SKILL: Generate Video via Hyperframes

Description

Converts multimodal inputs (HTML files, raw text, YouTube URLs, PDFs, or Images) into an automated video sequence using the local Hyperframes framework. This skill orchestrates data extraction, script generation, and programmatic video rendering.

Trigger

Use this skill when the user asks to "create a video", "generate a hyperframes video", or "turn this [input] into a video".

Expected Inputs

The user must provide a target source. This can be:

1. A local file path (e.g., ./guide.html, ./report.pdf, ./diagram.png)
2. A raw text string
3. A YouTube URL

Execution Steps