skills.rest
cgk-platform
cgk-platformOFFICIAL
Explore all skills by this author →
GitHub

video-remix

Analyze input videos and generate AI-driven remixes using Veo or Sora backends.

Updated Aug 27, 2026
Search Tags:#prompt-engineering#ai-video#video-remix#gemini-3-flash#veo-sora#image-remix
One-click install
npx skills add https://github.com/cgk-platform/cgk --skill video-remix
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: video-remix
Source: https://github.com/cgk-platform/cgk/tree/main/openclaw-skills/video-remix
Command: npx skills add https://github.com/cgk-platform/cgk --skill video-remix

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires google-genai, and includes scripts (resource) components.

What problem does it solve?

The Video Remix Skill analyzes input videos and produces AI-generated remixes using Veo/Sora backends, enabling rapid experimentation with different looks and styles without manual editing.

Core Features & Use Cases

  • Analyze videos with Gemini to extract scene details, lighting, and camera work for generation prompts.
  • Support two modes: Text-mode prompt-to-video and Image-remix mode (clone/remix from a frame or user-provided image) to create diverse outputs.
  • Use cases include rebranding video assets, creating alternate social media formats (9:16), and quickly generating multiple stylistic variations from a single clip.

Quick Start

Provide a video path or URL and your desired modifications, then run the skill to generate a remixed video.

Frequently Asked Questions about video-remix

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

FAQPage Schema
How do I generate an AI video remix from an existing clip?▼

To generate an AI video remix, provide a local file path or URL with your desired modifications. The skill analyzes the input with Gemini to extract scene details, then uses Veo or Sora backends to produce the remixed video output.

Can I remix a video using a specific image frame instead of text prompts?▼

Yes, you can remix a video using a specific image frame. The skill supports an Image remix mode that extracts frames from your input or accepts user-provided images to clone and remix videos with different looks and lighting.

Does the video remix workflow accept external video URLs for processing?▼

Yes, the video remix workflow accepts external video URLs for processing. It handles both local file uploads and external links, applying error handling and fallbacks during Gemini-based analysis and generation.

What is the best way to convert an existing video into a 9:16 social media format using AI?▼

The best way to convert an existing video into a 9:16 social media format is using AI video remixing. By analyzing your input clip, the skill generates stylistic variations and alternate aspect ratios without requiring manual video editing.

Do I need a Gemini API to analyze video scenes for prompt-to-video generation?▼

Yes, you need the Google GenAI dependency to analyze video scenes for prompt-to-video generation. The skill uses Gemini-based analysis to extract lighting, camera work, and scene details to build accurate generation prompts.

Related Skills

Explore More Design & Creative Skills→
secondskysecondsky
204

google-gemini-api

Integrate Google Gemini API via @google/genai SDK for text generation and function calling.

Community
Advanced
xg-gh-25xg-gh-25
36

video-gen

Generate short-form videos from structured prompts and storyboards.

Community
Advanced
maxgent-aimaxgent-ai

video-gen

Automates AI video generation with Veo and Sora models from text prompts.

Official
Intermediate
TheArchitectitTheArchitectit
3

video-frames

Extract and analyze video frames using ffmpeg, ffprobe, and Pillow.

Community
Intermediate