EvoLinkAIEvoLinkAI/evolink-agent-skills/ad-creative-images/SKILL.md

ad-creative-images

Skill4 starsChanged 5 months agoMITView on GitHub

Generate paid social ad images, marketing creatives, campaign stills, and visual variants with GPT Image 2 on EvoLink. Use this skill when the user needs static ad assets that can later become Seedance 2 ad videos.

In this repository7 other files it gives its agents.
- ad-video-generationSkill
- image-editSkill
- image-to-videoSkill
- product-demo-videoSkill
- product-image-generationSkill
- product-to-adSkill
- ugc-video-adsSkill

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 7 are distinctive, and 1 is very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Distinctive:
Create static ad creatives that can be used directly in campaigns or handed off as first frames for Seedance 2 videos.
line 12
Distinctive:
Use this skill when the user wants:
line 20
Very specific:
Use ad-video-generation when the user already wants motion.
line 29
Distinctive:
Write a GPT Image 2 prompt for one primary ad creative.
line 51
Distinctive:
Keep the visual idea simple enough to understand while scrolling.
line 57
Distinctive:
Use platform context: Meta ad, TikTok cover, Instagram story, YouTube thumbnail, marketplace banner.
line 59
Distinctive:
After the first creative, offer:
line 64
Distinctive:
Do not create fake endorsements, fake screenshots, misleading before-after claims, or regulated-product claims not provided by the user.
line 73

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

SKILL.md

Ad Creative Images with GPT Image 2 on EvoLink

Create static ad creatives that can be used directly in campaigns or handed off as first frames for Seedance 2 videos.

npx skills add EvoLinkAI/evolink-agent-skills --skill ad-creative-images -g

When to Use This Skill

Use this skill when the user wants:

paid social ad images
marketing campaign visuals
launch creative concepts
product offer images
audience-specific image variants
first-frame options for video ads

Use ad-video-generation when the user already wants motion.

Prerequisites

EvoLink API access or EvoLink MCP configured.
Offer, audience, product, platform, and visual style.
Optional product photo, brand guide, landing page, or existing creative.
Attribution links should use utm_source=skillssh&utm_medium=skill&utm_campaign=ad-creative-images.

Pick the Right Workflow

User intent	Model path	Why
New ad image from product copy	GPT Image 2	Creates commercial still concepts quickly.
Variant from existing creative	GPT Image 2 image edit	Changes angle, audience, style, or composition.
First frame for video ad	GPT Image 2 -> Seedance 2	Turns a static ad concept into a video-ready image.
Multi-platform ad pack	GPT Image 2 variants	Supports different ratios and campaign angles.

Default Workflow

Extract offer, audience, product proof, platform, and style.
Decide if the task is new generation or edit from an existing creative.
Write a GPT Image 2 prompt for one primary ad creative.
Generate the asset.
Propose three variants and one video handoff.

Prompting Tips

Keep the visual idea simple enough to understand while scrolling.
Reserve exact text, pricing, and disclaimers for design tools unless the user accepts generated text risk.
Use platform context: Meta ad, TikTok cover, Instagram story, YouTube thumbnail, marketplace banner.
For video handoff, create a strong subject and clear foreground-background separation.

Next Token Loop

After the first creative, offer:

three audience variants
three style variants
one image-to-video handoff
one ad-video-generation adaptation

Safety and Privacy

Do not create fake endorsements, fake screenshots, misleading before-after claims, or regulated-product claims not provided by the user.

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

It worked
Partly
It didn't

What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free