alchaincyf avatar

Huashu Xhs Image

Generates cover images for Xiaohongshu (Little Red Book) posts with a specific design workflow. You get 2-3 design proposals first, pick one, then it produces both an AI-generated version via Gemini and an HTML fallback for comparison. The workflow is opinionated around a creator named Huashu's preferences: warm colors, oversized text that fills the frame, handwritten fonts, paper textures, and absolutely no watermarks. It enforces 3:4 portrait format at 1080x1440px and includes built-in design review scoring before upload. The whole thing assumes you're writing in Chinese and optimizing for mobile feed visibility. If you're posting to Xiaohongshu regularly and want consistent, scroll-stopping visuals without manually designing each one, this handles the full pipeline from concept to image hosting.

skills.sh installs
740
GitHub stars
2.2K
last updated
Aug 21, 2026

Install

$ npx -y skills add alchaincyf/huashu-skills --skill huashu-xhs-image --agent claude-code

Installs into .claude/skills of the current project.

Files

小红书配图工作流

⚠️ 核心原则:先提案,后生成

绝对不能跳过设计提案直接出图。 正确流程:

理解内容 → 设计提案(2-3个方向)→ 用户选择 → 生成 → 预览确认 → 上传

花叔设计审美画像

喜欢的

  • 质感和温度 — 纸张褶皱、手写笔触、印章、胶带等有机元素
  • 手绘/书法字体 — 笔记感、个人分享场景尤其适合
  • 文字撑满画面 — 小红书是手机竖屏,文字要大到一眼看清
  • 核心元素强化 — 关键数字/关键词做视觉hero(放大3倍、变色、加装饰)
  • 结构清晰 — 主标题 > 副标题 > 列表,层次分明
  • 暖色调 — 奶油色、暖橙、暖金表现好

不喜欢的

  • HTML截图 — 太平面、像PPT模板、没有灵魂(仅精确数据表格兜底)
  • 赛博霓虹/深蓝底 — #0D1117等深蓝色底属于审美禁区
  • 署名/水印 — 封面图不出现「花生」「花叔」「@花生」
  • 过度留白 — 宁可满一点,不要空荡荡

验证过的好风格

风格表现适用
手绘笔记(暖色纸张+书法字+手绘图标)⭐⭐⭐⭐⭐教程、干货、个人分享
暗金海报(深色底+金色大字)⭐⭐⭐⭐产品发布、震撼标题(需搭配好内容)
极简信息图(浅底+大数字+简洁层次)⭐⭐⭐⭐数据驱动、对比

核心参数

参数值
标准尺寸1080 x 1440 px (3:4)
AI 生成分辨率--resolution 2K
AI Prompt 长宽比声明3:4 portrait aspect ratio, 1080x1440 pixels
HTML viewport(兜底用)--viewport-size=1080,1440

Step 1: 理解内容

读取用户提供的内容,快速提炼:

  • 主题:这篇讲什么?
  • 核心关键词:哪些词/数字需要做视觉hero?
  • 情绪/调性:悬念?干货?温暖?震撼?
  • 图片数量和类型:单封面 / 轮播套图 / 信息图?

不需要向用户展示分析结果,直接进入Step 2。


Step 2: 设计提案 ✅ 必须等用户选择

这是整个流程最关键的一步。禁止跳过。

提案格式

向用户展示 2-3个设计方向,每个方向包含:

Sponsors

Details

Repository
github.com/alchaincyf/huashu-skills
Category
Frontend Development
First seen
Jun 3, 2026

More from alchaincyf/huashu-skills

All 21
1ruvnet avatarddd-contextruvnet/rufloCreate and manage a DDD bounded context with standard directory structure. Use when starting a new subdomain, splitting a monolith into bounded contexts, or sca739skills.sh installs
2voltagent avatarvoltagent-best-practicesvoltagent/skillsVoltAgent architectural patterns and conventions. Covers agents vs workflows, project layout, memory, servers, and observability.739skills.sh installs
3posit-dev avatarr-cli-appposit-dev/skillsBuild command-line apps in R using the Rapp package. Use when creating a CLI tool in R, adding argument parsing to an R script, turning an R script into a comma736skills.sh installs
4joellewis avatarforward-riskjoellewis/finance_skillsEstimate potential future losses using VaR, Expected Shortfall, Monte Carlo simulation, and stress testing. Use when the user asks about Value-at-Risk, CVaR, Ex733skills.sh installs
5aedev-tools avatarafter-effectsaedev-tools/adobe-agent-skillsAutomate Adobe After Effects via ExtendScript. Use when the user asks to create, modify, or query anything in an After Effects project — layers, keyframes, expr731skills.sh installs
6ruvnet avatarvector-clusterruvnet/rufloCluster code by graph community detection via npx ruvector@0.2.25 hooks graph-cluster (spectral / Louvain)729skills.sh installs