Huashu Design: prototypes, slides, animations and infographics in HTML
alchaincyf/huashu-design
One large design playbook for your AI assistant, written in Chinese. It makes clickable app prototypes, web pages, slide decks, infographics and short animated videos as HTML, then exports them to PDF, PowerPoint, MP4 or GIF. Before any new design it shows you three real drafts to choose from and stops until you pick one.
Pack description by its author: “One large design playbook for your AI assistant, written in Chinese. It makes clickable app prototypes, web pages, slide decks, infographics and short animated videos as HTML, then exports them to PDF, PowerPoint, MP4 or GIF. Before any new design it shows you three real drafts to choose from and stops until you pick one.”
Design and frontendKnowledge and rules for your assistantGives your assistant new abilities with scripts
1. Changes your files
Skills that write or edit files: huashu-design.
github.com/alchaincyf/huashu-design/blob/4fc7bfd/2. Runs code on your machine
Start of every design task: learn.py, design_lint.py ledger and capabilities.py run locally. capabilities.py lists skill folder names in ~/.claude/skills and similar, and checks whether OPENAI_API_KEY / GEMINI_API_KEY are set without reading them. Nothing is written. End of a task: design_lint.py check opens the delivery in headless Chromium; ledger add appends the look, project name and absolute path to ~/.huashu-design/ledger.jsonl; learn.py add writes taste notes to ~/.huashu-design/experience.md. HUASHU_DESIGN_HOME moves the folder.
github.com/alchaincyf/huashu-design/blob/4fc7bfd/3. Sends data
The author publishes a full list of network hosts, local files and deletions in SECURITY.md. Watch three things: ref_board.py opens any URL the assistant picks, the local ledger stores absolute project paths, and the optional HyperFrames init adds 19 skills to ~/.claude/skills/. README also links to the author's other skills and social pages; SKILL.md tells the assistant not to promote them during normal tasks.
github.com/alchaincyf/huashu-design/blob/4fc7bfd/4. Commercial use
MIT since 2026-05-14: keep the license notice; older copies had a personal-use license
github.com/alchaincyf/huashu-design/blob/4fc7bfd/Checked against the pack's files at commit 4fc7bfd, on Oct 31, 2026. Tap a verdict to see its source.How we checkedReport an error
The pack has changed since AgentGid checked it on Oct 31, 2026. Some details may be out of date.
Good for you if
- You want a prototype, a deck, a landing page mockup, an infographic or a launch animation from one sentence
- You want to pick between three different looks before the assistant builds the final version
- You need the result as an editable PowerPoint, a PDF, an MP4 or a GIF
- You use Claude Code, Codex, Cursor, Trae, OpenClaw or Hermes
Probably not for you if
- You need a production web app, a site built for search traffic or anything with a server behind it: the skill says it does not cover these
- You want complex 3D, physics or particle animations: the author lists them as out of scope
- You want a quick one-shot result: every new design first goes through the three-drafts step
What you'll notice
- Three drafts first: six small previews, then three full drafts, and the assistant waits for your choice
- Before work starts, the assistant runs small local scripts that read your saved taste notes and past looks
- It searches the web to check facts about any product it shows, and fetches official logos
- It keeps a taste file and a list of past designs in a .huashu-design folder in your home folder, and tells you when it saves a quote of yours
What you need
- Claude Code, Codex, Cursor, Trae, OpenClaw, Hermes
- Free, MIT license
- One command with the skills tool, or clone the folder into your skills folder
- Checks and exports need Python with Playwright and Chromium, Node and ffmpeg. Voice-over and AI video review are optional and need your own ByteDance (Volcengine) keys.
Words on this page
- Skill
- A set of written instructions your AI assistant follows. Installing one is like giving it a playbook.
- API
- A way for programs to talk to a service, usually with a key.
- CLI
- A program you run by typing commands in a terminal.
- Hook
- A small program the assistant runs by itself at set moments, for example when a session starts.
| Repository | alchaincyf/huashu-design |
|---|---|
| GitHub stars | 29,533 |
| Skills | 1 |
| Category | Design and frontend |
| License | MIT |
| Last updated | Nov 10, 2026 · card checked Oct 31, 2026 at commit 4fc7bfd |
| Install counts | alchaincyf/huashu-design on skills.sh, Vercel's skills directory, which shows installs and security audits per skill |
alchaincyf/huashu-design popularity over time
What Huashu Design does
- Routes each request to a module manual: web pages and desktop UI, slide decks, infographics, iOS app prototypes, motion and video, or design critique.
- Start-of-work routine: three local scripts read the user's saved taste notes, the look of recent deliveries (to avoid repeating it) and what tools are installed.
- Fact check first: any named product, version or event is checked with a web search and written to product-facts.md before questions are asked.
- Brand asset rule: every recognisable product or brand in a design gets its official logo, downloaded, checked and recorded in brand-spec.md.
- Three-directions gate: six candidates from three logics (a best-fit designer, a real reference work screenshotted first, a random style from an 84-style library), drawn as thumbnails; the three strongest become full drafts; then it stops.
- Honest content: no invented data, reviews or logo walls; template decorations like an uppercase label over every heading are removed.
- Readability floor in every style: web body text at least 14px, slide body text at least 24px, body contrast at least 4.5:1.
- End-of-work routine: a design check script, a record of the delivered look, and a review of what is worth remembering.
Never cut, per the skill: real brand assets, the readability floor and the three-directions gate, even in weaker assistants.
From the pack's SKILL.md files, summarised by AgentGid.
The skill, explained
huashu-design
Designs prototypes, decks, infographics and animations as HTML files and exports them
You give
- What you want made: a page, an app prototype, a deck, an infographic, an animation or a review
- Your brand assets if you have them: logo, product photos, screenshots, colours, fonts
- References you like
- Your pick among the three drafts
You get
- Six thumbnails and three full drafts in a design-demos folder of your project
- The chosen design as HTML files in your project
- Exports on request: PDF, editable PPTX, MP4, GIF
- For a review: a score per dimension, Keep / Fix lists and three quick wins
Its rules, in pictures
Fonts it uses and the ones it never uses
Accents of two of its sample styles (Pentagram red, Build warm gold)
How things move: its curve against a plain one
Drawn by AgentGid from the values in the skill's files. This is not output of the skill; sample text is ours.
See it in action
The skill defines what its answer looks like. Its own example:
Design review report Overall score: X.X/10 (capped at 6 when the concept scores 5 or less) Scores: concept, philosophy fit, visual hierarchy, craft, function, originality, each X/10 with one line Keep: what works, in design terms Fix: problems by severity, each with current state, why it is a problem and a fix with values Quick wins: the three fixes to make if you only have 5 minutes
When to reach for it
| You want | Use |
|---|---|
| A deck, a prototype or a page from scratch | Describe it in one sentence; pick one of the three drafts |
| Turn an existing HTML file into PDF or PPTX, take screenshots, fix text | Ask directly; mechanical tasks skip the three-drafts step |
| Feedback on a design | "Run a 5-dimension expert review on this design." |
Skills in alchaincyf/huashu-design
| Skill | In plain words | Changes files? | What it does (author) |
|---|---|---|---|
| huashu-design | Designs prototypes, decks, infographics and animations as HTML files and exports them | Yes | 花叔Design——用HTML做高保真原型、幻灯片、动画、可视化与专家评审。任何新设计100%先出三个方向初稿给用户选(指定风格/品牌也不豁免),选定后才执行。触发词:做原型、PPT、幻灯片、动画、设计风格、评审、做个HTML页面、UI mockup、导出MP4/GIF、做个好看的。生产级Web App/需后端的系统不适用。npx skills add alchaincyf/huashu-design --skill huashu-design |
The author's descriptions come from each skill's SKILL.md; the plain-words column is AgentGid's.
Good to know before you install
- Free for commercial use: the pack moved to the MIT license on 2026-05-14. It used to have a personal-use license that barred commercial use, so older copies and forks may carry the old terms.
- It always stops after the three drafts and waits for your choice, even in unattended runs. Skipping needs your explicit words, recorded in direction-approved.md.
- It keeps memory outside your project: ~/.huashu-design/experience.md holds verbatim quotes of your taste remarks, and ledger.jsonl holds each delivery's look, project name and full folder path. Delete the folder to forget.
- About every 30 days it checks GitHub for a newer version tag and writes the date to .last-update-check in the skill folder. It only tells you; it never updates itself. Write off in that file to stop it.
- The optional HyperFrames animation backend installs 19 extra skills into ~/.claude/skills/ when its init command runs.
- The author says the brand asset approach was taken from Claude Design's system prompts circulating in the community.
Before you start
Works in
- Claude Code: skills folder
- Any agent with a skills folder: skills CLI
- Codex: skills folder
- Cursor: skills folder
You will need
- Python with Playwright, Pillow and Chromium: Design checks, reference boards and screenshots
- Node.js and npx: Deck exports (playwright, pdf-lib, sharp, pptxgenjs) and video rendering
- ffmpeg: MP4 and GIF exports
- Volcengine / ByteDance API keys (optional): Cloud voice-over and AI video review only
Steps only you can do
- Pick one of the three drafts (or say in the session that the step may be skipped) (SKILL.md (three-directions gate))
Then: The assistant builds the chosen direction and records the choice in direction-approved.md - Provide brand assets you have (logo, product photos, screenshots, colours, fonts) (references/brand-asset-protocol.md)
Then: The assistant records them in brand-spec.md instead of searching for them - Optional: get your own Volcengine/ByteDance keys and put them in the skill's .env, then allow the run with --yes (.env.example)
Then: The assistant can run cloud voice-over and AI video review - Optional: add design-gate-hook.sh to your agent settings yourself (scripts/design-gate-hook.sh)
Then: Renders of videos 45 seconds or longer are blocked until direction-approved.md exists
Mistakes to avoid
Install with an old skills CLI and use the folder as is
Check that references/, assets/, scripts/ and demos/ are in the skill folder; if not, upgrade the CLI and reinstall or use git clone
Old skills CLI versions copied only SKILL.md, and the skill depends on the other foldersStart an unattended run and expect a finished design at the end
Be there to pick one of the three drafts, or say in that session that the step may be skipped
The assistant stops after showing the drafts, even in unattended sessionsTreat "continue" as permission to skip a gate
Say explicitly that a gate may be skipped; the skip is written to the gate file
The pack counts "continue" as moving to the next step onlyRely on the design check without Python Playwright installed
Install playwright, pillow and Chromium first if you want the check to run
Without the Python Playwright package the check silently skips and only prints the install commandExpect voice-over or AI video review to run after adding keys
Also pass --yes or set HUASHU_CLOUD_OK=1 for those cloud scripts
Both cloud scripts print what would be sent and exit without the consent flag
Which one to pick
| If you need | Pick |
|---|---|
| You want one pack for prototypes, decks, infographics and animations, with three drafts to pick from first | This pack |
| You only need HTML slide decks built with the agent's frontend skills | zarazhangrui/frontend-slides |
| You want Claude Design-style UI mockups, prototypes and decks as self-contained HTML | JimLiu/baoyu-design |
| Your main job is a commercial product launch film | alchaincyf/huashu-motion |
Works well with
- hyperframes: The pack's animation guide uses HyperFrames as a render backend for HTML animations
- simple-icons: The brand asset protocol fetches monochrome brand logos from Simple Icons
- ffmpeg: MP4 and GIF exports call ffmpeg
- claude-code: The README install path is the Claude Code skills folder
May I use it like this?
| Use | Answer | Condition |
|---|---|---|
| In a commercial app | Yes | MIT since 2026-05-14: keep the license notice; older copies had a personal-use license |
| Work for clients | Yes | MIT allows use in client deliverables |
| Passing the files on | Yes | MIT: keep the copyright and permission notice in copies |
| Shipped inside your app | Yes | MIT: keep the copyright and permission notice |
What leaves your machine
- Names of products, versions and events to check → The agent's web search, When a design names a real product, technology, event or person. Opt out: Give the facts yourself or ask the assistant not to search
- Plain GET requests for logos and brand assets → Brand websites, simpleicons.org, Google favicon service, When a design is about a specific brand or names products. Opt out: Provide the logos yourself
- URLs of reference works, opened in headless Chromium → Any URL the assistant picks, When it builds a reference board during the three-directions step. Opt out: Give your own references or ask it to skip the board
- Image search keywords → commons.wikimedia.org, When the assistant fetches stock images for a content design. Opt out: Supply your own images
- A tag listing request for the skill repository → GitHub (git ls-remote against the clone's origin), About every 30 days, only when the skill folder is a git clone. Opt out: Write off into .last-update-check in the skill folder
- Narration text, and compressed segments of your rendered video → openspeech.bytedance.com and ark.cn-beijing.volces.com, with your own keys, Only when you run the optional cloud scripts with --yes or HUASHU_CLOUD_OK=1. Opt out: Do not set the keys or the consent flag
- Font and library requests from generated HTML → fonts.googleapis.com, cdn.jsdelivr.net, unpkg.com and similar CDNs, When you open a generated HTML file in a browser. Opt out: Use system fonts or local copies in the design
Install Huashu Design
Official commands from the repository
npx skills add alchaincyf/huashu-design
Check that references/, assets/, scripts/ and demos/ were copied too; skills CLI 1.5.15 and older copied only SKILL.md.
Remove: delete the huashu-design folder from your skills folder, and ~/.huashu-design/ for the local memory
git clone https://github.com/alchaincyf/huashu-design.git ~/.claude/skills/huashu-design
A git clone also enables the version check; it is skipped when the folder is not a git clone.
Remove: rm -rf ~/.claude/skills/huashu-design (and ~/.huashu-design/)
pip install playwright pillow && playwright install chromium
Deck exports also need npm packages (playwright, pdf-lib, sharp, pptxgenjs) and video needs ffmpeg.
Or with the open-source skills CLI: npx skills add alchaincyf/huashu-design. Skills are instructions your agent follows: read them before installing.
What it installs and runs on your machine
Read in the code at commit 4fc7bfd, Oct 31, 2026
| When | What happens |
|---|---|
| Start of every design task | learn.py, design_lint.py ledger and capabilities.py run locally. capabilities.py lists skill folder names in ~/.claude/skills and similar, and checks whether OPENAI_API_KEY / GEMINI_API_KEY are set without reading them. Nothing is written. |
| End of a task | design_lint.py check opens the delivery in headless Chromium; ledger add appends the look, project name and absolute path to ~/.huashu-design/ledger.jsonl; learn.py add writes taste notes to ~/.huashu-design/experience.md. HUASHU_DESIGN_HOME moves the folder. |
| Network | The assistant runs web searches for named products and downloads official logos from brand sites, simpleicons.org or Google's favicon service (instructions, no script). |
| Network | ref_board.py opens any URL the assistant picks in headless Chromium and screenshots it (no URL filter). fetch_images.py searches Wikimedia Commons and downloads CC or public-domain images. |
| Network | Every 30 days (7 after a failure) the assistant runs git ls-remote against the GitHub origin and writes .last-update-check in the skill folder. |
| Network | tts-doubao.mjs sends narration text to openspeech.bytedance.com and ai-review-video.py sends compressed video segments to ark.cn-beijing.volces.com, with your own keys from the skill's .env, only with --yes or HUASHU_CLOUD_OK=1. |
| Exports | Local Node, Playwright and ffmpeg scripts render HTML to MP4, GIF, PDF and PPTX in your project; temporary folders they create are deleted afterwards. |
| Only if you add it yourself | design-gate-hook.sh is a PreToolUse hook that blocks rendering videos of 45 seconds or more until direction-approved.md exists. It is never installed automatically. |
The author's numbers, as reported
AgentGid did not run these tests
- A style library of 84 HTML-native styles: web 20, deck 20, infographic 20, app 12, Chinese and East Asian 12 (author's count). Source
- In the author's A/B test (v1 vs v2, 6 agents each), v2 reduced stability variance by 5× (internal test, not published). Source
- Design from zero without brand assets drops to 60–65 points by the author's own scale (author's estimate). Source
Settings
HUASHU_DESIGN_HOME: Moves the local memory folder (default ~/.huashu-design)HUASHU_CLOUD_OK: Set to 1 to allow the cloud scripts without --yesSKIP_DESIGN_GATE: Set to 1 in a render command to pass the optional gate hookDOUBAO_TTS_API_KEY, DOUBAO_TTS_VOICE_ID, DOUBAO_TTS_CLUSTER, DOUBAO_TTS_ENDPOINT, ARK_API_KEY: Keys for the optional cloud voice-over and video review, in the skill's .env.last-update-check: File in the skill folder; write off to stop the version check
Quick answers
- Can I use designs made with it commercially?
- Yes. Since 2026-05-14 the pack is under the MIT license, which allows commercial use without asking. Before that date it had a personal-use license that restricted commercial use.
- Does anything leave my computer?
- The design and export steps run locally. The assistant does web searches, logo and image downloads, reference screenshots and a version check against GitHub. Voice-over and AI video review send data to ByteDance only with your own key and an explicit --yes.
- Do I need an API key?
- No. Keys are only for the optional cloud voice-over and video review, read from the skill's own .env.
- The instructions are in Chinese. Does it work in English?
- The author says the assistant works fine with English tasks, and the demos have English versions.
- Can I skip the three drafts?
- Yes, if you say so in that session; the skip is written to direction-approved.md. Iterations on a chosen direction and mechanical tasks skip it too.
Checked by AgentGid on Oct 31, 2026 against commit 4fc7bfd of the pack's own files. Related: alchaincyf/huashu-motion, alchaincyf/huashu-gpt-image, alchaincyf/huashu-art-motion, alchaincyf/huashu-md-html. agent.md for AI agents · Report a mistake
More design and frontend skill packs
| # | Skill pack | Skills | GitHub stars | Updated |
|---|---|---|---|---|
| 1 |
nextlevelbuilder/ui-ux-pro-max-skill Your AI assistant gets a local design library: UI styles, colour palettes, font pairings and UX rules for many product types. Bef…
|
7 | 150K | 2026-11-14 |
| 2 |
Leonxlnx/taste-skill Your AI coding assistant stops building the average landing page. It picks one of 20 researched design directions, finds real, cr…
|
1 | 116K | 2026-11-08 |
| 3 |
tt-a1i/archify Your AI assistant turns a description, a Mermaid sketch or your project's code into an interactive diagram saved as one HTML file…
|
5 | 96.5K | 2026-11-15 |
| 4 |
cathrynlavery/diagram-design Your AI assistant draws clean, editorial diagrams in your brand colours and fonts. You describe the diagram in plain words and ge…
|
1 | 67.2K | 2026-11-12 |
| 5 |
Nutlope/hallmark Your AI assistant builds web pages that look designed, not machine-made. It asks once for your real material and picks one of fif…
|
1 | 55.2K | 2026-11-11 |
| 6 |
wheresryan22/anatomy Your AI assistant explains a technical idea by drawing it as a small, real-looking machine. A rate limiter becomes a bucket of to…
|
1 | 27.4K | 2026-10-18 |