# alchaincyf/huashu-design
> An HTML design skill for AI agents (Claude Code, Codex, Cursor) that turns a single prompt into deliverable designs: App/Web prototypes, editable PPTX, animations and infographics. Includes an 84-style library and a six-direction selection flow.
- Magnitude: 3.7 out of 10 — Peaking
- Stars: 26,493 total · +66 stars measured 2026-10-26, 11:33–13:13 UTC, ≈ 135 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: HTML · License: MIT · Created: 2026-04-19 · Last push: 2026-10-23
- GitHub: https://github.com/alchaincyf/huashu-design · Page: https://gitnova.dev/en/r/alchaincyf/huashu-design
## Useful for
- Generate a clickable iOS app prototype from a single text prompt
- Build an HTML deck and export it to editable PPTX
- Produce a 60-second animation and export it as MP4 or GIF
## Why it’s here
- Star-counter measurements on 2026-10-26 (UTC), 11:33–13:13: 26427 → 26493 stars (+66). This is the change over that interval.
- Estimated end-of-day forecast: about +135 stars, using observed gains and the previous day.
- Over the last two days the pace is 1.6× that of the previous week and a half.
- GitHub Trending today: #13, +177 stars.
- About 18 forks a day — people are taking the code.
## Star trust
Star growth looks organic.
Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.
## Numbers
- Forks: 2,950
- Issues and pull requests: 56
- Watchers: 99
- Average over the last week: 152 per day
- Usual pace: 60 per day
- Stars in the last hour (measured): 51
- Latest release: v3.0.0 (2026-10-17)
## Stars per day, last 30 days (oldest → newest, today is partial)
2026-09-27 … 2026-10-26: 26, 20, 29, 13, 12, 9, 11, 17, 20, 26, 38, 38, 56, 48, 50, 48, 48, 46, 69, 49, 173, 116, 98, 146, 101, 90, 223, 164, 205, 66
## Spotted in now
- GitHub Trending today: #13, +177 stars
## Similar by description
1. **genspark-ai/genoffice** — 3.2 · Steady · Apps · TypeScript · +80 stars measured 2026-10-26, 00:14–13:14 UTC, ≈ 136 by evening
Open-source office suite with a built-in AI agent: edits real .docx/.xlsx/.pptx, PDF, Markdown and HTML files, converts PDF to Word on-device, runs on macOS, Windows and Linux.
Full card: https://gitnova.dev/en/r/genspark-ai/genoffice.md
2. **Vincentwei1021/video-shotcraft** — 3.7 · Steady · AI agents · TypeScript · +128 stars measured 2026-10-26, 00:13–13:13 UTC, ≈ 220 by evening
An AI agent skill for Claude Code and Codex that turns them into a motion-design studio: storyboards, animates, and sound-designs cinematic product promo videos with Remotion using 157 shot recipe cards.
Full card: https://gitnova.dev/en/r/Vincentwei1021/video-shotcraft.md
3. **guanmo-ai/design-style** — 0.9 · Cooling · Learning & lists · TypeScript · +2 stars measured 2026-10-26, 00:20–13:22 UTC, ≈ 4 by evening
An open library of design styles and layout methods: each entry has a 15-second motion film, style images, rules, AI prompts and full source code. Useful for designers and AI as a source of visual references and constraints.
Full card: https://gitnova.dev/en/r/guanmo-ai/design-style.md
4. **ZSeven-W/openpencil** — 3.2 · Breakout · AI agents · Rust · +28 stars measured 2026-10-26, 00:12–13:14 UTC, ≈ 55 by evening
Open-source AI-native vector design tool that turns prompts into UI directly on a live canvas, with concurrent agent teams and a built-in MCP server. .op files are JSON with code export.
Full card: https://gitnova.dev/en/r/ZSeven-W/openpencil.md
5. **MiniMax-AI/MiniMax-H3** — 3.0 · Steady · Generative media · Python · +49 stars measured 2026-10-26, 00:14–13:15 UTC, ≈ 86 by evening
MiniMax H3 is an omni-modal generative system that understands text, images, video and audio and generates video with native stereo audio up to 2K and 15 seconds. The repository bundles prompt-writing and style-specific video generation…
Full card: https://gitnova.dev/en/r/MiniMax-AI/MiniMax-H3.md
---
Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-26 13:24 UTC, updated every 30 minutes.