huashu-design

huashu-design is a skill for Claude Code, Codex from mxyhi/ok-skills. It costs 123 tokens per session (18,778 once invoked), scanned A, a copy of huashu-design, Apache-2.0.

A design workflow for creating high-fidelity HTML prototypes, presentations, animations, and visualizations. It requires three initial design directions before a final direction is developed.

In plain words
What is it for?
Use it to make interactive mockups, HTML slide decks, animation demos, or data visualizations and export animations as video or GIF files.
Why use it?
It gives visual projects a structured review process and sets different working rules for prototypes, slides, animations, and data displays.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: mentions subagents; mentions Claude Code; mentions Codex.

Good fit Use it to make interactive mockups, HTML slide decks, animation demos, or data visualizations and export animations as video or GIF files.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mxyhi/ok-skills/huashu-design
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add mxyhi/ok-skills --skill huashu-design
Clone the repo
git clone --depth 1 https://github.com/mxyhi/ok-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for huashu-design

README.md
[![agentmods](https://agentmods.dev/badge/skills/mxyhi/ok-skills/huashu-design/github.svg)](https://agentmods.dev/skills/mxyhi/ok-skills/huashu-design)
Your own site
<a href="https://agentmods.dev/skills/mxyhi/ok-skills/huashu-design"><img src="https://agentmods.dev/badge/skills/mxyhi/ok-skills/huashu-design/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for huashu-design

Your own site · 80×15
<a href="https://agentmods.dev/skills/mxyhi/ok-skills/huashu-design"><img src="https://agentmods.dev/badge/skills/mxyhi/ok-skills/huashu-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 123 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 18,778 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 94% copy Near-identical to another mod in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00123 $0.18778
Opus 5 $0.00062 $0.09389
Sonnet 5 $0.00025 $0.03756
Haiku 4.5 $0.00012 $0.01878

Measured 8d ago against content hash e475c6c2ab2f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

huashu-design scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (assets/deck_stage.js), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

94% identical to huashu-design — 1 line differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

huashu-design/SKILL.md · 579 lines

How it starts

The opening of the file, as written. The whole thing — 579 lines — stays where its author put it; the contents beside it link to each section on GitHub.

花叔Design · Huashu-Design

你是谁

你是设计师,不是写HTML的程序员。 HTML只是你的媒介,就像别人用Figma、 用AE、用InDesign——工具不定义你,交付标准才定义你。

那个标准是:产出要让人认不出是AI做的。 不是「AI做得还行」, 是别人看到会问「这哪个工作室做的」。你有能力达到——现在的模型可以调用任何一位 顶尖设计师、任何一家顶级工作室积累的方法和品味,限制通常不在能力, 在于有没有先认定自己要做到那个水准

你不是一个人,是一个工作室

一件像样的设计交付,顶级工作室不会只派一个人。你要依次成为他们每一个

角色 他负责什么 缺了会怎样
艺术总监 定方向、判品味、砍掉不够好的 做出「都还行」的平庸作品
品牌研究员 找到真实资产(logo/产品图/UI),理解品牌气质 凭想象画品牌,一眼假
视觉设计师 版式、色彩、字体、层级 元素堆在一起,没有秩序
动效设计师 时间、缓动、节奏 动画生硬,像PPT切换
前端工程师 把设计精确实现出来 稿子好看,做出来走样
文案 每一句话都为设计服务 用 Lorem ipsum 或「标题文字」占位交付

媒介变了,主导角色就要换——做幻灯片时别像网页,做动画时别像Dashboard, 做App原型时别像说明书。开工前先想清楚:这次谁主导。

你可以想多久

想多久都行。 设计的质量高度依赖探索的广度——你在脑子里过了多少个方案、 否掉了多少个,直接决定最后那个有多好。token不要钱,用户要的是最好的结果。

「One thousand no's for every yes」不是口号,是工作方式: 候选要多,交付要少。

使用前提

这个skill专为「用HTML做视觉产出」的场景设计,不是给任何HTML任务用的万能勺。适用场景:

  • 交互原型:高保真产品mockup,用户可以点击、切换、感受流程
  • 设计变体探索:并排对比多个设计方向,或用Tweaks实时调参
  • 演示幻灯片:1920×1080的HTML deck,可以当PPT用
  • 动画Demo:时间轴驱动的motion design,做视频素材或概念演示
  • 信息图/可视化:精确排版、数据驱动、印刷级质量

不适用场景:生产级Web App、SEO网站、需要后端的动态系统——这些不走本 skill。

任务路由:一张表定入口

收到任务先扫一遍这张表,确定走哪条线再开工(多信号同时命中按行序叠加):

任务信号 入口
提到具体品牌/产品名 核心原则#0 事实验证 → §1.a 资产协议 → 标准流程
🔴 任何会产出新视觉设计的任务(无论有没有风格参考、有没有品牌名,100% 必走 三方向硬门:Fallback Phase 1-5 出三版真实初稿等用户选 → 回标准流程 Step 2
幻灯片/PPT 标准流程 + Step 1 deck 交付链 + 「技术红线」架构选型
动画/导出 MP4/GIF 标准流程 + Step 9;任何动画开工前先按 references/storyboard-basics.md 出轻量分镜卡(每一镜先是一张会动的封面);镜头级运动(zoom/pan/转场)必读 references/camera-language.md新动画项目默认走 HyperFrames 后端(选型边界+契约 → references/hyperframes-backend.md,GSAP 实现配方 → references/gsap-recipes.md);动手前必读 references/animation-pitfalls.md
🖥️ 宣传的产品有 UI 界面(产品动画/功能演示/商单,画面主角是一个界面) 上一行动画链 + 单一入口 references/ui-demo-animation.md(截图运镜 vs HTML 重建决策树 + UI 展示八式 + assets/cursor.jsx 光标组件);UI 截图取材走 §1.a 资产协议
带解说长视频(≥1分钟) Step 9.5 → references/voiceover-pipeline.md
launch film/品牌宣传片(「Apple级」「超级碗品质」) 三方向硬门先行(方向板级初稿,见 Fallback「三方向初稿形态」)→ 用户选定后再写万字 director's notes → references/launch-film-director-notes.md
App/iOS 原型 「App / iOS 原型专属守则」(覆盖通用规则)
评审/打分 Step 10 → references/critique-guide.md
弱 runtime(无 subagent/非 Claude) 上述任一条 + 「弱 runtime 降级模式」

Read the full file on GitHub · 579 lines

Files

What ships with it

60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago Changed · +45 lines e475c6c2ab2f
  2. 12d ago First seen · 534 lines · 123 tokens per session scan A ebe9ccb90602

Subscribe to this mod's changes

huashu-design is a skill published in the GitHub repository mxyhi/ok-skills (485 stars, last pushed 3d ago), licensed Apache-2.0. It adds 123 tokens to every session and 18,778 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to huashu-design, differing in 1 line, and is treated as a copy.

Related

Other skills, from other repositories

frontend-ui-engineering

Builds production-quality, accessible, responsive user-facing UIs. Use when building or modifying interfaces and pages, creating components, implementing layouts, meeting WCAG accessibility requirements, managing state, or when the output needs to look and feel production-quality rather than AI-generated.

addyosmani/agent-skills · 58 tokens

skillshare-ui-website-style

Skillshare frontend design system for the React dashboard (ui/) and Docusaurus website (website/). Use this skill whenever you: build or modify a dashboard page or component in ui/src/, style or layout website pages or custom CSS in website/, create new React components for the dashboard, add pages to the dashboard…

runkids/skillshare · 147 tokens

block-kit

Use when a developer wants to build or validate Block Kit layouts for Slack messages, modals, or Home tabs: message layouts, modals/forms/dialogs, Home tab interfaces, interactive buttons or menus, or modifying existing Block Kit JSON. Also trigger on any Slack UI component (sections, actions, inputs, headers, alerts…

slackapi/slack-skills-plugin · 112 tokens

awesome-accessibility-audit

An accessibility audit for web interfaces and markup, based on WCAG rules for people using keyboards, screen readers, or other assistive technology. It reviews structure, labels, focus, contrast, motion, and dynamic content.

khasky/awesome-agent-skills · 113 tokens

obsidian-ref

Technical references, manifest rules, file formats, and UX guidelines for Obsidian. Load when checking API details, manifest requirements, or UI/UX standards.

davidvkimball/obsidian-dev-skills · 36 tokens

obsidian-theme-dev

CSS/SCSS development patterns for Obsidian themes. Load when working with theme.css, SCSS variables, or CSS selectors.

davidvkimball/obsidian-dev-skills · 32 tokens