content-engine

Compile raw visual assets into brand identity files and execute multi-model generation workflows.

3|2|Updated Mar 17, 2026
One-click install
npx skills add https://github.com/broomva/skills --skill content-engine-broomva
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: content-engine
Source: https://github.com/broomva/skills/tree/main/skills/video/content-engine
Command: npx skills add https://github.com/broomva/skills --skill content-engine-broomva

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill solves the fragmentation of AI content creation by unifying visual identity, character consistency, and multi-platform distribution into a single, automated pipeline.

Core Features & Use Cases

  • Visual DNA Compilation: Analyzes raw brand assets via Gemini to create persistent, reusable identity files.
  • Cinematic Generation: Orchestrates high-end video and image generation using Higgsfield, ComfyUI, and other specialized tools.
  • Automated Distribution: Compounds existing distribution skills to adapt and publish content across social platforms, blogs, and newsletters.
  • Use Case: A marketing team can compile their brand's visual DNA once, then use the engine to generate a 10-scene campaign with consistent character identity and automated captioning for Instagram, X, and LinkedIn.

Quick Start

Use the content engine to compile the brand identity from the raw assets in the knowledge directory.

Frequently Asked Questions about content-engine

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

FAQPage Schema
How do I automate brand identity compilation for multi-platform content creation?

Automate brand identity compilation by analyzing raw visual assets via Gemini multimodal analysis to generate persistent, reusable Visual DNA files for multi-platform content creation. This unifies visual identity and character consistency into a single automated pipeline.

What is the best way to maintain character consistency across AI video generation workflows?

Maintain character consistency across AI video generation workflows by compiling a structured brand identity file first, then orchestrating cinematic generation using Higgsfield and ComfyUI with persistent Visual DNA constraints applied to each scene.

Do I need Higgsfield CLI and ffmpeg to execute cinematic video production pipelines?

Yes, you need Higgsfield CLI and ffmpeg dependencies to execute end-to-end cinematic video production pipelines. Higgsfield orchestrates high-end generation while ffmpeg handles media processing for automated distribution across social and web platforms.

Can I use browser automation tools to distribute AI generated campaigns across social platforms?

Yes, you can use browser automation tools to distribute AI generated campaigns across social platforms. The pipeline compounds existing distribution skills to adapt and publish content automatically across Instagram, X, LinkedIn, blogs, and newsletters.

How does multimodal analysis work for creating reusable brand identity files?

Multimodal analysis works by feeding raw brand assets into Gemini to extract and structure visual traits into reusable brand identity files. This Visual DNA compilation ensures consistent storytelling and character identity across all subsequent AI generation workflows.

What are the limitations of automating multi-model generation workflows for social media content?

Limitations of automating multi-model generation workflows include dependency on external integrations like Higgsfield CLI, Gemini, and browser automation tools. Successful end-to-end campaign execution requires these environments to be properly configured and accessible.