CCM
/Skills
SkillsMCPMarketplacesDigestToolsAdvertise

This week in Claude

Every Monday: Claude Code, Agent SDK, MCP, and the Anthropic platform moves worth your time.

Skills by Category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP Servers by Category
Sales & MarketingWeb & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web Crawling
Marketplaces by Category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control

Claude Code Marketplaces

Discover Claude Code plugins, extensions, and tools. Automatically updated directory of Anthropic Claude AI marketplaces with development tools, productivity plugins, and integrations.

Resources

  • Browse Skills
  • Browse MCP Servers
  • Browse Marketplaces
  • Skill index
  • MCP index
  • Marketplace index
  • Plugins Reference

Community

  • About
  • Tools
  • Feedback
  • Privacy Policy
  • Advertise

Built for the Claude Code community with Claude Code by mertbuilds.com

Independent project, not affiliated with Anthropic
alchaincyf avatar

Huashu Design

alchaincyf/huashu-skills
716 installs1.4k stars
Summary

This is a design philosophy consultant that actually shows you options instead of making you guess. When you need a design direction for anything visual (landing pages, PDFs, presentations), it asks a few clarifying questions, then recommends three deliberately different styles from different design schools, each anchored to a real designer or firm like Kenya Hara or Pentagram. The clever part is it immediately spins up three parallel agents to generate actual visual demos as HTML screenshots or AI images using your real content, not lorem ipsum placeholders. You pick one, it generates the AI prompt with specific color codes and constraints, and later runs a brutally honest design critique scoring five dimensions. The whole thing is opinionated about avoiding clichés and comes from a developer who clearly has strong aesthetic preferences.

Install to Claude Code

npx -y skills add alchaincyf/huashu-skills --skill huashu-design --agent claude-code

Installs into .claude/skills of the current project.

CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
inference shell
inference shell
create and run specialised agents in minutes
build now →
MCP-ready Email SendingMCP-ready Email Sending
MCP-ready Email Sending
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Capacitor - Shared memory for your team’s coding agents.
Capacitor - Shared memory for your team’s coding agents.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Give your AI the whole web as clean markdownGive your AI the whole web as clean markdown
Give your AI the whole web as clean markdown
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
inference shell
inference shell
create and run specialised agents in minutes
build now →
MCP-ready Email SendingMCP-ready Email Sending
MCP-ready Email Sending
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Capacitor - Shared memory for your team’s coding agents.
Capacitor - Shared memory for your team’s coding agents.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Give your AI the whole web as clean markdownGive your AI the whole web as clean markdown
Give your AI the whole web as clean markdown
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
Files
SKILL.mdView 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

  1. 约束哲学而非形式 - 定义「为什么这样设计」而非「长什么样」
  2. 深度理解优先 - 先理解用户真正要传达什么,再推荐风格
  3. 设计是概率性的 - 好的约束产生多样化的高质量结果
  4. 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:

  1. 用 Agent Teams 启动3个后台 agent(run_in_background: true)
  2. 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
  3. 用 Playwright 截图(npx playwright screenshot file:///path.html output.png --viewport-size=1200,900)
  4. 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

Phase 4: 用户选择与迭代

用户看完3个视觉Demo后:

  • 选方向:「我喜欢方向A」→ 进入 Phase 5 深化
  • 混合:「A的配色 + C的布局」→ 生成混合版Demo
  • 微调:「方向B不错但字太小了」→ 调整后重新截图
  • 重来:「都不满意」→ 回到 Phase 3 重新推荐

Phase 5: 生成AI提示词

  • 结构:[设计哲学约束] + [内容描述] + [技术参数]
  • ✅ 用具体特征而非风格名
  • ✅ 包含颜色代码(#HEX值)、比例、空间分配、输出规格
  • ❌ 避免花叔禁区:赛博霓虹/深蓝底(#0D1117)
  • 参考 references/design-styles.md 获取提示词模板

Phase 6: 支持迭代优化

  • 变体建议 / 平台优化 / 混合实验

Workflow: 设计后(Phase 7)

自动触发时机:当设计输出完成后

评审维度(0-10分):

  1. 哲学一致性 - 是否忠实于选定的设计哲学?
  2. 视觉层级 - 信息重要性是否清晰?
  3. 细节执行 - 对齐、间距、字体、颜色是否精确?
  4. 功能性 - 设计是否服务于目标,有无过度装饰?
  5. 创新性 - 是否有独特之处,避免了cliché?

输出格式:

## 设计评审报告
**总体评分**:X.X/10 [优秀/良好/需改进/不合格]
**分项评分**:[5个维度各X/10]

### 优点(Keep)
[具体指出做得好的地方]

### 问题(Fix)
[严重程度:⚠️致命 / ⚡重要 / 💡优化]
- 当前状态 → 为什么是问题 → 修复建议(含具体数值)

### 快速修复清单(Quick Wins)
如果只有5分钟,优先做这3件事

评审语气:直接不绕弯 / 解释为什么 + 怎么改 / 7分=良好,8分+=优秀 / 批评设计而非设计师

详细评分标准和常见问题 → 参考 references/critique-guide.md

References Library

文件内容读取时机
references/design-styles.md20种设计哲学详细库(5大流派),含AI提示词模板需要更多风格选项、了解风格细节
references/scene-templates.md按输出类型组织的场景模板(封面/PPT/PDF/信息图等)需要特定场景的尺寸规格和推荐风格
references/critique-guide.md评审深度指南:详细评分标准、场景评审侧重、常见问题清单需要更精确的评审依据

User Preferences

  • ❌ 赛博霓虹/深蓝色底(#0D1117)= 审美禁区
  • ✅ 配图优先AI生成,HTML截图仅在精确数据表格时用
  • ✅ 封面图不加个人署名/水印
  • ✅ 使用「」引号而非""引号(文案中)

网页/App设计 — 图标与图片规则

绝对禁止:

  • ❌ 不使用任何默认 emoji 作为图标
  • ❌ 不留空白占位区域(「此处放置图片」之类的灰色框)

图标方案(按优先级):

  1. 引用开源图标库 — 选与设计风格最匹配的:Lucide(极简)/ Phosphor(温暖)/ Heroicons(Apple风)/ Tabler(通用)
  2. 手写SVG图标 — 当开源库没有合适图标时,用内联 SVG 自行设计,确保线条粗细/圆角与设计系统一致

图片方案(按优先级):

  1. 找到最合适的真实图片 — 搜索并引用外部链接,或下载到本地后在成品中引用本地路径
  2. 引用开源图片 — Unsplash / Pexels 等免费图库的直链
  3. AI生成图片 — 调用 nano-banana-pro 生成匹配当前设计风格的图片,下载后本地引用

总之:交付的设计成品必须是完整的,不能有任何待填充的空缺。

Notes

  • 必须包含设计师/机构名字 — 说「Pentagram的网格系统」而非「网格系统」
  • 推荐时永远解释「为什么这个设计师适合」,不只是「这个风格是什么」
  • 评审时直接指出问题 + 给出解决方案(含具体数值)
  • 鼓励用户实验和迭代,设计本就是概率性的

花叔出品 | AI Native Coder · 独立开发者 公众号「花叔」| 30万+粉丝 | AI工具与效率提升 代表作:小猫补光灯(AppStore付费榜Top1)·《一本书玩转DeepSeek》

Featured
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
inference shell
inference shell
create and run specialised agents in minutes
build now →
MCP-ready Email SendingMCP-ready Email Sending
MCP-ready Email Sending
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Capacitor - Shared memory for your team’s coding agents.
Capacitor - Shared memory for your team’s coding agents.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Give your AI the whole web as clean markdownGive your AI the whole web as clean markdown
Give your AI the whole web as clean markdown
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
Categories
DocumentationSales & MarketingDesign & UI/UX
First SeenJun 3, 2026
View on GitHub

More from alchaincyf/huashu-skills

All 21 skills →
  • Huashu Wechat Image694
  • Huashu Data Pro692
  • Huashu Research686
  • Huashu Xhs Image686
  • Huashu Script Polish685
  • Huashu Topic Gen677
  • Huashu Speech Coach663
  • Huashu Article Edit649
  • Huashu Video Outline647
  • Huashu Article To X645
  • Huashu Info Search645
  • Huashu Image Upload634
  • Huashu Material Search628
  • Huashu Video Check626
  • Huashu Agent Swarm625
  • Huashu Prompt Save617
  • Huashu Md To Pdf990
  • Huashu Douyin Script922
  • Huashu Proofreading813
  • Huashu Slides777

Recommended

More Documentation →
cap-go avatar
capacitor-ci-cd

cap-go/capgo-skills

Complete CI/CD guide for Capacitor apps covering GitHub Actions, GitLab CI, build automation, app signing, and deployment pipelines. Use this skill when users need to automate their build and release process.
715
58
quodsoler avatar
ue-networking-replication

quodsoler/unreal-engine-skills

Use this skill when working on multiplayer networking, replication, RPC calls, net role logic, server/client authority, prediction, or synchronizing game state. Also use when the user mentions 'DOREPLIFETIME', 'dedicated server', 'replicated', or 'net role'. See references/replication-patterns.md for common patterns and references/rpc-decision-guide.md for RPC type selection. For GAS networking, see ue-gameplay-abilities.
714
301
github avatar
code-tour

github/awesome-copilot

Use this skill to create CodeTour .tour files — persona-targeted, step-by-step walkthroughs that link to real files and line numbers. Trigger for: "create a tour", "make a code tour", "generate a tour", "onboarding tour", "tour for this PR", "tour for this bug", "RCA tour", "architecture tour", "explain how X works", "vibe check", "PR review tour", "contributor guide", "help someone ramp up", or any request for a structured walkthrough through code. Supports 20 developer personas (new joiner, bug fixer, architect, PR reviewer, vibecoder, security reviewer, and more), all CodeTour step types (file/line, selection, pattern, uri, commands, view), and tour-level fields (ref, isPrimary, nextTour). Works with any repository in any language.
708
38k
cap-go avatar
capacitor-mcp

cap-go/capgo-skills

Model Context Protocol (MCP) tools for Capacitor mobile development. Covers Ionic/Capacitor component APIs, plugin documentation, CLI commands, and AI-assisted development via MCP. Use this skill when users want to integrate AI agents with Ionic/Capacitor tooling.
703
58
harbor-framework avatar
create-task

harbor-framework/harbor

Create a new Harbor task for evaluating agents. Use when the user wants to scaffold, build, or design a new task, benchmark problem, or eval. Guides through instruction writing, environment setup, verifier design (pytest vs Reward Kit vs custom), and solution scripting.
703
4k
ruvnet avatar
sparc-refine

ruvnet/ruflo

Run the SPARC Refinement and Completion phases — review code, improve test coverage, validate against specification, and generate documentation
702
67.2k