creatify-ai

creatify-ai / ad-creative-evaluator

Public

Claude agent skill: Score any video ad with an AI expert panel. 8-dimension rubric + 3 specialist personas.

17
0
100% credibility
Found Mar 05, 2026 at 17 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

A Claude AI skill that evaluates video advertisements using three AI expert personas across eight key dimensions, providing scores and improvement suggestions, along with a utility to extract representative frames from videos.

How It Works

1
📰 Discover the ad checker

You find a helpful tool that lets AI experts review your video ads like real pros would.

2
✅ Set it up quickly

You add this simple skill to your AI assistant so it's ready to use right away.

3
📹 Prepare your video

You pull out a few key snapshots from your ad video to show the important moments clearly.

4
⭐ Get expert reviews

Three smart reviewers—a marketer, creative lead, and everyday viewer—score your ad on what grabs attention, looks great, and makes people act.

5
📋 Review the feedback

You get a clear report with scores, strong points, weak spots, and easy ideas to make it better.

🚀 Create winning ads

Your ads now hook viewers faster, convert better, and stand out from the crowd.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 17 to 17 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is ad-creative-evaluator?

This Python-based Claude agent skill lets you score any video ad using three AI personas—a performance marketer, creative director, and target consumer—across an 8-dimension rubric covering hook, message, visuals, audience fit, pacing, CTA, emotion, and sound-off performance. It pulls key frames from videos via a simple CLI tool, then delivers structured reports with weighted scores, persona disagreements, strengths, weaknesses, and targeted fixes. Perfect for devs using claude agent builder or claude agent sdk to automate ad feedback in claude agent mode.

Why is it gaining traction?

The multi-persona claude agent team uncovers blind spots—like when marketers love a hook but consumers hate it—while weighted scoring prioritizes conversion killers like hooks and CTAs. It ties into claude agentic workflows, claude github integration, and companion tools for generating fixes, making it a quick win for claude agents github pipelines over generic evaluators. Devs dig the structured output for claude agent skills chaining.

Who should use this?

Growth marketers iterating video ads at scale, indie devs building claude agentic ad platforms, or agencies reverse-engineering competitors with claude github copilot extensions. Ideal for teams in claude agent team setups evaluating creatives before launch.

Verdict

Solid concept with clear docs and MIT license, but at 17 stars and 1.0% credibility score, it's early-stage—expect tweaks for production. Grab it if you're in AI ad eval; skip for battle-tested claude github plugin alternatives.

(178 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.