blog-image

Generate and edit blog images via Gemini MCP with structured prompts.

8|5|Updated Feb 18, 2026
One-click install
npx skills add https://github.com/shenxingy/Clade --skill blog-image-shenxingy
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: blog-image
Source: https://github.com/shenxingy/Clade/tree/main/configs/skills/blog-image
Command: npx skills add https://github.com/shenxingy/Clade --skill blog-image-shenxingy

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Creates and refines blog images (hero, inline illustrations, OG/social cards) without forcing you to manually write complex prompts or manage image-generation details.

Core Features & Use Cases

  • AI image generation & editing: Generates new blog images and edits existing ones with blog-optimized instructions.
  • Prompt engineering with 6-component brief: Converts your intent into a structured Subject/Action/Context/Composition/Lighting/Style prompt for more reliable results.
  • Blog domain modes: Supports domain-focused styles such as Editorial, Product, Landscape, UI/Web, Infographic, and Abstract.
  • MCP-based Gemini orchestration: Uses nanobanana-mcp tools when available, and gracefully falls back when MCP is not configured.
  • Alt text and frontmatter-ready outputs: Produces descriptive alt text plus suggested cover/OG frontmatter snippets for common blog setups.

Quick Start

Ask the AI to generate a blog hero image for your post idea by running: /blog image generate "Your topic and desired style"

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 and OG social cards automatically?

Generating blog images and OG social cards is handled by transforming your intent into a 6-component prompt and orchestrating Gemini via MCP, returning image paths, alt text, and frontmatter suggestions.

What is the best way to write prompts for AI image generation?

Writing effective AI image generation prompts is structured here using a 6-component brief covering Subject, Action, Context, Composition, Lighting, and Style, ensuring reliable and blog-optimized visual outputs without manual prompt engineering.

Do I need MCP configured to use Gemini for image editing?

You do not strictly need MCP configured to use Gemini for image editing; the Skill uses nanobanana-mcp tools for Gemini orchestration when available and gracefully falls back when MCP is not configured.

Can I edit existing image files instead of generating new ones?

You can edit existing image files by providing an image path; the Skill supports targeted edits to existing images alongside generating new hero, inline, and OG social card visuals using Gemini.

Does this tool support different blog image styles like infographics?

The tool supports domain-focused blog image styles including Editorial, Product, Landscape, UI/Web, Infographic, and Abstract, allowing tailored visual generation for specific content contexts.