alchaincyf avatar

Huashu Wechat Image

This handles image generation for WeChat articles with opinionated defaults that actually make sense. It walks you through cover images at 2.35:1, body illustrations at 16:9 or 4:3, and info graphics, always showing you design proposals before generating anything. The creator strongly prefers AI generation over HTML screenshot templates because they look less like PowerPoint, only falling back to HTML for complex data tables where you need pixel-perfect text accuracy. It knows about WeChat's safe zone requirements, automatically suggests image counts based on article length, and includes a style gallery mapped to content types. Outputs go straight to an image host since WeChat needs network URLs. Built for the specific constraints of Chinese social publishing.

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

Install

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

Installs into .claude/skills of the current project.

Files

公众号配图工作流

⚠️ 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

设计审美画像和提案格式见姊妹skill xhs-image/SKILL.md,公众号配图同样适用。

核心参数

图片类型尺寸比例Playwright viewportAI Prompt 长宽比声明
头条封面1800 x 766 px2.35:1--viewport-size=1800,7662.35:1 ultra-wide landscape, 1800x766 pixels
正文宽图1920 x 1080 px16:9--viewport-size=1920,108016:9 landscape, 1920x1080 pixels
正文方图1440 x 1080 px4:3--viewport-size=1440,10804:3 landscape, 1440x1080 pixels
信息图1080 x 自由自由--viewport-size=1080,N按内容定

Step 0: 确定配图需求 ✅ 用户确认

向用户展示选项,等待确认:

类型说明图片数量推荐路径
A. 仅封面头条封面图1张AI 生成
B. 正文配图章节配图,辅助阅读理解3-8张AI 生成为主
C. 全套配图封面 + 正文全部4-10张AI 生成为主
D. 纯信息图数据对比、流程图、清单1-5张AI 生成(精确数据表格用HTML兜底)

问用户:

  1. 做封面、正文插图、还是全套?
  2. 文章路径/内容是什么?(分析内容确定配图位置)
  3. 总共需要几张图?

配图数量建议

Sponsors

Details

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

More from alchaincyf/huashu-skills

All 21
1alchaincyf avatarhuashu-xhs-imagealchaincyf/huashu-skills为小红书笔记生成高质量配图。默认AI生成(Gemini),仅精确数据表格用HTML兜底。当用户提到"小红书配图"、"小红书封面"、"小红书图片"、"做张小红书图"、"笔记配图"时使用此技能。740skills.sh installs
2ruvnet 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
3voltagent avatarvoltagent-best-practicesvoltagent/skillsVoltAgent architectural patterns and conventions. Covers agents vs workflows, project layout, memory, servers, and observability.739skills.sh installs
4posit-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
5joellewis 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
6aedev-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