Loading...
Loading...
Found 3 Skills
Choose GPT-Image2 / gpt-image-2 visual styles and industrial prompt templates from the awesome-gpt-image-2 style library. Use when an agent needs to create, rewrite, classify, or improve image-generation prompts with repository-backed templates, categories, style tags, scene tags, pitfalls, and example cases.
Use when the user wants Claude Code to generate images from prompts, use /gi or /gi-setup, configure an OpenAI Images API-compatible endpoint, create placeholder images, delegate generation to a background subagent named painter, pass model parameters, choose output paths, or maintain an image index. If generation is requested before setup, guide the user through /gi-setup instead of failing.
Plan, generate, judge and package a full paid-social ad campaign (feed masters + 3-frame story sequences) with Higgsfield gpt_image_2 — copy matrix → prompt build → direction gate → batch generation → vision judge loop → launch package with captions. Use when the user asks for an ad campaign, a batch of ads, or paid-social creative at volume.