Ross ROSS = Recommend OSS · open-source software intelligence for agents

alchaincyf/huashu-design

Some data may be outdated — see provenance labels.

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 observed · 2026-10-06

github.com/alchaincyf/huashu-design · HTML · MIT (permissive) observed · 2026-10-06

Health v2 · maintenance only

60/100

  • Activity 96
  • Release rhythm 41
  • Longevity 13
How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-10-21. Adoption (stars, forks) is never an input.

  • gap_med: n/a
  • age_days: 184
  • days_rel: 183
  • days_push: 28
  • n_releases_24m: 1

Full methodology

Adoption not part of the score

24608 stars · 2793 forks observed · 2026-10-06

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

Huashu Design is an agent-agnostic skill (installable via skills.sh) that turns one-line prompts into production-quality HTML-native designs: high-fidelity clickable prototypes, presentation slides, animations, and infographics. It bundles 20 design philosophies, a 60-style HTML design library, a 5-dimension design review rubric, and MP4/GIF export, working inside Claude Code, Cursor, Codex, and other skill-capable agents.

Use cases

  • generate a presentation deck from a one-line prompt
  • build a clickable high-fidelity app prototype in HTML
  • create a product launch animation and export it as MP4 or GIF
  • run a 5-dimension design critique on an existing design
  • apply brand assets (logo, palette, screenshots) to generated designs
  • produce print-quality infographics without Figma

When to choose

  • you work inside Claude Code, Cursor, Codex, or another skills-compatible agent and want deliverable designs from prompts
  • you need fast high-fidelity HTML prototypes, slides, or animations without design tools
  • you want consistent, brand-aware output that avoids generic AI-generated look

When to avoid

  • you need a visual design editor with manual control like Figma or After Effects
  • your project requires non-HTML output formats or pixel-perfect design tool files
  • you are not using any agent that supports the skills ecosystem

Facets

plugin · maturity active

templating animation data-visualization developer-tools web-design frontend developer-tools cli cross-platform claude-code ai-agent-skill html-design high-fidelity-prototyping slides mp4-export design-review agent-agnostic automation

1 source

Member repositories

RepositoryRoleHealth v2
alchaincyf/huashu-designmain60

For agents

markdown · JSON · MCP: product_card(name="alchaincyf/huashu-design")

Data as of 2026-10-19T08:05:51.212177+00:00 · Report a problem