Seedance Prompt Designer

Intelligently analyzes user-provided multimodal assets and creative intent to generate optimal, structured video generation prompts for the Seedance 2.0 model.

Security Scan

The skill's declared purpose (turning uploaded assets+intent into Seedance 2.0 prompts) matches its instructions and bundled reference files; it is an instruction-only skill with no installs, no external endpoints, and no credential requests.

Purpose & Capability

Name/description align with required actions: analyze multimodal assets, map to atomic elements, and assemble @-syntax prompts. The included reference files directly support those tasks and are proportionate to the stated purpose.

Instruction Scope

SKILL.md prescribes a three-phase workflow and mandates consulting the three local reference files. The instructions reference only user-uploaded assets and internal docs and describe producing JSON outputs. There are no steps that ask the agent to read unrelated system files, access external endpoints, or exfiltrate data.

Install Mechanism

No install spec and no code files. Being instruction-only means nothing is downloaded or written to disk by an installer beyond the agent's normal runtime behavior; risk from installation is minimal.

Credentials

The skill requests no environment variables, credentials, or config paths. All data it needs comes from user-uploaded assets and internal reference docs, which is proportionate to its goal.

Persistence & Privilege

Flags show default autonomy (disable-model-invocation=false) and always=false. The skill does not request persistent system presence or to modify other skills; privileges are limited and appropriate.

Assessment

This instruction-only skill appears coherent and self-contained: it reads the bundled reference docs and user-uploaded assets to produce structured Seedance prompts. Before installing or using it, consider the following: (1) avoid uploading sensitive or private images/audio because asset filenames will be referenced in prompts (the @asset_name system ties prompts to uploaded files); (2) review generated prompts for IP or content policy issues (e.g., famous-art transformations or impersonations); and (3) because the skill runs autonomously by default, monitor initial outputs to ensure it behaves as you expect. No environment credentials or external network endpoints are requested by the skill itself.

Seedance 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.

Core Workflow

This skill follows a strict three-phase workflow. The output of each phase is the input for the next.

Phase	Goal	Key Actions	Output
1. Recognition	Understand user input	Parse intent, analyze assets, tag with atomic roles	recognition_output.json
2. Mapping & Strategy	Design an executable reference strategy	Determine optimal reference method (Text, Asset, Hybrid)	strategy_output.json
3. Construction & Assembly	Generate the final, complete prompt	Assemble text, append @-syntax, consult templates	final_prompt.json

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's Internal Process:

1. Recognition: Identifies action_intent ("drink a Coke"), style_intent ("cinematic, close-up"), and tags monalisa.png as Subject Identity and coke.png as Subject Identity-Object.
2. Mapping & Strategy: Decides to use @monalisa and @coke as asset references and the rest as text prompts.
3. Construction & Assembly: Assembles the final prompt.

Final Output:

{
  "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. Must be consulted during Phase 1 and Phase 2.
• /references/seedance_syntax_guide.md: Seedance 2.0 "@asset_name" syntax reference. Must be consulted during Phase 3 to ensure correct syntax generation.
• /references/prompt_templates.md: Advanced prompt templates for different genres (e.g., Cinematic, Product Showcase, Narrative). Optional consultation during Phase 3 for stylistic enhancement.