Blog Image

This orchestrates Gemini's image generation specifically for blog content, with Claude acting as creative director between your intent and the API. It uses a 6-component prompt engineering system (subject, action, context, composition, lighting, style) across six domain modes like Editorial, Product, and Infographic. Generates hero images, OG cards, inline illustrations, and section dividers at blog-appropriate dimensions and aspect ratios. The workflow includes MCP availability checking with graceful fallback, intelligent aspect ratio selection, and post-processing with ImageMagick for web optimization. What stands out is the structured approach to prompt construction. Instead of passing raw user requests to Gemini, it translates vague ideas into detailed narrative prompts with proper technical specs, which likely produces far more consistent results than ad-hoc generation.

skills.sh installs: 2.7K
GitHub stars: 2.7K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add agricidaniel/claude-blog --skill blog-image --agent claude-code

Installs into .claude/skills of the current project.

Files

Blog Image - AI Image Generation for Blog Content

Bundled paths below use host Markdown substitution of ${CLAUDE_SKILL_DIR}; it is not an exported shell variable. Resolve them before execution, quote paths, and refuse nonabsolute overrides. Pass blog_reference_root resolved from ${CLAUDE_SKILL_DIR}/../blog/references, blog_template_root from ${CLAUDE_SKILL_DIR}/../blog/templates, and needed sibling roots to agents. Read the main reference orchestration-details.md before loading project context; pass only its helper-fenced output to downstream agents.