picture-stack — Claude Code skill: video effect and install
The picture-stack Claude Code skill adds a floating-photo sequence to portrait video. Three images appear above the speaker before one grows into the focus image.
MIT ★ 94 updated 2026-10-30
/plugin marketplace add artemnovitckii/claude-editing-skills
/plugin install editing-skills@claude-editing-skillsWhat picture-stack does
The skill builds a portrait-video treatment that keeps the speaker and original room in view while three photo cards gather above them. Then one card expands to become the main image. Its starter composition runs for 4.2 seconds at 1080x1920 and 30fps. Use --prepare-only to create an editable composition without rendering.
The build needs Python 3.9+, ffmpeg, ffprobe, Node.js 22+ and npm. On the first build, it downloads GSAP 3.15.0; rendering uses HyperFrames 0.8.214. The helper checks the finished MP4 by decoding it fully. Output is silent by default, and longer edits require changes to the HTML timeline and source-video windows. Short templates need no transcript or API key.
What it helps with
- add a floating-photo sequence to portrait footage
- bring one of three photo cards into focus
- prepare an editable composition without rendering
- check a rendered MP4 through full decoding
Example prompts for the agent
- Apply
/picture-stackto this portrait clip. - Build a portrait edit with three photos above the speaker, then focus on one.
- Prepare the composition without rendering the video.
How to install picture-stack
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 picture-stack -a claude-code3Manually: put the files in place
~/.claude/skills/picture-stack/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/picture-stack/
1Skills CLI (Vercel)
npx skills add artemnovitckii/claude-editing-skills --skill picture-stack -a codex2Manually: put the files in place
.agents/skills/picture-stack/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add artemnovitckii/claude-editing-skills --skill picture-stack -a cursor2Manually: put the files in place
.cursor/skills/picture-stack/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install artemnovitckii/claude-editing-skills skills/picture-stack2Manually: put the files in place
.github/skills/picture-stack/SKILL.md1Skills CLI (Vercel)
npx skills add artemnovitckii/claude-editing-skills --skill picture-stack -a gemini-cli2Platform CLI
gemini skills install https://github.com/artemnovitckii/claude-editing-skills --path skills/picture-stackManually: put the files in place
.devin/skills/picture-stack/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 picture-stack
How do I install picture-stack 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 picture-stack do?
It adds three photo cards above the speaker in a portrait clip, then enlarges one card into the main image.
What does picture-stack require?
It needs Python 3.9+, ffmpeg, ffprobe, Node.js 22+ and npm. The first build fetches GSAP 3.15.0, and rendering uses HyperFrames 0.8.214.
Source text
SKILL.md · MIT
--- name: picture-stack description: A small cluster of photographs floats above the speaker in the original room, then one photograph takes focus. Use for /picture-stack or to apply this specific portrait-video treatment. --- # /picture-stack 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/picture-stack.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/picture-stack/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 the original room and speaker continuous. Three photographic cards collect above the head; at 2.05s the first two leave and the third grows into the focus image. Tune `#p0`, `#p1`, `#p2` and `#q1` in the template. Preserve visible headroom and use small, purposeful rotations. Asset keys: `banana-heels.jpg`, `explainer.mp4`, `pixel-burger.jpg`, `pixel-fruit.jpg`. Full-resolution example images and source credits are in [assets/style-showcase](../../assets/style-showcase/README.md). This style uses the original room and requires no alpha cutout. 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. 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