Individual skill
vox-director
Turn ONE topic into a finished Vox-style paper-collage explainer / ad video, end to end on the Atlas Cloud API + local ffmpeg — script, collage keyframes, motion, voice-over, music, captions, all automated. Use this whenever the user wants a "Vox style" video, a paper/torn-paper collage animation, a "motion collage", a narrated explainer or short ad built from AI-generated collage posters, a scrapbook-style tribute, or wants to turn a topic / product / person into a punchy narrated collage video — even if they don't say the word "Vox". Also use when reproducing Stav Zilber / rom1trs / Higgsfield-style collage ad workflows. Three input modalities: a topic (B-roll), a talking-head video (A-roll mode), or a single photo of a person/product anchored into the collage (C-roll mode). Triggers: "vox video", "collage video", "motion collage", "paper collage explainer", "make a collage ad", "turn this topic into a collage video", "turn my photo/this product shot into a collage video".
SKILL.md
Source commit 6a85a7c341610442a6a5b1885e6e0217ab82a11f
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- No
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Not checked yet
- Last checked
- Nov 9, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 2,781
- Repository last updated
- Oct 5, 2026
- License
- MIT
Observed agent integration: codex
- ai-video Repository topic
- claude-code Repository topic
- claude-skill Repository topic
- explainer-video Repository topic
- motion-graphics Repository topic
- text-to-video Repository topic
- vox Repository topic
- collage-video Repository topic
- ai Repository topic
- ffmpeg Repository topic
- research Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
.gitignoreasset · 512 bytesAGENTS.mddoc · 1,259 bytesLICENSEasset · 1,067 bytesREADME.mddoc · 8,493 bytesREADME.zh.mddoc · 8,133 bytesSKILL.mdcore · 22,397 bytesSKILL.mdcore · 22,397 bytesSKILL.zh.mddoc · 20,061 bytesassets/showcase-football.mp4asset · 8,257,315 bytesassets/showcase-money.mp4asset · 8,493,950 bytesassets/showcase-silicon-valley.mp4asset · 6,144,834 bytesassets/showcase-tang.mp4asset · 7,928,635 bytesassets/thumbs/football.jpgasset · 49,052 bytesassets/thumbs/mexican.jpgasset · 42,912 bytesassets/thumbs/money.jpgasset · 25,761 bytesassets/thumbs/silicon-valley.jpgasset · 35,292 bytesassets/thumbs/tang.jpgasset · 47,537 bytesexamples/cr7-act.elements_spec.jsonasset · 1,795 bytesexamples/money-15s.beats.jsonasset · 2,637 bytesexamples/money-60s-9x16-english.beats.jsonasset · 26,503 bytesexamples/ronaldo-9x16-kling.beats.jsonasset · 4,983 bytesexamples/tang-30s.beats.jsonasset · 13,462 bytesllms.txtdoc · 1,442 bytespackage.jsonruns · 933 bytesreferences/beat-layer.mddoc · 10,451 bytesreferences/host-mode.mddoc · 6,866 bytesreferences/local-engine.mddoc · 4,556 bytesreferences/models-and-gotchas.mddoc · 5,984 bytesreferences/prompt-guide.mddoc · 20,588 bytesreferences/voices.mddoc · 4,181 bytesscripts/aroll_assemble.pyruns · 3,413 bytesscripts/aroll_clips.pyruns · 9,224 bytesscripts/asr_beats.pyruns · 6,885 bytesscripts/assemble.pyruns · 7,783 bytesscripts/atlas_cloud.pyruns · 8,693 bytesscripts/audio.pyruns · 5,311 bytesscripts/clips.pyruns · 10,426 bytesscripts/confetti.pyruns · 2,008 bytesscripts/croll_keyframes.pyruns · 6,834 bytesscripts/extract_elements.pyruns · 2,881 bytesscripts/host.pyruns · 15,832 bytesscripts/host_clips.pyruns · 9,038 bytesscripts/host_plates.pyruns · 4,843 bytesscripts/kenburns.pyruns · 3,217 bytesscripts/keyframes.pyruns · 3,967 bytesscripts/lipsync_score.pyruns · 3,960 bytesscripts/mg_scrapbook.pyruns · 7,299 bytesscripts/motion.pyruns · 9,874 bytesscripts/provider.pyruns · 5,132 bytesscripts/style_bakeoff.pyruns · 3,143 bytesscripts/styles.pyruns · 14,950 bytesscripts/text_overlay.pyruns · 6,487 bytesvox-director.skillasset · 113,466 bytes
Read excerpt
# Vox Director
Turn a one-line topic into a finished **Vox-style paper-collage video**: a bold, punchy,
narrated explainer/ad where each beat is a torn-paper collage poster that comes alive, with
voice-over, music and captions. Runs on **one Atlas Cloud API key** + local **ffmpeg**.
The look is the modern editorial paper-collage popularized by Vox explainers and creators
like Stav Zilber / rom1trs: hand-cut paper cut-outs, torn edges, tape, halftone dots,
newspaper clippings, bold flat color per beat, big cut-out headlines.
## The core idea (read this first)
The Vox collage look and the collage motion are **two different steps**:
