alchaincyf/huashu-design

Huashu Design · HTML-native design skill for Claude Code · Claude Code 里 HTML 原生的设计 skill · 高保真原型 / 幻灯片 / 动画 + 20 设计哲学 + 5 维评审 + MP4 导出 · Agent-agnostic

View on GitHub ↗Jump to charts ↓

Summary Information

Updated 23 minutes ago
Added to GitGenius on September 1st, 2026
Created on April 19th, 2026
Open Issues & Pull Requests: 4 (+0)
GitHub issues: Enabled
Number of forks: 2,767
Total Stargazers: 23,948 (+0)
Total Subscribers: 95 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 5.1 days
Mean response time: 11.2 days
90th percentile: 47.0 days
Tracked items: 34

How this project is maintained

Around half of the issues opened in the past year never receive a reply. Only 19% of issues opened in the past year have been closed. Three people close 97% of everything that gets resolved.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 3
New in 7 days: 1
Closed in 7 days: 0
Avg open age: 15 days
Stale 30+ days: 1
Stale 90+ days: 0

Recent activity

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

Top labels

No label distribution available yet.

Most active issues this week

No issue events were indexed in the last 7 days.

Detailed Description

Huashu Design is a design skill for Claude Code and other AI agents that generates production-ready visual assets from text prompts.

The tool addresses the gap between rapid prototyping and design quality by generating HTML-native designs—product animations, clickable app prototypes, editable presentations, and print-ready infographics—in three to thirty minutes. It works by accepting brand assets like logos, color palettes, and UI screenshots to understand brand identity, then applies three logic advisors and sixty HTML native style libraries as fallback when no brand materials are provided. The generated designs are created entirely through HTML and code rather than external design tools, and the tool itself demonstrates its capabilities through animations and interactive elements built with its own system.

The tool suits teams shipping products quickly who need professional-grade design output without design tool expertise or extended timelines. It works across multiple AI agents including Claude Code, Cursor, Codex, OpenClaw, and Hermes, making it agent-agnostic. The README does not compare it to alternative design tools or approaches.

The project includes comprehensive supporting materials beyond the main skill file, with four subdirectories containing recipes, scripts, assets, and demos that are essential to functionality. Installation requires ensuring all supporting directories are present, as older versions of the skills CLI had a bug that only synced the main file. The project provides video tutorials and detailed setup documentation, including fallback installation via git clone for users encountering issues with the package manager approach.