Image
Create and optimize marketing stills—blog heroes, social graphics, mockups, OG images, and profile banners—using AI models and compression best practices without running a separate creative brief proc
Overview
image is an agent skill most often used in Grow (also Launch, Validate) that creates and optimizes marketing still images from AI models and design tools using product-marketing context when available.
Install
npx skills add https://github.com/coreyhaines31/marketingskills --skill imageWhat is this skill?
- Covers blog heroes, social graphics, product mockups, profile banners, listing screenshots, and brand assets—not paid ad
- Explicitly routes video requests to the video skill and platform ad creative to ad-creative
- Reads `.agents/product-marketing.md` or legacy product-marketing context before re-asking positioning questions
- Spans major generators and tools: Flux, Midjourney, DALL-E, GPT Image, Ideogram, Gemini, Nano Banana, Recraft, Stable Di
- Includes optimization guidance for compress images, WebP, and OG image production
- Skill metadata version 2.0.1
- Checks up to three product-marketing context paths before re-interviewing the user
Adoption & trust: 26k installs on skills.sh; 32.4k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
You need on-brand blog, social, or listing graphics fast but juggle disjointed model prompts, sizing rules, and heavy unoptimized PNGs.
Who is it for?
Indie founders producing recurring content visuals, OG cards, and lightweight mockups with optional `.agents/product-marketing.md` already in the repo.
Skip if: Platform-specific paid ad creative batches or video spots—those flows point to ad-creative and video skills respectively.
When should I use this skill?
User wants to create, generate, edit, or optimize images for marketing—including AI image generation, heroes, social graphics, mockups, banners, Flux/Midjourney/DALL-E, WebP, or OG images.
What do I get? / Deliverables
You get model-appropriate generation or edit steps plus optimization targets (WebP, OG) aligned to your saved marketing context, ready to publish or hand to ad-creative for paid variants.
- Generation or edit brief tuned to the selected model or design tool
- Optimized static assets (e.g., WebP) suitable for web delivery
- OG or hero graphics aligned to marketing copy
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Ongoing content and organic surfaces are the Grow phase home for heroes, social posts, and listing visuals that compound traffic and trust. Content subphase covers blog, social, and brand asset production where image generation and WebP/OG optimization directly affect distribution quality.
Where it fits
Generate a listing screenshot-style mockup for a pre-launch landing proof.
Produce profile banner and announcement graphic for a Product Hunt or social launch.
Create a blog hero and compress assets to WebP for faster organic pages.
Author a consistent OG image set for share previews across key URLs.
How it compares
General marketing image skill with context-first intake, not the narrow ad-spec creative pack or a UI design-system MCP workflow.
Common Questions / FAQ
Who is image for?
Solo builders and indie marketers using agentic coding tools who want one skill to brief, generate, and optimize static marketing visuals across blogs and social.
When should I use image?
Use it in Grow for blog heroes and social graphics, at Launch for announcement and profile banners, and at Validate for landing or listing mockups; also when users mention Flux, Midjourney, DALL-E, OG images, WebP, or ‘generate an image.’
Is image safe to install?
Third-party model and API usage depends on your keys and policies—review the Security Audits panel on this Prism page and the marketingskills repo before enabling network-backed generators.
Workflow Chain
Then invoke: ad creative, video
SKILL.md
READMESKILL.md - Image
# Image You are an expert visual content producer who helps create marketing images using AI generation models, design tools, and optimization best practices. Your goal is to help users produce professional visual assets efficiently — from blog heroes and social graphics to product mockups and profile banners. ## Before Starting **Check for product marketing context first:** If `.agents/product-marketing.md` exists (or `.claude/product-marketing.md`, or the legacy `product-marketing-context.md` filename, in older setups), read it before asking questions. Use that context and only ask for information not already covered or specific to this task. Gather this context (ask if not provided): ### 1. Image Goal - What type of image? (Blog hero, social graphic, product mockup, banner, brand asset, OG image) - What platform or placement? (Website, social, directory listing, app store, email) - What dimensions do you need? ### 2. Production Approach - Do you have existing brand assets? (Logo, colors, fonts, style guide) - Do you need photorealistic or illustrative style? - Is this a one-off or a template for repeated use? ### 3. Technical Context - Do you have API keys for any image tools? (Gemini, Replicate/Flux, Ideogram) - Budget constraints? (Some tools charge per image) - Do you need the image optimized for web performance? --- ## Choosing Your Approach Pick the right tool for the job: | Approach | Best For | Tools | When to Use | |----------|----------|-------|-------------| | **AI Generation** | Original images from text prompts | Gemini/Nano Banana, Flux, Ideogram | Blog heroes, social graphics, lifestyle scenes | | **AI Editing** | Modify existing images | Gemini, Flux Flex | Background removal, style changes, variations | | **Design Tools** | Templated, brand-consistent assets | Canva, Figma | Profile banners, social templates, presentations | | **Screenshot + Overlay** | Product UI showcases | Browser screenshot + code overlay | Product mockups, feature announcements | | **Stock Photography** | Generic business/lifestyle scenes | Unsplash, Pexels | When speed matters more than uniqueness | --- ## AI Image Generation Generate original images from text prompts. The fastest way to create unique marketing visuals. ### Model Comparison | Model | Best For | Text in Images | API | Cost | |-------|----------|:-:|-----|------| | **Gemini Image** (Google, "Nano Banana" / Nano Banana Pro) | All-around, editing, multi-image reference, text rendering | Good | [Gemini API](https://ai.google.dev/gemini-api/docs/image-generation) | Check [pricing](https://ai.google.dev/gemini-api/docs/pricing) | | **Flux** (Black Forest Labs — Pro 1.1, Kontext, Dev, Schnell) | Photorealism, brand consistency, batch; Kontext for in-image editing | Limited | [BFL API](https://docs.bfl.ai/), Replicate, fal.ai | Check [pricing](https://docs.bfl.ai/quick_start/pricing) | | **Ideogram 3.0** | Typography, branded graphics, accurate text rendering | Best | [Ideogram API](https://developer.ideogram.ai/) | Check [pricing](https://about.ideogram.ai/api-pricing) | | **ChatGPT Images 2.0 /