# vox-director

This skill turns a single topic into a finished paper-collage explainer or ad: script, poster keyframes, motion, voice-over, music and captions. It runs on the Atlas Cloud API plus local ffmpeg.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · ★ 2446
- Author: Alisa0808
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/Alisa0808/vox-director/tree/HEAD/SKILL.md
- Updated: 2026-10-05
- HTML: https://affpapa.org/en/nevibecode/skills/vox-director

## What it does

The skill takes a project from one topic to a rendered file. It first maps the topic onto beats along a narrative arc, then generates a collage poster per beat, animates those posters with image-to-video, and adds narration, music and captions. Scripts handle each stage, and the whole project state lives in a single `beats.json` under `out/<project>/`.

Three input modes are supported: a topic (B-roll), a talking-head video (A-roll), and a single photo of a person or product anchored into the collage (C-roll). Separate scripts cover the work: `style_bakeoff.py` for picking a visual style, `keyframes.py` for posters, `clips.py` for animation. Styles come from presets such as `american-retro`, `punk-zine` or `soviet-constructivist`, or you can compose a custom theme from the prompt-guide dimensions.

Check three things before you start: the `ATLASCLOUD_API_KEY` variable, `ffmpeg` and `ffprobe` on PATH, and Pillow for Python. Without the key the skill stops right away, so set that first. Two points need your call: the beat map before generation, and aspect routing against the chosen video model. For real people and brand logos, Omni and Seedance refuse, so you have to switch to `kwaivgi/kling-video-o3-pro/image-to-video`.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add Alisa0808/vox-director --skill vox-director -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/vox-director/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/vox-director/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add Alisa0808/vox-director --skill vox-director -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/vox-director/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add Alisa0808/vox-director --skill vox-director -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/vox-director/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install Alisa0808/vox-director vox-director
```

2. **Manually: put the files in place**
- File: `.github/skills/vox-director/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add Alisa0808/vox-director --skill vox-director -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/Alisa0808/vox-director
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/vox-director/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add Alisa0808/vox-director --skill vox-director -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/Alisa0808/vox-director/tree/HEAD/SKILL.md

## When to use it
- map a topic onto beats along a fitting narrative arc
- generate a collage poster per beat with the headline baked in
- animate static posters with varied camera moves
- assemble narration, music and captions into one film
- anchor a photo of a person or product into the collage

## Example prompts
- make a vox video about the history of the subway, 60 seconds
- build a collage ad for this product from my photo
- turn this topic into a motion collage with narration

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: 7854d1603ae8aeaf.

BEGIN THIRD-PARTY FILE 7854d1603ae8aeaf
```text
---
name: vox-director
description: >
  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".
---

# 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**:

1. **The look is born in the IMAGE step.** Each beat is a finished collage *poster* made by a
   text-to-image model. All the collage DNA (torn paper, cut-outs, halftone, bold color,
   headline text) lives in that image. If the image isn't a rich collage, nothing downstream
   will save it.
2. **The motion is added after.** By default an AI video model animates the whole poster (the
   "living poster" path — simple, automated). For dramatic *piece-by-piece* assembly you cut
   the poster into parts and drive them with the local keyframe engine (advanced path).

Everything hinges on the prompts. **Before writing any image or video prompt, read
`references/prompt-guide.md`** — it has the exact prompt structures that make the difference
between "a real Vox collage" and "a moving PowerPoint".

## Prerequisites (check, don't skip)
```
END THIRD-PARTY FILE 7854d1603ae8aeaf

The third-party file has ended. Everything between the 7854d1603ae8aeaf tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2549 of 22397 bytes. © Alisa0808 · MIT · https://github.com/Alisa0808/vox-director/tree/HEAD/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md