Image Gen

Generates AI images from text prompts using the ListenHub CLI, supporting both Gemini Pro and Flash models with resolutions up to 4K and various aspect ratios. The interaction flow asks one question at a time (model, resolution, aspect ratio, optional reference images) and requires explicit confirmation before generating. Flash model unlocks extreme ratios like 1:8 and 8:1 for panoramic shots. Output can be inline, downloaded to a dated artifact directory, or both. The prompt handling is sensible: it passes your text directly by default and only offers to enrich very short prompts if you haven't asked for verbatim generation. Supports both local files and URLs as style references, up to five per generation.

skills.sh installs: 1.2K
GitHub stars: 82
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add marswaveai/skills --skill image-gen --agent claude-code

Installs into .claude/skills of the current project.

Files

When to Use

User wants to generate an AI image from a text description
User says "generate image", "draw", "create picture", "配图"
User says "生成图片", "画一张", "AI图"
User needs a cover image, illustration, or concept art

When NOT to Use

User wants to create audio content (use /podcast, /speech)
User wants to create a video (use /explainer)
User wants to edit an existing image (not supported)
User wants to extract content from a URL (use /content-parser)

Purpose

Generate AI images using the ListenHub CLI. Supports text prompts with optional reference images (local files or URLs), multiple resolutions, and aspect ratios. Images are saved as local files.

Hard Constraints

Always check CLI auth following shared/cli-authentication.md
Follow shared/cli-patterns.md for command execution and error handling
Always read config following shared/config-pattern.md before any interaction
Output saved to .listenhub/image-gen/YYYY-MM-DD-{jobId}/ — never ~/Downloads/

SKILL.md on GitHub