Seedance 2.0 prompter

Skill ulpi-io/plugin-marketplace/plugins/pexoai/skills/seedance-2.0-prompter

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.From its SKILL.md

Install

npx -y skills add ulpi-io/plugin-marketplace --skill seedance-2.0-prompter

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.4 KB, 473 tokens by cl100k_base, as published. Nobody here has run it

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).

What ships with it: 3 files

7.8 KB alongside SKILL.md

references/

Gives 0 of the 12 instructions most video audio skills give in 473 tokens

Counted across 619 of the 725 authors here whose files we hold, read 2026-09-06

Read product marketing context firstin 13 of 619, across 7 files
Define the core visual thesis in one sentencein 11 of 619, across 3 files
Break the concept into 3 to 6 scenesin 11 of 619, across 3 files
Render the smallest working version firstin 11 of 619, across 3 files
Start with a low-quality smoke test renderin 11 of 619, across 3 files
Add captions for accessibility and engagementin 11 of 619, across 5 files
Write the scene outline before writing codein 11 of 619, across 3 files
Specify subject, action, camera, style, and moodin 11 of 619, across 5 files
Decide what each scene provesin 10 of 619, across 2 files
Export one clean thumbnail framein 10 of 619, across 2 files
Pick the right tool for the jobin 10 of 619, across 4 files
Run the test suite before proposing a fixin 8 of 619, across 7 files

Said here and by no other author read

Consult internal reference files during execution
Analyze all user inputs
Generate a single optimized JSON object

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.