ad-creative-evaluator

Extract video frames and generate structured multi-persona ad evaluation reports.

28|Updated Mar 2, 2026

Search Tags:#rubric #frame-extraction #video-ads #ad-evaluation #creative-feedback #persona-evaluation

Ready to run

npx skills add https://github.com/creatify-ai/ad-creative-evaluator --skill ad-creative-evaluator

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: ad-creative-evaluator
Source: https://github.com/creatify-ai/ad-creative-evaluator/tree/main
Command: npx skills add https://github.com/creatify-ai/ad-creative-evaluator --skill ad-creative-evaluator

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires opencv-python, Pillow.

What problem does it solve?

The AI-driven evaluation workflow provides structured, actionable feedback on video ads by aligning three expert personas to deliver consistent, multi-angled insights.

Core Features & Use Cases

Frame extraction from videos to enable visual analysis
Independent persona scoring (Performance Marketer, Creative Director, Target Consumer)
Synthesis into a structured evaluation report with strengths, weaknesses, and improvement recommendations
Standardized output template for downstream decision-making and optimization

Quick Start

Provide a video file or URL to start the evaluation, and the system will extract frames, run the three personas, and return a structured report.

Frequently Asked Questions about ad-creative-evaluator

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

FAQPage Schema

How do I evaluate video ads using AI to get actionable creative feedback?▼

You can evaluate video ads by providing a video file or URL. The system extracts key frames and runs them through an AI expert panel to generate a structured report with scores and actionable recommendations.

What is the best way to get multi-perspective feedback on video ad performance?▼

The best way is to use a persona-based evaluation approach. The system scores videos across eight dimensions using three distinct personas: Performance Marketer, Creative Director, and Target Consumer, ensuring multi-perspective feedback.

Does video ad evaluation work with any video format and require specific dependencies?▼

The evaluation requires video input via a file or URL and uses OpenCV and Pillow dependencies for frame extraction. It applies to video ads across various platforms and formats to generate structured feedback.

How to extract frames from a video ad for creative analysis and scoring?▼

Frame extraction is handled automatically via a Python script using OpenCV and Pillow. You simply provide the video file or URL, and the system extracts frames to enable visual analysis for the subsequent persona evaluations.

What dimensions are scored when evaluating video ad creatives?▼

Video ad creatives are scored across eight dimensions by three expert personas. This standardized process produces a structured output template detailing strengths, weaknesses, and specific improvement recommendations for downstream optimization.

Can I use this ad evaluation workflow for optimizing ads across different social platforms?▼

Yes, the workflow applies to video ads across platforms and formats. By synthesizing feedback from performance, creative, and consumer perspectives, it outputs a standardized template to guide downstream decision-making and optimization.