通过指导agent智能调度 GPT-image 模型，针对\"画面中需要清晰可读文字、复杂多元素布局、严格指令跟随\"等场景深度优化 prompt 工程，擅长海报、信息图、菜单字、电商详情页、复杂指令构图与多场景电商视觉，支持多元素指令跟随与文字渲染。
no risky patterns detected
Type: Agent skill (SKILL.md) · Category: Images, Video & Audio · Source: https://github.com/infometa/workbuddyskills/tree/HEAD/connectors/ai-hive/skills/
| Capabilities (fewer powerful permissions = higher) | 50/50 |
| Maintenance | 24/35 |
| Documentation | 15/15 |
Always review files before installing. How scores work. Request a correction