op7418/guizang-social-card-skill

🪧 Claude Code / Codex skill — generate Xiaohongshu carousels & WeChat 21:9+1:1 cover pairs. Editorial × Swiss visual systems, 28 layouts, 10 themes,...

View on GitHub ↗Jump to charts ↓

Summary Information

Updated 33 minutes ago
Added to GitGenius on September 1st, 2026
Created on May 27th, 2026
Open Issues & Pull Requests: 11 (+0)
GitHub issues: Enabled
Number of forks: 546
Total Stargazers: 6,897 (+3)
Total Subscribers: 8 (+0)

Repository Insights (GitGenius)

Most active contributors

Sign in to see contributor activity.

Related repositories by overlapping contributors

No overlapping-contributor repos identified yet.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 8
New in 7 days: 0
Closed in 7 days: 0
Avg open age: 57 days
Stale 30+ days: 3
Stale 90+ days: 2

Recent activity

Opened in 7 days: 0
Closed in 7 days: 0
Comments in 7 days: 1
Events in 7 days: 1

Top labels

No label distribution available yet.

Detailed Description

Guizang Social Card Skill is an agent skill that generates social media cards for Chinese platforms from HTML templates rendered to PNG.

The tool solves the problem of creating platform-specific image layouts for Xiaohongshu (Rednote) carousel posts and WeChat cover pairs with dimensions of 21:9 and 1:1. It works by providing a single HTML file that can be customized and rendered into images through Playwright. The skill includes two distinct visual design systems: an Editorial approach inspired by magazines like Monocle and Kinfolk, emphasizing restrained layouts suitable for narrative and lifestyle content; and a Swiss International style using grids, single accent colors, and extreme typographic contrast, suited for product reviews and technical content. The tool offers 28 layouts across 10 themes, allowing users to generate multiple image variations from articles, captions, screenshots, product notes, subtitles, or photos.

Developers should choose this tool if they need to automate social card generation for Chinese social platforms and work within Claude Code or Codex agent environments. It suits editorial projects, lifestyle content, product reviews, and tutorial documentation where consistent visual branding across multiple layout variations is valuable. The tool is designed as a skill for AI agents rather than a standalone application, making it most useful for workflows where an agent can invoke it programmatically. The project is positioned as a sibling to a related PPT skill, sharing aesthetic language while addressing different content formats: this tool handles static image feed content while the companion project addresses presentation slides.

Development activity shows consistent maintenance with regular updates to support agent environments. The project maintains clear documentation in both English and Chinese, reflecting its focus on accessibility for both international and Chinese-speaking users. Active engagement with the agent ecosystem is evident through explicit support badges for Claude Code and Codex platforms.