create-end-card-from-reference

Generate on-brand end-cards from a reference image and product PNGs.

6|1|Updated May 29, 2026
One-click install
npx skills add https://github.com/gooseworks-ai/gooseworks-ads-skills --skill create-end-card-from-reference
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: create-end-card-from-reference
Source: https://github.com/gooseworks-ai/gooseworks-ads-skills/tree/main/skills/atoms/end-cards/create-end-card-from-reference
Command: npx skills add https://github.com/gooseworks-ai/gooseworks-ads-skills --skill create-end-card-from-reference

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires higgsfield, playwright, ffmpeg, yt-dlp, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill allows the generation of visually compelling end-cards that closely match a given reference image, with emphasis on typography and product imagery, tailored for lifestyle and Pinterest-coded brands.

Core Features & Use Cases

  • Generative Imagery: Utilizes Nano Banana 2 to create product flat-lays on a gradient background, while HTML hyperframes overlay typography.
  • Reference-Based Design: Aligns the end-card visually with a provided reference image, ensuring a consistent aesthetic.
  • Customization: Offers flexibility in typography, label styles, background gradients, and layout patterns.
  • Use Case: Ideal for brands aiming to create on-brand end-cards for social media ads or product showcases that leverage a unique visual grammar.

Quick Start

To generate an end-card, provide product PNGs, a reference image, brand wordmark, headline, and relevant labels.

Frequently Asked Questions about create-end-card-from-reference

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

FAQPage Schema
How do I create an end-card from a reference image for social media ads?

To create an end-card from a reference image, you provide product PNGs, brand wordmarks, and typography details. The Skill aligns the generated end-card visually with your reference, ensuring a consistent aesthetic for social media ads.

Can I generate product flat-lays and typography overlays for Pinterest-style ad design?

Yes, you can generate product flat-lays and typography overlays for Pinterest-style ad design. The process utilizes generative AI for imagery on gradient backgrounds and HTML hyperframes to overlay typography.

What do I need to generate a high-quality end-card with AI-assisted design?

You need reference images, product SKUs or PNGs, typography details, brand wordmarks, and background specifications. These inputs allow the system to coordinate AI-generated imagery with HTML-based typography overlays.

Does this end-card generation approach work with specific dependencies like ffmpeg and playwright?

The end-card generation process works with dependencies like ffmpeg, playwright, yt-dlp, and higgsfield. These tools coordinate the AI design generation, HTML typography rendering, and media processing.

What is the best way to match my brand's visual grammar when creating end-cards?

The best way to match your brand's visual grammar is by using a reference-based design approach. This ensures the generated end-card closely matches the provided reference image, maintaining a consistent brand aesthetic.

Why does the end-card require both AI-generated imagery and HTML typography overlays?

The end-card requires AI-generated imagery and HTML typography overlays to combine high-quality visual generation with precise text formatting. This ensures product flat-lays and brand typography align perfectly for lifestyle brands.