикой
- собрать три разных версии одного клипа для Instagram
- показать фотографии или скриншоты рядом с ведущим
- добавить к ролику список с оценками от S до F
Примеры запросов агенту
- Смонтируй клип
~/Downloads/my-clip.mp4в формате объясняющего ролика командой/editing-skills:explainer. - Сделай три варианта ролика из
~/Downloads/my-reel.mp4командой/editing-skills:trial-reels. - Добавь мои публикации из
~/Desktop/postsза ведущим в клипе~/Downloads/clip.mp4командой/editing-skills:behind-the-person.
Как установить editing-skills
Через маркетплейс плагинов
/plugin marketplace add artemnovitckii/claude-editing-skills/plugin install editing-skills@claude-editing-skillsПо шагам, с командами для каждой платформы: Плагины Claude Code: маркетплейсы, установка и как собрать свой
Вопросы об editing-skills
Как установить editing-skills в Claude Code?
Выполни в Claude Code сначала /plugin marketplace add artemnovitckii/claude-editing-skills, затем /plugin install editing-skills@claude-editing-skills.
Что делает editing-skills?
Плагин добавляет одиннадцать сценариев монтажа видео: шесть для роликов с говорящим ведущим и пять с фотографическими стилями. Сценарии оформляют речь титрами, графикой и изображениями.
Что нужно для работы editing-skills?
Нужны macOS или Linux, ffmpeg, Node.js 22+ и Python 3.9+. Для расшифровки в исходных шести сценариях нужен бесплатный ключ Groq API; пять фотографических шаблонов работают без ключа.
Исходный текст
SKILL.md · MIT
# Claude editing skills Eleven skills for Claude Code: six workflows that edit your talking-head clips around your words, plus five photographic styles with editable templates and included image assets. Rendering happens on your own computer.  | Skill | What it makes | |---|---| | `/trial-reels` | The same clip as **3 visually distinct reels** to post as Instagram trial reels: a big title with karaoke captions, a post-card header with punch-in zooms, and a pixel-font stat in a framed shot. | | `/behind-the-person` | **Graphics behind you.** You are cut out and stand in front of a panel (your post grid, a bar chart or a screenshot). Big words land on your chest and a profile card counts up. | | `/explainer` | **You at the bottom, visuals on top.** A rounded panel on a light backdrop with your head breaking out over it, and a before-to-after comparison (or a list) explaining the point. | | `/split-screen` | **The classic half-and-half.** A step badge, a serif headline and a window showing the step on top, you on the bottom, and captions on the seam. | | `/ranking-list` | **A tier list on your chest.** Each item pops up when you name it and drops into its tier (S to F) on the verdict. | | `/storytelling` | **Three image cards, a title and a subtitle**, all landing together over one continuous take, with simple TikTok-style captions. | ## Five new photographic styles | Skill | What it makes | |---|---| | [`/shape-shift`](skills/shape-shift/SKILL.md) | Circular photographic match cuts above an established speaker. | | [`/picture-stack`](skills/picture-stack/SKILL.md) | Three image cards above the speaker, then one expands into focus. | | [`/scene-switch`](skills/scene-switch/SKILL.md) | Sharp photographic backgrounds change behind a continuous speaker cutout. | | [`/visual-notes`](skills/visual-notes/SKILL.md) | A complete image becomes a close-up of one meaningful detail. | | [`/orbit-reel`](skills/orbit-reel/SKILL.md) | Image cards orbit in 3D, passing behind and in front of the speaker. | | Shape Shift | Picture Stack | Scene Switch | Visual Notes | Orbit Reel | |---|---|---|---|---| | [](docs/style-showcase/shape-shift.mp4) | [](docs/style-showcase/picture-stack.mp4) | [](docs/style-showcase/scene-switch.mp4) | [](docs/style-showcase/visual-notes.mp4) | [](docs/style-showcase/orbit-reel.mp4) | Click an image for its moving preview. These five start from reviewed **4.2-second silent templates**, with nine source photographs and sample footage included. They can showcase a visual idea independently of the spoken topic. [Build and customize them](docs/style-showcase/README.md) · [Browse the images and credits](assets/style-showcase/README.md). See the original six moving: **[novitckii.com/resources/editing-skills](https://novitckii.com/resources/editing-skills/)** More skills are coming. Pull the repo to get them. ## Install You need macOS or Linux with **ffmpeg**, **Node.js 22+** and **Python 3.9+**, plus a free **[Groq API key](https://console.groq.com/keys)** for the original six skills’ transcripts. The five photographic templates do not require an API key. ```bash brew install ffmpeg node # if you don't have them export GROQ_API_KEY=gsk_... # add it to ~/.zshrc so it sticks git clone https://github.com/artemnovitckii/claude-editing-skills.git ~/claude-editing-skills cd ~/claude-editing-skills && ./install.sh ``` `install.sh` links every skill into `~/.claude/skills/` (so they show up as `/trial-reels`, `/explainer` and so on) and runs the one-time setup. The setup: - makes a Python environment in `kit/.venv` - fetches GSAP - warms up HyperFrames - downloads the matting model when run with `--cutout` To update later, run `git pull && ./install.sh`. **It's also packaged as a Claude Code plugin.** Run these inside Claude Code: ``` /plugin marketplace add artemnovitckii/claude-editing-skills /plugin install editing-skills@claude-editing-skills ``` Plugin skills are namespaced (`/editing-skills:explainer`). The git clone above is the route tested end to end. ## Use the original six workflows Open Claude Code anywhere and point it at a clip: ``` /explainer ~/Downloads/my-clip.mp4 /trial-reels ~/Downloads/my-reel.mp4 use the hook /behind-the-person ~/Downloads/clip.mp4, my posts are in ~/Desktop/posts ``` The original six skills follow these five steps: 1. It transcribes the clip with word timings (Groq Whisper). 2. It picks a stretch and looks at a frame to find your eyes and chin. 3. It writes a small JSON spec next to your clip. Every visual is anchored to a spoken word, so it lands when you say it. 4. It renders with [HyperFrames](https://github.com/heygen-com/hyperframes) (HTML and GSAP to MP4, 1080x1920, 30 fps, your voice kept). 5. It checks a contact sheet with Instagram's safe zones marked, and fixes what's off. You get `my-clip.explainer.mp4` (and its `.sheet.jpg`) next to the clip. Rendering takes about 15 to 30 seconds per reel. The cutout skills add about 0.1 s per frame for the matting. Bring your own images (your posts, screenshots, analytics) for the visuals that need them. Every skill also has visuals that need none. ## How it's built ``` skills/<name>/SKILL.md what Claude follows: steps, the spec, taste rules skills/<name>/build.py spec.json -> HyperFrames composition -> mp4 kit/reel.py shared: clip prep, word anchors, captions, render, checks kit/transcribe.py Groq Whisper with word timestamps kit/cutout.py speaker cutout (RobustVideoMatting, ONNX on the CPU) -> VP9 alpha webm kit/setup.sh one-time setup ``` To add a skill, copy a folder in `skills/` and change its `build.py`. The original six use `Job(spec) -> Comp -> finish()` for clips, words, captions, rendering and safe-zone sheets. The five photographic styles use `kit/style_template.py` to prepare their editable HTML templates and media overrides. Then run `./install.sh` again. ## Credits - [HyperFrames](https://github.com/heygen-com/hyperframes) by HeyGen renders the compositions. - [GSAP](https://gsap.com) drives the animation. It is fetched at setup, not included here. - [RobustVideoMatting](https://github.com/PeterL1n/RobustVideoMatting) by Shanchuan Lin et al. (GPL-3.0) does the cutout. The model is downloaded at setup, not included here. - Transcription is Whisper on [Groq](https://groq.com). - The fonts are Inter, Archivo Black, DM Serif Display, Instrument Serif, Pixelify Sans and TikTok Sans, all under the SIL Open Font License. Made by [Artem Novitckii](https://novitckii.com). Code and authored instructions are MIT licensed; [image and sample-media rights are separate](assets/style-showcase/README.md#rights-and-sample-footage).
© Artem Novitckii · MIT · artemnovitckii/claude-editing-skills