Image Generation

Generates illustration images for articles and documentation with a smart three-tier fallback: tries Codex's built-in image_gen tool first, then falls back to OpenAI API, then Gemini if needed. You get a default style optimized for technical content (clean, minimal, soft tones) that auto-prepends to your prompts unless you override it. The workflow is practical about paths too, it looks at your existing markdown to figure out where images should go rather than making you specify every time. Defaults to 3:2 landscape at 1K resolution, which works well for blog headers without burning through credits. Handles the boring parts like provider detection and credential checking so you can focus on writing good prompts.

skills.sh installs: 4K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add zc277584121/marketing-skills --skill image-generation --agent claude-code

Installs into .claude/skills of the current project.

Files

Image Generation Skill

Generate illustration images for blog posts, documentation, and technical articles. The workflow is provider-aware:

Codex built-in path first — when the current agent is Codex and the built-in image_gen tool is available, use it directly. This path does not require OPENAI_API_KEY.
OpenAI API fallback — outside Codex, or when the built-in tool is unavailable, use the local script with OPENAI_API_KEY if present.
Gemini fallback — if OpenAI API generation is unavailable or fails, use the same script with GEMINI_API_KEY and the existing Gemini image model.

Load provider-specific references only when needed:

Codex built-in path: references/codex-built-in.md
OpenAI API fallback: references/openai-api.md
Gemini fallback: references/gemini-api.md

When to Use

User asks to generate an illustration, diagram, concept image, article visual, or documentation visual
User is writing an article and needs visual explanations for concepts or workflows
User explicitly asks for a generated raster image