xiaohongshu-cover-generator

Convert Xiaohongshu copy into three JSON prompt variants with an HTML interface.

Updated Feb 6, 2026
One-click install
npx skills add https://github.com/xu18961999959-sketch/zt --skill xiaohongshu-cover-generator
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: xiaohongshu-cover-generator
Source: https://github.com/xu18961999959-sketch/zt/tree/main/%E5%B0%8F%E7%BA%A2%E4%B9%A6%E5%B0%81%E9%9D%A2%E7%94%9F%E6%88%90%E5%99%A8
Command: npx skills add https://github.com/xu18961999959-sketch/zt --skill xiaohongshu-cover-generator

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill converts user-provided Xiaohongshu copy into optimized cover-generation prompts, saving time and ensuring consistent, high-quality visuals without manual prompting.

Core Features & Use Cases

  • Automated prompt generation: from Xiaohongshu copy to structured prompts for image models.
  • Multi-variant outputs: provides three JSON prompt variants (A/B/C) for quick A/B testing.
  • Interactive HTML workflow: generates an HTML page to preview prompts, copy, and trigger image-generation via Gemini Imagen API.
  • Use case: creators who want fast, repeatable cover prompts for Xiaohongshu posts.

Quick Start

Run the skill with your Xiaohongshu copy; the system will generate three prompt variants and a ready-to-use HTML interface.

Frequently Asked Questions about xiaohongshu-cover-generator

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate image prompts for Xiaohongshu covers from social media copy?

This tool provides three JSON prompt variants (A/B/C) for quick A/B testing, allowing you to select the best structured prompt to trigger image-generation via the Gemini Imagen API.

What is the best way to A/B test visual prompts for social media content creation?

After generating prompt variants from your copy, the system outputs an interactive HTML page to preview prompts, copy text, and trigger image-generation via the Gemini Imagen API.

How does the HTML workflow handle Gemini Imagen API image generation?

The HTML workflow handles image generation by providing an interactive page where users preview generated prompt variants and directly trigger the Gemini Imagen API to produce cover visuals without manual prompting.

Can I use this prompt generator for platforms other than Xiaohongshu?

While designed for social-media content creation and Xiaohongshu covers, the structured, high-density prompts generated from your copy can potentially be adapted for other image-generation platforms requiring similar visual outputs.