home / skills / pexoai / pexo-skills / seedance-2.0-prompter

seedance-2.0-prompter skill

safe

This skill transforms scattered multimodal assets and intent into a structured executable prompt for Seedance 2.0, ensuring high quality video prompts.

npx playbooks add skill pexoai/pexo-skills --skill seedance-2.0-prompter

Review the files below or copy the command above to add this skill to your agents.

Files (4)

SKILL.md

2.4 KB

---
name: seedance-2.0-prompter
description: >
  Expert prompt engineering for Seedance 2.0. Use when the user wants to generate a video with multimodal assets (images, videos, audio) and needs the best possible prompt.
version: 2.1.0
author: pexoai
tags: [video, generation, prompt, seedance, multimodal]
---

# Seedance 2.0 Prompt Designer Skill

This skill transforms a user's scattered multimodal assets (images, videos, audio) and ambiguous creative intent into a structured, executable prompt for the Seedance 2.0 video generation model. It acts as an expert prompt engineer, ensuring the highest quality output from the underlying model.

## When to Use

- When the user provides multiple assets (images, videos, audio) for video generation.
- When the user's request is complex and requires careful prompt construction.
- When using the Seedance 2.0 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.

## Usage Example

**User Request:** "Make the Mona Lisa drink a Coke. I want it to feel cinematic, like a close-up shot."
*User uploads `monalisa.png` and `coke.png`*

**Agent using `seedance-2.0-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": "A cinematic close-up shot of a woman picking up a bottle of Coke and taking a sip. The scene is lit with dramatic, high-contrast lighting. Use @monalisa as the subject reference, and the object appearing in the video is @coke.",
  "recommended_parameters": {
    "duration": 8,
    "aspect_ratio": "16:9"
  }
}
```

## 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.
- **`/references/seedance_syntax_guide.md`**: Seedance 2.0 "@asset_name" syntax reference.
- **`/references/prompt_templates.md`**: Advanced prompt templates for different genres (e.g., Cinematic, Product Showcase, Narrative).

Overview

This skill is an expert prompt engineer for Seedance 2.0 that converts scattered multimodal assets and vague creative briefs into a single, high-quality prompt and recommended parameters. It focuses on maximizing video generation fidelity when the user supplies images, clips, or audio. The output is an optimized JSON object ready for the next step in a generation pipeline.

How this skill works

It ingests user text plus any uploaded images, videos, and audio, then analyzes asset types and creative intent to produce a concise final_prompt string and recommended generation parameters (duration, aspect ratio, style cues, etc.). The skill consults internal reference mappings and Seedance syntax rules to ensure assets are referenced correctly (e.g., @asset_name) and that prompts follow best-practice templates.

When to use it

You have multiple assets (images, video clips, audio) for a single video project.
The creative brief is ambiguous or contains mixed stylistic requests that need consolidation.
You want a single, executable prompt and recommended parameters for Seedance 2.0.
Preparing inputs for a chained agent workflow where a downstream skill performs generation.
Optimizing prompts for cinematic, product, or narrative genres using available assets.

Best practices

Provide clear asset names and short captions so the skill can generate accurate @asset_name references.
Attach high-quality source files; include representative stills for key subjects when possible.
State desired shot types, duration, and mood explicitly (e.g., close-up, 8s, cinematic).
Mention any constraints (brand safety, licensing, motion limits) up front.
Allow the skill to consult its internal reference files for asset mapping and Seedance syntax compliance.

Example use cases

Turn a product photo, a voiceover clip, and a short demo video into a polished 10s product showcase prompt.
Combine a portrait image and background footage to create a cinematic character close-up sequence.
Convert a storyboard text and several concept images into a single Seedance 2.0 narrative prompt with timing suggestions.
Prepare a branded social video by referencing logo and jingle assets with explicit usage instructions.

FAQ

What does the skill return?

A JSON object containing a final_prompt string and recommended_parameters such as duration and aspect_ratio.

Do I need to format asset names a certain way?

Provide short, descriptive filenames; the skill will map them to Seedance @asset_name references using its internal guidelines.