og Image Gen

    2

    Generate professional 1200x630 Open Graph social preview images instantly using Google Gemini.

    $12

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    og-image-gen

    Example session with this skill installed

    Generate a professional OG image with the title "Scaling Python APIs" and subtitle "Best practices for high-concurrency systems" using brand color #4f46e5.

    • Read your context and instructions
    • Compiled the og-image-gen

    Generating OG image...
    Title: Scaling Python APIs
    Subtitle: Best practices for high-concurrency systems
    Brand color: #4f46e5
    Model note: Generated a professional card with indigo gradient.
    SAVED: ./og-image.png (428 KB)
    Ready to upload to your assets folder!

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Professional Open Graph Images in Seconds

    Creating high-quality social sharing images is often a manual chore for developers. This skill automates the creation of 1200x630 Open Graph (OG) images using Google Gemini's advanced image generation capabilities. It transforms a simple title and subtitle into a professionally designed marketing asset ready for blog posts, documentation, or product launches.

    What it does

    The skill takes your text input and branding preferences to generate a custom PNG. It handles the prompt engineering required to produce clean, high-contrast layouts that are readable on mobile feeds and social timelines. It specifically targets the professional 'card' aesthetic, moving away from generic AI art toward functional UI/UX assets.

    Supported Tools & Frameworks

    • Engine: Powered by Google Gemini (Free Tier supported).
    • Environment: Requires a Bash-capable environment with Python 3.
    • Integration: Outputs a standard 1200x630 PNG file to your local directory.

    Why use this skill?

    Unlike manual prompting, this skill applies consistent design constraints—ensuring the correct aspect ratio, font legibility, and modern gradient backgrounds every time. It saves you from opening Figma or Photoshop just to create a simple link preview image.

    • AI-generated text in images can occasionally have spelling artifacts.
    • Requires an external GEMINI_API_KEY environment variable.
    • Limited to 2 images per minute on Gemini free tier.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 7 months ago

    Requires

    Python

    Permissions

    Terminal / Shell
    Environment Variables
    Listed7 months ago

    What's inside

    Frequently Asked Questions

    This skill automates the creation of 1200x630px social media preview images (Open Graph) using Google Gemini, eliminating the need for manual design work in tools like Figma or Photoshop.

    The skill requires a Bash-capable environment with Python 3 installed and an active Google Gemini API key (the free tier is fully supported).

    Upon purchase, you receive the full skill logic ready for deployment, including the automated prompt engineering framework that ensures consistent layout and legibility.

    This skill is designed for any platform or agent that supports Python-based executions and command-line interactions within a local or containerized environment.

    Yes, while the skill automates the design, you can provide specific text inputs like titles, subtitles, and branding colors to ensure the output matches your project's aesthetic.

    The skill is optimized to generate images in the industry-standard 1200x630 pixel resolution, ensuring they look perfect on X (Twitter), LinkedIn, and Facebook feeds.

    New in Image & Video