huashu-skills is a catalogue of Agent Skills, which are reusable instruction packages that extend coding agents such as Claude Code, Codex, and Kimi Code for particular tasks. It organizes skills for design, research, document conversion, content creation, and other workflows, and includes machine-readable metadata and update checking. The catalogue entries are the skills and related tools that agents install and use.
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.
npx skills add alchaincyf/huashu-skills --skill huashu-designgit clone --depth 1 https://github.com/alchaincyf/huashu-skillsWrote 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.
[](https://agentmods.dev/skills/alchaincyf/huashu-skills/huashu-design)<a href="https://agentmods.dev/skills/alchaincyf/huashu-skills/huashu-design"><img src="https://agentmods.dev/badge/skills/alchaincyf/huashu-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.
<a href="https://agentmods.dev/skills/alchaincyf/huashu-skills/huashu-design"><img src="https://agentmods.dev/badge/skills/alchaincyf/huashu-skills/huashu-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 80 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00069 | $0.02499 |
| Opus 5.5 | $0.00028 | $0.01000 |
| Sonnet 5.5 | $0.00014 | $0.00500 |
| Haiku 4.5 | $0.00007 | $0.00250 |
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 1mo ago.
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.
How it starts
The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Philosophy Consultant
像顶级设计企业那样理解需求，推荐设计哲学方向，生成AI提示词，并进行专家级评审。
Core Principles
- 约束哲学而非形式 - 定义「为什么这样设计」而非「长什么样」
- 深度理解优先 - 先理解用户真正要传达什么，再推荐风格
- 设计是概率性的 - 好的约束产生多样化的高质量结果
- 评审如乔布斯 - 高标准，但给出可执行的改进路径
When This Skill Triggers
设计前（Design Direction） — 任何涉及视觉呈现的输出需求：
- 网页/落地页/官网、App界面/原型
- PPT/Keynote、PDF报告/白皮书
- 信息图/海报/配图/封面
设计后（Design Critique） — 当视觉设计产出完成后自动启动评审。
Workflow: 设计前（Phase 1-6）
Phase 1: 深度理解需求
- 提问：目标受众 / 核心信息 / 情感基调 / 输出格式
- 一次最多3个问题；需求已清晰则跳过
Phase 2: 顾问式重述（100-200字）
- 用自己的话重述本质需求、受众、场景、情感基调
- 以「基于这个理解，我为你准备了3个设计方向」结尾
Phase 3: 推荐3套设计哲学
每个方向包含：
| 要素 | 说明 |
|---|---|
| 风格名称 | 必须含设计师/机构名（如「Kenya Hara式东方极简」，不能只说「极简主义」） |
| 为什么适合 | 50-100字，连接需求与该设计师的哲学 |
| 核心特征 | 3-4条标志性视觉要素 |
| 气质关键词 | 3-5个 |
| 代表作参考 | 可选，方便用户搜索理解 |
差异化策略（必须遵守）：
3个方向必须来自3个不同流派，形成明显的视觉反差：
| 流派 | 视觉气质 | 适合作为 |
|---|---|---|
| 信息建筑派（01-04） | 理性、数据驱动、克制 | 安全/专业选择 |
| 运动诗学派（05-08） | 动感、沉浸、技术美学 | 大胆/前卫选择 |
| 极简主义派（09-12） | 秩序、留白、精致 | 安全/高端选择 |
| 实验先锋派（13-16） | 先锋、生成艺术、视觉冲击 | 大胆/创新选择 |
| 东方哲学派（17-20） | 温润、诗意、思辨 | 差异化/独特选择 |
推荐组合示例：
- 「Pentagram编辑风（信息建筑）+ Sagmeister实验排版（极简主义）+ Kenya Hara东方留白（东方哲学）」
- 「Fathom数据叙事（信息建筑）+ Field.io粒子生成（运动诗学）+ Takram思辨设计（东方哲学）」
❌ 禁止从同一流派推荐2个以上风格 — 那样差异化不够，用户看不出区别
Phase 3.5: 并行生成3个视觉Demo
核心理念：看到比说到更有效。 不要让用户凭文字描述想象设计风格，直接展示。
推荐完3个方向后，立即主动启动 Agent Teams，并行生成3个视觉Demo：
告知用户：「我已启动3个并行Agent，正在为你生成3个方向的视觉样稿。
稍等片刻就能看到实际效果，比文字描述直观得多。
看完后你可以：选一个方向深化 / 混合多个方向的元素 / 提出修改意见。」
生成流程：
- 用 Agent Teams 启动3个后台 agent（
run_in_background: true） - 每个 agent 根据对应风格的提示词DNA + 用户实际内容，生成一个单页 HTML Demo
- 用 Playwright 截图（
npx playwright screenshot file:///path.html output.png --viewport-size=1200,900） - 3个 agent 完成后，将3张截图一起展示给用户
Demo内容规则：
- 使用用户的真实内容/主题（不是占位符Lorem ipsum）
- Demo 呈现用户要求的实际输出格式（要PPT就做slide样式，要封面就做封面）
- HTML 文件存放在
_temp/design-demos/目录，命名：demo-[风格名].html
执行路径选择：
| 风格的「最佳路径」 | Demo 生成方式 |
|---|---|
| HTML | 生成完整 HTML → Playwright 截图 |
| AI生成 | 用 nano-banana-pro 生成图片（风格DNA + 内容描述） |
| 混合 | 生成 HTML 布局 + 用 AI 生成插画配图 |
What ships with it
3 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.
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.
- 1mo ago First seen · 189 lines · 69 tokens per session scan A a66f6a59124c
huashu-design is a skill published in the GitHub repository alchaincyf/huashu-skills (2,025 stars, last pushed yesterday), licensed MIT. It adds 69 tokens to every session and 2,499 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
frontend-design
Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.
display-glasses-with-jetpack-compose-glimmer
Provides guidelines for developing projected Android XR apps for display glasses using the Jetpack Compose Glimmer UI toolkit. Covers Glimmer design principles, workflows, and interaction models for the glasses form factor. Use this skill to build an Android XR Augmented Experience app with Jetpack Compose Glimmer.…
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
read
Fetches URLs and PDFs, then summarizes or returns clean Markdown; can also search the web through DeepSeek when built-in search is thin. Use when asked to read, fetch, quote, cite, convert, or save a URL or PDF. Not for local text files already in the repo.
visual-edit
Open and collaboratively edit a running local app in Design, with shared fallback previews and source handoff. Use when the user asks to inspect, share, or edit a real local app in Design.
visual-plan
Turn ordinary text plans into rich interactive visual plans with diagrams, file maps, annotated code, open questions, and UI/prototype review when useful.