media-creation
Installation
SKILL.md
Use when
- Generate images or video via Alibaba Wan, Google Gemini/Veo, or OpenAI GPT Image APIs.
- Create transparent PNGs (prefer GPT Image 1.5 for native transparency support).
- Convert consistent renders (3D, compositing) with different backgrounds into a transparent RGBA output.
- Prefer Gemini for general image generation; use Wan when content is restricted (e.g., babies).
Don't use when
- If API access or credentials are not available.
- If the task does not involve media generation or background extraction.
Outputs
- Generated media files in
artifacts/(PNG, WEBP, MP4, etc.) or API JSON responses when requested.
Templates or Examples
- Use the API request examples below as templates.