veo-3.2-prompter

What the source does

• FilesystemNone observedNo reads or writes in the source
• NetworkNone observedNo outbound calls in the source
• ShellNone observedNo commands run in the source
• DependenciesPinnedNothing floats
• SecretsNone foundNo keys in source

Five audit layers

Gates applied: no behavioural pass.

Audit 0.4.1 · source sha a72d4da09420 · 23 Oct 2026Report an issue or request a re-scan

• Publisherpexoai GitHub userOwner of the repository this skill is read from
• Source folderpexoai/pexo-skills/skills/veo-3.2-prompterThe exact folder we audited
• LicenceMITAs the repository states it
• Commit pinned for this verdicta72d4da09420A new audit runs when the source changes
• Repository statusNot archivedLast push 64 days ago
• Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

Its 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.

---
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
{
  "final_prompt": "Hero shot, a frosted glass perfume bottle with gold cap rotating slowly on a reflective dark surface, three-point studio lighting with soft key and rim light creating subtle caustics, smooth 180-degree arc, hyper-realistic luxury commercial style with shallow depth of field. Crystalline chime, soft ambient pad.",
  "reference_images": [
    {
      "file": "perfume.png",
      "reference_type": "SUBJECT"
    }
  ],
  "recommended_parameters": {
    "model": "veo-3.2-generate",
    "duration_seconds": 8,
    "aspect_ratio": "16:9",
    "resolution": "1080p",
    "generate_audio": true
  }
}
```

## Veo 3.2 Key Differentiators

| Feature | Capability |
|---|---|
| Engine | Artemis — world-model physics simulation (not pixel prediction) |
| Max duration | ~30s native continuous generation |
| Audio | Native dialogue + synchronized SFX |
| Reference images | Up to 3 (`STYLE`, `SUBJECT`, `SUBJECT_FACE`) |
| Video extension | Chain clips via previous video input |
| First/last frame | Specify start and/or end keyframes |
| Resolutions | 720p, 1080p, 4K (with upscaling) |
| Aspect ratios | 16:9, 9:16 |

## Knowledge Base

This skill relies on an internal knowledge base to make informed decisions. The agent MUST consult these files during execution.

- **`references/atomic_element_mapping.md`**: **Core Knowledge**. Contains the "Asset Type → Atomic Element" and "Atomic Element → Optimal Reference Method" mapping tables, adapted for Veo 3.2's reference image system.
- **`references/veo_syntax_guide.md`**: Veo 3.2 Gemini API syntax reference, covering `RawReferenceImage`, `GenerateVideosConfig`, video extension, and first/last frame specification.

Excerpt, first 3,864 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

git clone https://github.com/pexoai/pexo-skills
git -C pexo-skills checkout a72d4da09420

Works in

1. 2026-10-23
   ✓SAFE B 89 / 100

   first audit · source a72d4da09420

Questions about veo-3.2-prompter

• github.com/pexoai/pexo-skills/tree/main/skills/veo-3.2-prompter — the audited source at commit a72d4da09420 and every finding aboveObserved · 23 Oct 2026

Spotted something wrong? Report a correction · Methodology