What problem does it solve?
This Skill removes the friction of producing blog-quality images by acting as a Creative Director that interprets intent, crafts optimized 6-component prompts, and orchestrates Gemini via an MCP server so authors get consistent hero, inline, OG, and divider images without manual prompt engineering.
Core Features & Use Cases
- Reasoned Prompt Engineering: Always creates a 6-component Reasoning Brief (Subject, Action, Context, Composition, Lighting, Style) and never forwards raw user text directly to the API.
- Generation & Editing: Drives MCP tools (set_aspect_ratio, gemini_generate_image, gemini_edit_image, gemini_chat) to generate or iteratively refine images and returns image path, crafted prompt, settings, alt text, and frontmatter snippets.
- Domain Modes & Robustness: Supports six blog-optimized domain modes (Editorial, Product, Landscape, UI/Web, Infographic, Abstract), model selection guidelines, post-processing steps, safety rephrase logic, and a graceful fallback to stock photos when MCP is not configured.
- Use Case: Produce a 16:9 hero image for a feature article, generate alt text and a frontmatter snippet, convert to WebP/AVIF, and provide 1–2 refinement suggestions.
Quick Start
Generate a 16:9 editorial hero image for the blog post titled How AI helps governance and return the image path, alt text, aspect ratio, model used, and a frontmatter snippet.
