meigen

Quick gallery search. Use when user runs /meigen:find with keywords to browse inspiration.

Quick image generation. Use when user runs /meigen:gen with a prompt. Skips intent assessment, generates directly.

List available AI models and switch the default model for this session. Use when user runs /meigen:models to see or change models.

Interactive provider configuration wizard. Use when the user runs /meigen:setup, says "configure meigen", "set up image generation", "add API key", or otherwise needs help wiring up an image generation provider (MeiGen platform, ComfyUI, or any OpenAI-compatible API).

Gallery search and inspiration agent. Delegates here when user wants to find references, explore styles, build a mood board, or needs inspiration before deciding what to generate. Searches the MeiGen gallery database of 1,446 curated AI-generated images.

Image generation executor agent. Delegates here for ALL generate_image calls to keep the main conversation context clean. Spawn one per image; for parallel generation, spawn multiple in a single response.

Batch prompt writing agent. Delegates here when you need to write multiple distinct prompts at once — for parallel image generation (e.g., "5 logo concepts"), serial-to-parallel workflows (e.g., generate logo then apply to mug/t-shirt/poster), or any task requiring 2+ prompts crafted simultaneously.

Multi-angle product imagery workflow. Use when the user wants to "shoot a product", "make e-commerce product images", "product photography set", "电商产品图", "产品多角度图", "brand product visuals", or provides a single product photo and asks for marketing-ready variations. Produces 4 distinct directions (lifestyle scene, macro detail, scale/context, marketing layout) from one reference image. NOT for: portraits, generic illustration, logo design, video creation — use other skills or generate_image directly.

Vertical-format thumbnail and poster workflow for short-video platforms and social feeds. Use when the user asks for a "video thumbnail", "短视频封面", "竖版海报", "TikTok cover", "Reels cover", "YouTube Shorts thumbnail", "social media poster" — anything optimized for 9:16 mobile feed scrolling with prominent headline space. Produces high-contrast, headline-friendly cover art in 9:16 by default. NOT for: full posters meant for print, photorealistic portraits without text overlay intent, horizontal banners — use other skills.

This skill should be used when the user asks to "generate an image", "create artwork", "design a logo", "make a poster", "draw something", "find inspiration", "search for reference images", "enhance my prompt", "improve prompt", "brand design", "product mockup", "batch generate images", "multiple variations", "generate a video", "make a video", "animate this photo", "image-to-video", or discusses AI image/video generation, visual creativity, prompt engineering, reference images, style transfer. Also activate when user mentions MeiGen, image models, aspect ratios, or art styles. NOT for: generic chat/text tasks, code generation, document writing, video editing of existing footage, audio/TTS, real-photo retouching of user files outside the generation flow, or any task unrelated to AI image/video creation.

2 hooks across 2 events

Bare-minimum output. Just images and file paths, no commentary. Good for batch generation workflows.

Art direction mode. Frames everything through visual storytelling, mood boards, and design thinking. Ideal for extended creative sessions.