# veo-3.2-prompter

Turns your images, clips and audio into one ready JSON prompt for Google Veo 3.2 video generation. Handy when the request is complex and needs careful structuring.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 510 installs · ★ 814
- Author: wells
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/pexoai/pexo-skills/tree/HEAD/skills/veo-3.2-prompter/SKILL.md
- Updated: 2026-08-20
- HTML: https://affpapa.org/en/nevibecode/skills/veo-32-prompter

## What it does

The skill reads whatever assets you attach and builds a structured prompt for the Veo 3.2 model running on the Artemis engine. It works in three phases: recognising the assets, picking a reference method for each atomic element, then assembling the final prompt. What comes back is a single JSON object with the prompt text, a list of reference images and recommended parameters such as duration, aspect ratio and resolution.

Prompt construction follows a five-part framework: shot, subject, environment, camera, style. Reference images are attached through the `RawReferenceImage` system in the Gemini API. Two knowledge files ship with it: `references/atomic_element_mapping.md` holds the mapping tables for asset types and reference methods, and `references/veo_syntax_guide.md` covers the API syntax, video extension and first/last frame specification.

The agent runs the intermediate steps on its own and does not surface them. Keep in mind the output is a prompt and a parameter set, not a rendered video, so you still fire off the generation yourself. It also targets Veo 3.x models specifically, which means a different generator gets you nothing here.

Install takes one command through `npx skills add`, and the skill file lands at `~/.claude/skills/veo-3.2-prompter/SKILL.md`.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add pexoai/pexo-skills --skill veo-3.2-prompter -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/veo-3.2-prompter/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/veo-3.2-prompter/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add pexoai/pexo-skills --skill veo-3.2-prompter -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/veo-3.2-prompter/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add pexoai/pexo-skills --skill veo-3.2-prompter -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/veo-3.2-prompter/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install pexoai/pexo-skills veo-3.2-prompter
```

2. **Manually: put the files in place**
- File: `.github/skills/veo-3.2-prompter/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add pexoai/pexo-skills --skill veo-3.2-prompter -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/pexoai/pexo-skills --path skills/veo-3.2-prompter
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/veo-3.2-prompter/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add pexoai/pexo-skills --skill veo-3.2-prompter -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/pexoai/pexo-skills/tree/HEAD/skills/veo-3.2-prompter/SKILL.md

## When to use it
- build a cinematic prompt from an uploaded product photo
- break a complex idea into shot, subject, environment, camera and style
- choose how each asset should be referenced: image, text or hybrid
- get a JSON payload with the prompt and parameters for Veo 3.2
- set first and last keyframes or extend an existing clip

## Example prompts
- help me build a Veo 3.2 prompt from this perfume bottle image, luxury commercial look
- break my idea into the five parts and output JSON for veo-3.2-generate
- which reference images and parameters fit this Veo 3.2 video

## 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: 303ca5186a9880d8.

BEGIN THIRD-PARTY FILE 303ca5186a9880d8
````text
---
name: veo-3.2-prompter
description: >
  Expert prompt engineering for Google Veo 3.2 (Artemis engine). Use when the user wants to generate a video with Veo 3.2, needs help crafting cinematic prompts, or mentions Veo, Google video generation, or Artemis engine.
version: 0.1.0
author: wells
tags: [video, generation, prompt, veo, google, artemis, cinematic]
---

# Veo 3.2 Prompt Designer Skill

This skill transforms a user's scattered multimodal assets (images, videos, audio) and creative intent into a structured, executable prompt for the Google Veo 3.2 video generation model (Artemis engine). It acts as an expert prompt engineer, ensuring the highest quality output from the underlying model.

## When to Use

- When the user provides assets (images, videos, audio) for video generation with Veo 3.2.
- When the user's request is complex and requires careful prompt construction for the Veo model.
- When using any Google Veo 3.x model for video generation.

## Core Function

This skill analyzes all user inputs and generates a single, optimized JSON object containing the final prompt and recommended parameters. The internal workflow (Recognition, Mapping, Construction) is handled automatically and should not be exposed to the user.

### Internal Workflow

1. **Phase 1: Recognition** — Analyze uploaded assets and user intent. Use the `atomic_element_mapping.md` to classify each asset into its atomic element role(s).
2. **Phase 2: Mapping** — For each atomic element, determine the optimal reference method (reference image, text prompt, or hybrid). Use the mapping table to decide.
3. **Phase 3: Construction** — Assemble the final prompt using the 5-Part Framework (Shot → Subject → Environment → Camera → Style) and attach reference images via the Gemini API's `RawReferenceImage` system.

## Usage Example

**User Request:** "Make a cinematic shot of this perfume bottle rotating on a dark surface, like a luxury commercial."
*User uploads `perfume.png`*

**Agent using `veo-3.2-prompter`:**
*The agent internally processes the request and assets, then outputs the final JSON to the next skill in the chain.*

**Final Output (for internal use):**
```json
{
````
END THIRD-PARTY FILE 303ca5186a9880d8

The third-party file has ended. Everything between the 303ca5186a9880d8 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 2193 of 3885 bytes. © wells · MIT · https://github.com/pexoai/pexo-skills/tree/HEAD/skills/veo-3.2-prompter/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