shape-shift — Claude Code skill: video editing and installation
The shape-shift Claude Code skill builds portrait videos with a match cut between circular subjects. Each subject aligns to one anchor while the speaker stays below the photo panel.
MIT ★ 94 updated 2026-10-30
/plugin marketplace add artemnovitckii/claude-editing-skills
/plugin install editing-skills@claude-editing-skillsWhat shape-shift does
The skill assembles a portrait clip in which circular subjects change at a fixed point while the speaker remains visible beneath the photo panel. Its starter is 4.2 seconds long, at 1080x1920 and 30 fps. Without a spec file, the command writes a silent sample to .work/.
Builds require Python 3.9+, ffmpeg, ffprobe, Node.js 22+ and npm. The first build fetches GSAP 3.15.0 into a cache; HyperFrames 0.8.214 handles rendering. The helper checks media dimensions and duration, prepares the composition, renders the MP4 and decodes the finished file.
Replacement photos need manual alignment to the shared anchor; otherwise, the match cut breaks. A new presenter needs a frame-matched alpha cutout at the same dimensions. The helper does not segment footage automatically. Longer edits require changes to the HTML timeline and source windows, not just the duration.
What it helps with
- create a portrait clip with a match cut between circular subjects
- keep the presenter visible beneath the photo panel
- prepare an editable composition without rendering
- check media dimensions and decode the rendered MP4
Example prompts for the agent
- Make a portrait clip in the
shape-shiftstyle about this topic. - Prepare an editable
shape-shiftcomposition without rendering. - Apply
shape-shiftto this portrait clip and replace the photos with these.
How to install shape-shift
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 shape-shift -a claude-code3Manually: put the files in place
~/.claude/skills/shape-shift/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/shape-shift/
1Skills CLI (Vercel)
npx skills add artemnovitckii/claude-editing-skills --skill shape-shift -a codex2Manually: put the files in place
.agents/skills/shape-shift/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add artemnovitckii/claude-editing-skills --skill shape-shift -a cursor2Manually: put the files in place
.cursor/skills/shape-shift/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install artemnovitckii/claude-editing-skills skills/shape-shift2Manually: put the files in place
.github/skills/shape-shift/SKILL.md1Skills CLI (Vercel)
npx skills add artemnovitckii/claude-editing-skills --skill shape-shift -a gemini-cli2Platform CLI
gemini skills install https://github.com/artemnovitckii/claude-editing-skills --path skills/shape-shiftManually: put the files in place
.devin/skills/shape-shift/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 shape-shift
How do I install shape-shift in Claude Code?
Run /plugin marketplace add artemnovitckii/claude-editing-skills, then /plugin install editing-skills@claude-editing-skills.
What does shape-shift do?
It builds portrait video with a match cut: circular subjects line up at one anchor while the speaker stays below the photo panel.
What does shape-shift need to run?
It requires Python 3.9+, ffmpeg, ffprobe, Node.js 22+ and npm. The build fetches GSAP 3.15.0, and rendering uses HyperFrames 0.8.214.
Source text
SKILL.md · MIT
--- name: shape-shift description: A photographic match cut aligns circular subjects at one fixed anchor while the speaker stays established below. Use for /shape-shift or to apply this specific portrait-video treatment. --- # /shape-shift 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/shape-shift.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/shape-shift/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 Align the circular subject in every replacement photograph to the same anchor in `#photo-stage`. The example moves from an orange slice to a record and camera lens. Adjust each image’s width, left and top together; swapping an image without re-aligning its circle breaks the match cut. The speaker is a continuous alpha layer below the photographic panel. Asset keys: `camera.jpg`, `explainer_cut.webm`, `orange.jpg`, `record.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