PluginBench
Skill
Pass
Audit score 90

seedance-2.0-prompter

pexoai/pexo-skills

Expert prompt engineering for Seedance 2.0 video generation with multimodal assets.

What is seedance-2.0-prompter?

This skill transforms scattered images, videos, and audio into optimized prompts for Seedance 2.0 video generation. Use it when you have multiple assets and need structured, high-quality prompts that maximize the model's output quality.

  • Analyzes multimodal assets (images, videos, audio) and creative intent
  • Generates optimized JSON prompts with recommended parameters for Seedance 2.0
  • Applies asset-to-atomic-element mapping for proper reference syntax
  • Constructs cinematic and genre-specific prompts using internal templates
  • Handles complex creative requests with careful prompt engineering

How to install seedance-2.0-prompter

npx skills add https://github.com/pexoai/pexo-skills --skill seedance-2.0-prompter
Prerequisites
  • Access to Seedance 2.0 model or integration
  • Multimodal assets (images, videos, or audio files) to reference
  • Knowledge of Seedance 2.0 syntax and capabilities
Claude Code
Cursor
Windsurf
Cline

How to use seedance-2.0-prompter

  1. 1.Gather all multimodal assets (images, videos, audio) relevant to your video concept
  2. 2.Describe your creative intent and desired style (cinematic, product showcase, narrative, etc.)
  3. 3.Invoke the skill with your assets and description
  4. 4.Review the generated JSON prompt and recommended parameters
  5. 5.Pass the output to Seedance 2.0 or the next skill in your workflow

Use cases

Good for
  • Converting reference images and video clips into a single coherent video prompt
  • Creating cinematic product showcase videos from product images and brand assets
  • Generating narrative-driven videos from multiple scene references and audio tracks
  • Transforming ambiguous creative briefs into executable Seedance 2.0 parameters
  • Building high-quality video prompts when standard prompting produces suboptimal results
Who it's for
  • Video creators and producers using Seedance 2.0
  • Content creators working with multimodal assets
  • Prompt engineers optimizing AI video generation
  • Marketing and advertising teams creating video content
  • Anyone generating videos with complex creative requirements

seedance-2.0-prompter FAQ

What formats does this skill accept for assets?

The skill accepts images, videos, and audio files as multimodal inputs. Specific format requirements depend on your Seedance 2.0 integration.

Do I need to understand Seedance 2.0 syntax to use this skill?

No. The skill handles all syntax construction internally, including @asset_name references and parameter optimization.

Can this skill work with just one asset or image?

Yes, though it's optimized for multimodal scenarios with multiple assets. It will still generate a structured prompt for single-asset requests.

What does the skill output?

A JSON object containing a final_prompt string and recommended_parameters (duration, aspect_ratio, etc.) ready for Seedance 2.0.

How does the skill decide which prompt template to use?

It analyzes your creative intent and asset types, then applies the most appropriate template (cinematic, product showcase, narrative, etc.) from its knowledge base.

Full instructions (SKILL.md)

Source of truth, from pexoai/pexo-skills.


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):

{
  "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).