content-engine-dna

Compile raw visual assets into structured identity files with multimodal analysis.

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

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This skill solves the problem of visual identity drift in AI-generated content by compiling raw brand assets into structured, persistent identity files that ensure consistency across all downstream generation tools.

Core Features & Use Cases

  • Multimodal DNA Extraction: Uses Gemini to analyze color palettes, lighting, composition, and texture from raw assets.
  • Tool-Specific Prompting: Automatically generates optimized prompt fragments for Nano Banana Pro, Soul Cinema, Weavy, and ComfyUI.
  • Provenance Tracking: Maintains a strict link between raw source files and compiled identity files to ensure integrity and allow for automated linting.
  • Use Case: A creative team can drop a new mood board into the raw folder, run the compiler, and immediately have updated, consistent prompt fragments ready for their entire suite of generation tools.

Quick Start

Run the content-engine compile command to analyze all raw assets and generate the structured identity files.

Frequently Asked Questions about content-engine-dna

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

FAQPage Schema
How do I maintain visual identity consistency across AI-generated content?

Brand DNA files are structured identity files compiled from raw visual assets. They use multimodal analysis to lock visual parameters like color, lighting, and composition, ensuring provenance and brand consistency across multiple AI generation pipelines.

Does Gemini multimodal analysis work for extracting color palettes and lighting from raw assets?

Yes, Gemini multimodal analysis extracts color palettes, lighting, composition, and texture from raw assets. It translates these visual elements into structured parameters to enforce brand and character consistency in downstream generation tools.

How do I generate optimized prompt fragments for ComfyUI and Nano Banana Pro?

You generate optimized prompt fragments by running a compile command on raw assets. The compiler automatically extracts visual parameters and creates tool-specific prompting fragments tailored for platforms like ComfyUI, Nano Banana Pro, Soul Cinema, and Weavy.

Can I use ffmpeg to validate provenance and consistency in a content engine?

Yes, ffmpeg is required to support the content engine pipeline. It helps validate provenance and consistency through a multi-step pipeline including linting and cross-referencing raw source files with compiled identity files.

What are the limitations of style-locking for AI-generated content pipelines?

Style-locking limitations depend on the raw assets provided and the multimodal analysis depth. If source files lack distinct visual parameters or fail automated linting, the compiled identity files may not effectively prevent visual identity drift in downstream tools.