AI Visuals by SOLIDS FOR YOU

    1

    Art director for images and videos made with ChatGPT, Midjourney, Gemini, Flux, Sora, Veo and more: scores them for where they'll be used and hands back the exact fixed prompt.

    Free

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    About this skill

    AI Visuals makes Claude the art director for images and videos you made with ChatGPT, Midjourney, Gemini, Flux, Ideogram, Firefly, Canva, Sora, Veo, Kling or Runway. It reviews each result for where it will be used (an Amazon listing, an Instagram post, a LinkedIn banner, a YouTube thumbnail, an ad, a website) and scores it.

    Then it hands back the exact fixed prompt or edit for that generator, with every change explained, and a fix ladder for when a tool can't do something reliably (exact text, real logos, real products), so you stop re-rolling the same mistake. Bundled scripts compare prompts and total the scorecard. With your own OpenAI key it can also generate the image and check it again.

    It never fakes a real product: product photos stay real, and AI goes around them.

    Free, like every SOLIDS FOR YOU skill. The one skill we charge for is Reels Publisher for Instagram, which posts your finished Reels to your own account through the official API and reads back their numbers: https://agensi.io/skills/reels-publisher-for-instagram

    It doesn't generate images unless you set your own OPENAI_API_KEY (each call costs you money, and it asks first); for other tools you paste the prompt and share the result. Generator features change often, so it checks names and parameters against each tool's current docs. It never posts or uploads anything.

    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

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 22 days ago

    • Free with an Agensi account

    Requires

    Python 3

    Permissions

    Read Files
    Write Files

    Allowed Hosts

    api.openai.com (only when you ask it to generate)

    File Scopes

    a
    scratch
    folder
    for
    prompts
    and
    outputs

    generate_openai.py reads the key from OPENAI_API_KEY only, never from the chat, and calls the OpenAI Images API only when you agree to the cost.

    Listed22 days ago

    What's inside

    Frequently Asked Questions

    Art director for images and videos made with ChatGPT, Midjourney, Gemini, Flux, Sora, Veo and more: scores them for where they'll be used and hands back the exact fixed prompt.

    This skill uses the open SKILL.md standard. Use it through an MCP-compatible agent connected to Agensi, and check the compatibility information on this page for confirmed agents and required capabilities.

    Connect your AI agent to Agensi through MCP, then ask it to use AI Visuals by SOLIDS FOR YOU on your task. Your agent loads the latest approved version each time. Paid skills require a purchase or active subscription. Skill files are not available for download; your licence does not allow you to save, copy or export any part of a skill.

    New in Image & Video

    Free