Seo Image Gen
Generate production-ready OG, hero, product, and infographic images tuned for SEO and social sharing without leaving your agent workflow.
Overview
seo-image-gen is an agent skill most often used in Launch (also Grow, Validate) that generates SEO-oriented images—OG previews, heroes, product shots, and infographics—via Gemini through nanobanana-mcp and the banana pip
Install
npx skills add https://github.com/agricidaniel/claude-seo --skill seo-image-genWhat is this skill?
- Six command modes: og, hero, product, infographic, custom, and batch generation via `/seo image-gen`.
- Routes SEO use cases through the banana Creative Director pipeline on Gemini via nanobanana-mcp with tuned aspect ratios
- Covers OG and social previews, blog heroes, schema and favicon assets, product photography, infographics, banners, thumb
- Interactive SKILL.md drives generation; a separate audit-only agent assesses existing OG/social images during `/seo audi
- Requires the banana extension and nanobanana MCP server (Claude Banana compatibility).
- Six generation modes: og, hero, product, infographic, custom, and batch.
- Skill metadata version 1.9.9; requires nanobanana MCP and the banana extension.
- Separate audit-only agent path for OG/social image assessment during `/seo audit`.
Adoption & trust: 1.6k installs on skills.sh; 8.5k GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
You are ready to ship or promote a page but lack on-brand OG, hero, product, or schema images sized correctly for search and social.
Who is it for?
Solo builders on Claude Code who already run the banana extension and nanobanana MCP and need fast, SEO-labeled visuals for launches, blog posts, and product pages.
Skip if: Teams that cannot install MCP servers or the banana extension, need print-grade design without SEO defaults, or only want a passive image audit without generation.
When should I use this skill?
User says generate image, OG image, social preview, hero image, blog image, product photo, infographic, seo image, favicon, schema image, pinterest pin, banner, thumbnail, image-gen, create visual, or generate visual.
What do I get? / Deliverables
After running the skill, you get production-ready image assets mapped to SEO modes and aspect ratios, ready to attach to pages, metadata, and distribution channels.
- OG and social preview images with SEO-oriented aspect ratios
- Blog hero, product, infographic, banner, and thumbnail assets
- Schema, favicon, and Pinterest-oriented visuals from batch or custom runs
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Canonical shelf is Launch because the skill maps SEO and social preview assets (OG, schema, favicon, Pinterest) that matter when pages are meant to rank and get clicked from search and shares. Subphase seo matches the skill’s explicit SEO asset types, Gemini SEO-oriented modes, and triggers like OG image, schema image, and hero image for publishable URLs.
Where it fits
Generate a hero and OG pair for a waitlist landing page before you run traffic tests.
Produce schema and favicon-sized assets plus a Pinterest pin for a new product URL going live.
Create consistent social preview banners and thumbnails for launch posts across channels.
Batch blog hero images and infographics for an editorial calendar without leaving the agent.
How it compares
Use this SEO-tuned generator skill with Gemini MCP instead of ad-hoc image prompts or a generic creative tool with no OG, schema, or batch presets.
Common Questions / FAQ
Who is seo-image-gen for?
It is for solo and indie builders using Claude Code who ship websites, blogs, or storefronts and need OG, hero, product, infographic, and related SEO visuals without a separate design stack.
When should I use seo-image-gen?
Use it at launch when setting OG and schema images for new URLs, during grow when creating blog heroes and social previews, and at validate when a landing page needs credible product or hero imagery before you drive traffic.
Is seo-image-gen safe to install?
Review the Security Audits panel on this Prism page and your MCP trust posture before enabling network access to Gemini via nanobanana; do not assume pass/fail counts from this listing alone.
SKILL.md
READMESKILL.md - Seo Image Gen
# SEO Image Gen: AI Image Generation for SEO Assets (Extension) Generate production-ready images for SEO use cases using Gemini's image generation via the banana Creative Director pipeline. Maps SEO needs to optimized domain modes, aspect ratios, and resolution defaults. ## Architecture Note This extension is built on [Claude Banana](https://github.com/AgriciDaniel/banana-claude), the standalone AI image generation skill for Claude Code. This skill has two components with distinct roles: - **SKILL.md** (this file): Handles interactive `/seo image-gen` commands for generating images - **Agent** (`agents/seo-image-gen.md`): Audit-only analyst spawned during `/seo audit` to assess existing OG/social images and produce a generation plan (never auto-generates) ## Prerequisites This skill requires the banana extension to be installed: ```bash ./extensions/banana/install.sh ``` **Check availability:** Before using any image generation tool, verify the MCP server is connected by checking if `gemini_generate_image` or `set_aspect_ratio` tools are available. If tools are not available, inform the user the extension is not installed and provide install instructions. ## Quick Reference | Command | What it does | |---------|-------------| | `/seo image-gen og <description>` | Generate OG/social preview image (1200x630 feel) | | `/seo image-gen hero <description>` | Blog hero image (widescreen, dramatic) | | `/seo image-gen product <description>` | Product photography (clean, white BG) | | `/seo image-gen infographic <description>` | Infographic visual (vertical, data-heavy) | | `/seo image-gen custom <description>` | Custom image with full Creative Director pipeline | | `/seo image-gen batch <description> [N]` | Generate N variations (default: 3) | ## SEO Image Use Cases Each use case maps to pre-configured banana parameters: | Use Case | Aspect Ratio | Resolution | Domain Mode | Notes | |----------|-------------|------------|-------------|-------| | **OG/Social Preview** | `16:9` | `1K` | Product or UI/Web | Clean, professional, text-friendly | | **Blog Hero** | `16:9` | `2K` | Cinema or Editorial | Dramatic, atmospheric, editorial quality | | **Schema Image** | `4:3` | `1K` | Product | Clean, descriptive, schema ImageObject | | **Social Square** | `1:1` | `1K` | UI/Web | Platform-optimized square | | **Product Photo** | `4:3` | `2K` | Product | White background, studio lighting | | **Infographic** | `2:3` | `4K` | Infographic | Data-heavy, vertical layout | | **Favicon/Icon** | `1:1` | `512` | Logo | Minimal, scalable, recognizable | | **Pinterest Pin** | `2:3` | `2K` | Editorial | Tall vertical card | ## Generation Pipeline For every generation request: 1. **Identify use case** from command or context (og, hero, product, etc.) 2. **Apply SEO defaults** from the use cases table above 3. **Set aspect ratio** via `set_aspect_ratio` MCP tool 4. **Construct Reasoning Brief** using the banana Creative Director pipeline: - Load `references/prompt-engineering.md` for the 6-component system - Apply domain mode emphasis (Subject 30%, Style 25%, Context 15%, etc.) - Be SPECIFIC and VISCERAL: describe what the camera sees 5. **Generate** via `gemini_generate_image` MCP tool 6