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.

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.

Type: OpenClaw Skill Name: seedance-prompt-designer Version: 2.0.0 The skill bundle appears benign. All files, including the SKILL.md instructions for the AI agent, describe a legitimate workflow for generating structured prompts for a video generation model. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, or prompt injection attempts designed to subvert the agent's intended function or access sensitive data. The instructions for the agent are limited to consulting internal knowledge base files (`atomic_element_mapping.md`, `seedance_syntax_guide.md`, `prompt_templates.md`) to fulfill its stated purpose.