Skip to content
Get packs

Guide · Agent skill

How to use the Marketing Image Creation agent skill

Updated · written with AI from the project's own documentation and checked against our catalogue data

The Marketing Image Creation skill (skill name: image) is a set of instructions that makes an AI agent act as a visual content producer for marketing. Once it is installed, you can ask for blog heroes, social graphics, product mockups, profile banners or OG images, and the agent will work out goals, dimensions and a suitable tool before producing anything. This guide explains what the skill does, how to install it, how to trigger it and where to be careful.

Marketing Image Creationcoreyhaines31/marketingskills · MIT

Quick start

  1. 1Download the ZIP. Download the image skill ZIP from this directory's skill page.
  2. 2Unzip into a skills folder. Unzip it into ~/.claude/skills/ for personal use, or into a project's .claude/skills/ folder.
  3. 3Or upload it in the Claude apps. Go to Settings → Capabilities → Skills and upload the ZIP.
  4. 4Get keys for your image tool. Create an API key or account for the image tool you plan to use, such as Gemini, Flux, Ideogram or OpenAI.
  5. 5Describe the image you need. Ask in plain language, stating the purpose, platform and dimensions.
  6. 6Answer the agent's questions. Provide brand assets and style preferences when asked, or add .agents/product-marketing.md.
  7. 7Review and optimize. Check the output for errors and rights issues, then ask for compression or WebP conversion.

What an agent skill is and what this one does

An agent skill is a folder of instructions that an AI agent loads when a request matches the skill's description. This one is the image skill from the coreyhaines31/marketingskills collection, and it is licensed under MIT.

When you ask for a marketing visual, the agent first checks for a product marketing context file at .agents/product-marketing.md if one exists, then asks about the image goal, platform, dimensions and brand assets. It then recommends an approach: AI generation, AI editing, a design tool such as Canva or Figma, a screenshot with an overlay, or stock photography.

  • Covers blog and article hero images, social graphics, product mockups, profile banners, listing visuals and brand assets
  • Compares image models such as Gemini (Nano Banana), Flux, Ideogram, GPT Image, Midjourney, Recraft and Stable Diffusion
  • Provides a prompting formula: Subject + Setting + Style + Lighting + Composition + Technical
  • Gives image optimization advice, such as WebP compression

Install the image skill in Claude

You can install the skill in one of three places. Download the ZIP file from the skill's page on this directory, then choose one of the options below.

For a personal install that works in every project, unzip the download into ~/.claude/skills/. For a single project, unzip it into that project's .claude/skills/ folder. In the Claude apps, you can instead upload the ZIP under Settings → Capabilities → Skills.

  • Personal: unzip into ~/.claude/skills/
  • Single project: unzip into the project's .claude/skills/ folder
  • Claude apps: Settings → Capabilities → Skills, then upload the ZIP
~/.claude/skills/

How to trigger the skill with natural requests

You do not need a special command. Describe the image you need in plain language and mention the purpose. The skill's description lists many trigger phrases, so requests that use them are the most likely to activate it.

Useful details to include are the placement, the platform and the size. If you leave these out, the agent will ask for them.

  • "Create a blog hero image for my post about remote onboarding, 1200x630."
  • "Make a social graphic announcing our new feature for LinkedIn."
  • "I need an OG image for my pricing page."
  • "Generate a product mockup of our dashboard on a laptop."
  • "Compress these images and convert them to WebP."

Example workflow: from request to finished asset

Suppose you ask for a blog hero. The agent will ask about the post topic, the target dimensions and whether you have brand colours or a logo. It will then suggest an approach, for example AI generation with Ideogram if the image needs a short headline, or Gemini for editing an existing photo.

The skill's prompting guide suggests a structure like this for a blog hero of a SaaS product. Adjust the subject and style to your brand.

  • Keep text in the image short; the skill advises using overlays for anything beyond short headlines
  • Always state the aspect ratio or pixel size in the prompt
A clean workspace with a laptop displaying a colorful analytics dashboard, minimalist desk with a coffee cup and notebook, bright natural window lighting from the right, shallow depth of field, commercial photography style, 1200x630, high resolution

What you need before you start

The skill itself does not include a tool. You need an API key or account for any image tool you choose. The source names Gemini, Replicate/Flux, Ideogram, OpenAI and Canva as examples. Some tools charge per image, and the skill notes that model pricing and terms change often, so check each provider's pricing page before you commit.

An optional product marketing context file at .agents/product-marketing.md lets the agent reuse your positioning and brand details instead of asking again.

  • An API key or account for at least one image tool, if you use AI generation
  • Optional: .agents/product-marketing.md
  • Network access, since the skill uses the network

Safety notes: scripts and network use

According to the skill's listing, it does not run scripts. It does use the network, because the chosen image tools are online services. Any images you send to a tool leave your machine and go to that provider, so avoid uploading confidential or unreleased material unless you have checked that tool's terms.

AI outputs need human review. The skill says the image skill is not suited to final brand-critical or legal-sensitive imagery. Check every visual for accuracy, rights and brand fit before publishing.

  • No scripts are run by this skill
  • Network use is required for the image services you choose
  • Review all AI output for errors, including invented UI in product mockups

Tips for better results

Match the tool to the job. Use an AI generator for unique hero images, and a design tool such as Canva or Figma when you need a repeatable template or exact brand rules. The skill's comparison table is a useful starting point.

For web use, the skill recommends optimizing images for performance, and gives WebP compression as an example. Ask the agent to compress or convert your final files.

  • Name the model you prefer, or ask for a comparison first
  • Use the prompting formula and specify style, lighting and aspect ratio
  • For product screenshots, use real screenshots with an overlay rather than AI-generated UI
  • For paid ads, use the separate ad-creative skill; for video, use the video skill

What people use it for

  • Blog hero images at the top of articles
  • Social media graphics for launch announcements
  • OG images for web pages shared on social platforms
  • Product mockups using real screenshots with overlays
  • Profile banners and cover photos for social accounts
  • Listing visuals for directories

Frequently asked questions

How do I install the image agent skill?

Download the ZIP from this directory's skill page and unzip it into ~/.claude/skills/ for personal use, or into a project's .claude/skills/ folder. In the Claude apps you can also upload the ZIP under Settings → Capabilities → Skills.

What do I need to use this skill?

You need an API key or account for any image tool you choose, such as Gemini, Replicate/Flux, Ideogram, OpenAI or Canva. An optional product marketing context file at .agents/product-marketing.md helps the agent skip repeat questions.

Is the Marketing Image Creation skill free?

The skill is licensed under MIT. The image tools it recommends are separate services, and many charge per image or by subscription, so check each provider's pricing page.

Does the skill run scripts or use the internet?

According to the listing, it runs no scripts and does use the network, because the image tools it recommends are online services. Avoid sending confidential images unless you have checked the provider's terms.

Can it create paid ad images?

No. The skill says paid ad creative and platform-specific ad specs belong to a separate ad-creative skill. Video production belongs to a separate video skill.

Which image model should I use?

It depends on the job. The skill suggests Ideogram 3.0 for text-heavy graphics, Gemini for editing and multi-image reference, Flux for consistency across many images, and Recraft V3 for vector-style brand assets. Ask the agent for a comparison based on your task.

New agent skills, repos and AI tools — every week

The best new skills and open-source projects, the fastest-growing repos, and one free prompt. Five minutes to read. Unsubscribe anytime.

Our verdict

This skill suits marketers, small teams and founders who need blog, social, listing and OG visuals quickly and want help choosing between AI generators and design tools. It is not the right choice for paid ad creative, video, or final brand-critical or legal-sensitive images, which need human review and specialist tools.

Download the skill