What problem does it solve?
Creating a cohesive set of images (Xiaohongshu cards, e-commerce product sets, knowledge cards, carousels) often results in inconsistent subjects, drifting styles, and misplaced text. This Skill enforces a plan-first workflow that locks subject consistency, sequence logic, and visible text placement before any batch image generation happens.
Core Features & Use Cases
- Motive-Driven Set Planning: Infers the user's goal (clicks, education, product showcase, conversion) and selects the right set type and ordering strategy, such as 小红书文字卡片, 知识卡片套图, 知识图解漫画, or 电商配图.
- Batch Consistency Control: Defines one concise shared style guide covering subject identity, product appearance, color system, and lighting so every image in the batch stays visually unified.
- Approval-Gated Generation: Outputs a Markdown plan table with order, title, visual goal, text placement, and detail constraints, then only calls the image generation tool after explicit user confirmation.
- Use Case: A creator asks to turn an article into a 5-card Xiaohongshu carousel. The Skill produces a full card-by-card plan with exact headlines and layout positions, waits for approval, then submits one batch generation call with per-image compiled prompts.
Quick Start
Ask the assistant to turn your article or product into a set of Xiaohongshu cards or an e-commerce image set, then review and confirm the proposed batch plan before generation.
