Veo 3.2 Prompter

If you're working with Google's Veo 3.2 video generator and need help turning messy creative input into proper prompts, this does that translation work. It takes your images, videos, audio clips, and rough ideas, then outputs a structured JSON with an optimized prompt using Veo's 5-part framework (shot, subject, environment, camera, style) plus the right reference image attachments and parameters. Built specifically for the Artemis engine's capabilities like native audio generation, multi-reference images, and physics-based rendering. Honestly most useful when you're chaining this into a larger workflow where the next step actually calls the Veo API, since it just prepares the payload rather than generating video itself.

skills.sh installs: 240
GitHub stars: 768
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add pexoai/pexo-skills --skill veo-3.2-prompter --agent claude-code

Installs into .claude/skills of the current project.

Files

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.