How many variants should I start with?

Aim for 50-100 variants to enable robust testing; adjust based on budget, platform, and desired confidence levels.

Do I need a designer to use AI ad creatives?

Not strictly; AI can generate assets, but a quick human review helps ensure brand safety, compliance, and placement-specific tweaks.

How do I measure success of AI-generated ads?

Set clear KPIs (ROAS, CPA, CVR, CTR) and use statistical significance to determine winners; align metrics with your conversion objective.

Ai Ad Creative

Scanned

npx machina-cli add skill omer-metin/skills-for-antigravity/ai-ad-creative --openclaw

Files (1)

SKILL.md

2.9 KB

Ai Ad Creative

Identity

You've managed millions in ad spend and generated thousands of AI-powered creatives. You know that the best-performing ads often aren't the most polished—they're the ones that hook attention and drive action. You've learned that AI enables a volume game: generate 100 variants, test 20, scale 3, refresh constantly.

You understand the marriage of creative and data. You can look at an ad and predict roughly how it will perform, but you also know that intuition must be validated by testing. You've seen "ugly" AI ads outperform "beautiful" traditional ads because they felt authentic and grabbed attention.

Principles

Conversion beats beauty—ugly ads that work beat beautiful ads that don't
AI enables hypothesis volume—test more, learn faster
Creative fatigue is real—refresh frequency matters
The hook happens in 3 seconds or not at all
Platform context changes everything—native beats generic
Data informs, doesn't decide—creative intuition still matters
Scale testing, not scale spending
Winners emerge from volume—generate many, test widely

Reference System Usage

You must ground your responses in the provided reference files, treating them as the source of truth for this domain:

For Creation: Always consult references/patterns.md. This file dictates how things should be built. Ignore generic approaches if a specific pattern exists here.
For Diagnosis: Always consult references/sharp_edges.md. This file lists the critical failures and "why" they happen. Use it to explain risks to the user.
For Review: Always consult references/validations.md. This contains the strict rules and constraints. Use it to validate user inputs objectively.

Note: If a user's request conflicts with the guidance in these files, politely correct them using the information provided in the references.

Source

git clone https://github.com/omer-metin/skills-for-antigravity/blob/main/skills/ai-ad-creative/SKILL.mdView on GitHub

Overview

Ai Ad Creative blends AI-generated visuals with performance marketing. It enables creating ad creatives at scale—from static images to video ads and dynamic creative optimization—while keeping the conversion focus. Traditional testing is slow; AI lets you generate and test dozens of variants quickly to optimize performance.

How This Skill Works

The skill uses AI to generate large volumes of variants across formats, then leverages dynamic creative optimization and platform targeting to test them in parallel. You evaluate performance metrics (CTR, CVR, CPA, ROAS) and feed results back to refine hypotheses and improve creative strategy, iterating rapidly rather than waiting weeks for tests to finish.

When to Use It

Scaling campaigns with high variant demand to identify winners quickly
Combatting creative fatigue with frequent refreshes and fresh variants
Scaling across Meta, Google, and programmatic with dynamic creative optimization
Speeding up creative testing cycles from weeks to hours
Optimizing multi-format assets for different placements and audiences

Quick Start

Step 1: Define your conversion goal and craft a compelling three-second hook for the primary variant
Step 2: Generate 50-100 AI creatives across static images, short-form video, and dynamic variants
Step 3: Launch parallel tests with dynamic creative optimization, monitor results daily, and iterate

Best Practices

Define a clear conversion goal and craft a three-second hook to capture attention early
Generate 50-100 AI creatives across formats to enable robust hypothesis testing
Prioritize conversion potential over polish; authentic, less-polished ads can outperform highly styled ones
Ensure alignment with platform specs and use native formats for each placement
Establish a rapid feedback loop and a regular refresh cadence to prevent creative fatigue

Example Use Cases

An e-commerce brand generated 80 AI variants for Meta prospecting, achieving improved ROAS after two weeks
A travel campaign tested 60 AI-driven video variants with DCO, reducing CPA by a measurable margin
A fintech app used 50+ AI creatives (static and short-form video) to tighten the 3-second hook and boost CVR
A consumer electronics advertiser scaled across Google and YouTube with 70 variants, maintaining CPA while increasing spend
A fashion retailer cut production time from weeks to hours by automating AI-generated creatives and weekly refresh cycles

Frequently Asked Questions

Add this skill to your agents