carocut-media-visual

Retrieve stock or generate AI visuals for storyboard-driven video production.

120|12|Updated Mar 20, 2026
One-click install
npx skills add https://github.com/bilibili/carocut --skill carocut-media-visual
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: carocut-media-visual
Source: https://github.com/bilibili/carocut/tree/main/.opencode/skills/carocut-media-visual
Command: npx skills add https://github.com/bilibili/carocut --skill carocut-media-visual

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Visual production often stalls waiting for suitable visuals. This skill automates retrieval and generation of stock images, video clips, and AI-generated visuals to satisfy storyboard requirements and production timelines.

Core Features & Use Cases

  • Stock image/video retrieval from Pexels and Pixabay according to a resources.yaml.
  • AI-generated imagery guided by framing-aware search and metaphor search to match mood and composition.
  • Sprite sheet consideration and background removal to support animation and compositing tasks.

Quick Start

Fetch a batch of visuals for a product introduction video.

Frequently Asked Questions about carocut-media-visual

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate finding stock images and video clips for a storyboard?

AI-generated imagery uses framing-aware search to match composition and visual metaphor exploration to capture the desired mood, requiring specific image generation prompts defined in your resources.yaml.

Can I generate sprite sheets and remove backgrounds for video compositing?

Yes, you can generate sprite sheets and remove backgrounds to support animation and compositing tasks, delivering ready-to-use visual assets directly suited for video production workflows.

Do I need a resources.yaml file to retrieve stock images for video production?

Yes, a resources.yaml file is required to define storyboard-driven contexts, search strategies, and image generation prompts before retrieving stock images or generating AI visual assets.

What is the best way to batch fetch visuals for a product introduction video?

Batch fetch visuals for a product introduction video by configuring a resources.yaml with your storyboard contexts, enabling automated retrieval of stock media and generation of AI imagery.

What are the limitations of using framing-aware search for visual metaphor matching?

Framing-aware search and visual metaphor matching depend heavily on the accuracy of your image generation prompts and storyboard contexts defined in the resources.yaml to deliver relevant visual assets.