blog-image

Generates blog images via Gemini MCP using optimized six-component prompts.

Updated Apr 12, 2026
One-click install
npx skills add https://github.com/captaindevv/blogs --skill blog-image-captaindevv
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: blog-image
Source: https://github.com/captaindevv/blogs/tree/main/skills/blog-image
Command: npx skills add https://github.com/captaindevv/blogs --skill blog-image-captaindevv

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

Blog-image removes the friction of producing on-brand, publication-quality images for articles by converting a brief creative intent into optimized, model-ready prompts and orchestrating Gemini (via MCP) to produce or edit hero images, inline illustrations, OG/social cards, and dividers. It handles aspect ratios, model selection, safety rephrasing, and fallbacks so writers and editors don't need to learn image APIs or manual post-processing steps.

Core Features & Use Cases

  • 6-component prompt engineering: Builds Subject, Action, Context, Composition, Lighting, and Style as natural narrative prompts for consistent, high-quality outputs.
  • Generate & edit: Supports new image generation, targeted edits, multi-turn refinement, and delivery of alt text, frontmatter snippets, and paths for immediate use in blog pipelines.
  • Domain modes & sizing: Chooses Editorial, Product, Landscape, UI/Web, Infographic, or Abstract modes and sets blog-optimized aspect ratios and resolutions automatically.
  • Operational safety & fallbacks: Checks MCP availability, auto-rephrases on safety blocks, and falls back silently to stock photos for internal calls so publishing workflows continue.
  • Use case example: Create a 16:9 hero image for a travel feature, generate an OG social card, or edit a product shot to match brand lighting and crop for OG dimensions.

Quick Start

Use the blog-image skill to generate a hero image by saying: /blog image generate a wide editorial shot of a sunlit wooden desk with a laptop and coffee for a productivity blog.

Frequently Asked Questions about blog-image

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate blog images automatically from text descriptions?

You can generate blog-ready images by providing a creative intent; the Skill builds optimized six-component prompts covering Subject, Action, Context, Composition, Lighting, and Style, then orchestrates Gemini via the nanobanana-mcp bridge to produce the output.

What do I need to configure before generating images with Gemini via MCP?

Before generating images, you need a configured nanobanana-mcp with a Google AI API key, MCP tool support for set_aspect_ratio, gemini_generate_image, and gemini_edit_image, plus optional ImageMagick for post-processing outputs.

Can I edit existing product shots to match brand lighting and OG dimensions?

Yes, you can edit existing product shots by using the targeted image editing and multi-turn refinement capabilities, adjusting lighting and cropping to match specific brand requirements and social OG card dimensions automatically.

What is the best way to create optimized OG social cards for blog posts?

The best way to create optimized OG social cards is using the domain modes and sizing features, which automatically set blog-optimized aspect ratios and resolutions while generating targeted editorial imagery via Gemini.

What happens when an image generation request hits a safety block?

When an image generation request hits a safety block, the Skill auto-rephrases the prompt and falls back silently to stock photos for internal calls, ensuring publishing workflows and automated blog pipelines continue without interruption.