scene-switch — Claude Code skill: video edits and install
This Claude Code skill switches full-frame photo backgrounds behind a continuously visible speaker in portrait video. Invoke /scene-switch or request this visual treatment.
MIT ★ 94 updated 2026-10-30
/plugin marketplace add artemnovitckii/claude-editing-skills
/plugin install editing-skills@claude-editing-skillsWhat scene-switch does
The skill builds a portrait clip with the speaker on one continuous alpha layer and photographs changing behind them at set points. Image crops and the caption can be adjusted. It includes a 4.2-second starter at 1080×1920 and 30 fps; with no spec, the build writes a silent sample to .work/.
It requires Python 3.9+, ffmpeg, ffprobe, Node.js 22+ and npm. The first build downloads GSAP 3.15.0, and HyperFrames 0.8.214 handles rendering. Replacing the presenter requires a frame-matched alpha cutout at the same dimensions; the helper does not segment footage automatically. Audio is off by default.
What it helps with
- switch photo backgrounds behind a portrait-video speaker
- adjust image crops and captions
- prepare an editable composition without rendering
- validate and render an MP4
Example prompts for the agent
- Apply
/scene-switchto this portrait clip. - Change the background while keeping the presenter visible throughout.
- Prepare an editable composition without rendering.
How to install scene-switch
1Plugin marketplace
/plugin marketplace add artemnovitckii/claude-editing-skills/plugin install editing-skills@claude-editing-skillsThis installs the whole editing-skills plugin with all its skills
2Skills CLI (Vercel)
npx skills add artemnovitckii/claude-editing-skills --skill scene-switch -a claude-code3Manually: put the files in place
~/.claude/skills/scene-switch/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/scene-switch/
1Skills CLI (Vercel)
npx skills add artemnovitckii/claude-editing-skills --skill scene-switch -a codex2Manually: put the files in place
.agents/skills/scene-switch/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add artemnovitckii/claude-editing-skills --skill scene-switch -a cursor2Manually: put the files in place
.cursor/skills/scene-switch/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install artemnovitckii/claude-editing-skills skills/scene-switch2Manually: put the files in place
.github/skills/scene-switch/SKILL.md1Skills CLI (Vercel)
npx skills add artemnovitckii/claude-editing-skills --skill scene-switch -a gemini-cli2Platform CLI
gemini skills install https://github.com/artemnovitckii/claude-editing-skills --path skills/scene-switchManually: put the files in place
.devin/skills/scene-switch/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about scene-switch
How do I install scene-switch in Claude Code?
Run these commands in order: /plugin marketplace add artemnovitckii/claude-editing-skills, then /plugin install editing-skills@claude-editing-skills.
What does scene-switch do?
It builds portrait video with a continuously visible speaker and switching photographic backgrounds. The helper prepares the composition, checks rendering, and produces an MP4.
What does scene-switch require?
It requires Python 3.9+, ffmpeg, ffprobe, Node.js 22+ and npm. The first build downloads GSAP 3.15.0; rendering uses HyperFrames 0.8.214.
Source text
SKILL.md · MIT
--- name: scene-switch description: Full-frame photographic backgrounds cut behind a continuously visible isolated speaker. Use for /scene-switch or to apply this specific portrait-video treatment. --- # /scene-switch Apply this treatment to a portrait clip using the included 4.2-second, 1080x1920, 30fps starter. The style and images are independent of the sample speaker’s words; follow the user’s chosen topic. [See the reviewed example](../../docs/style-showcase/scene-switch.mp4). ## Use Resolve this skill folder from the base directory shown when the skill loads. Its `build.py` resolves the shared kit through that real path, including when installed as a symlink. Run: ```bash python3 /path/to/skills/scene-switch/build.py /path/to/spec.json ``` With no spec, the command reproduces the included silent sample into the repository’s `.work/` directory. `--prepare-only` builds an editable composition without rendering. Python 3.9+, ffmpeg/ffprobe and Node.js 22+/npm are required. The first build downloads pinned GSAP 3.15.0 into the ignored vendor cache; rendering uses HyperFrames 0.8.214. No transcript or API key is needed for these short templates. [Spec and custom-footage instructions](../../docs/style-showcase/README.md). ## Adapt the treatment Keep one continuous alpha speaker layer while the backgrounds switch at 1.4s and 2.8s. Tune `#scene0` through `#scene2`, their image crops, and `#caption`. Choose backgrounds with a coherent visual relationship and keep movement away from the face. Asset keys: `blue-stairs.jpg`, `cactus.jpg`, `explainer_cut.webm`, `red-stairs.jpg`. Full-resolution example images and source credits are in [assets/style-showcase](../../assets/style-showcase/README.md). Supply a same-size, frame-matched alpha cutout when changing the presenter. The existing `kit/cutout.py` can create it; see the shared guide. Inspect hair and hands over both bright and dark imagery. The build helper does not perform segmentation automatically. Keep the presenter visible from the first result frame. Use sharp photographs and clean type. Essential text and the face should clear platform overlays; let decorative imagery bleed rather than shrinking the entire composition. The sample’s captions and image anchors are starting points, not automatic tracking. ## Review and deliver The helper validates media dimensions/duration, prepares the composition, runs the renderer check, renders and fully decodes the MP4. Inspect the first frame, the main change and the ending. Check crop anchors, text readability and matching source/cutout timing. The default is silent; preserve or add speech, SFX or music only when the user requests them. Longer edits require extending the HTML timeline and source windows; changing only the duration is insufficient. These are local Claude Code/Codex editing workflows. The ChatGPT conversation in the showcase is an authored visual, not a built-in ChatGPT slash-command integration. Third-party image rights are documented separately from the code license in the asset directory.
© Artem Novitckii · MIT · artemnovitckii/claude-editing-skills