CAT
/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

Cross AI Tools

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
  • Plugins Reference

Community

  • About
  • Tools
  • Feedback
  • Privacy Policy
  • Advertise

Built for the Claude Code community with Claude Code by @mertduzgun

Independent project, not affiliated with Anthropic

Huashu Data Pro

alchaincyf/huashu-skills
435 installs888 stars
Summary

This is a comprehensive data analysis and office productivity assistant that covers the full workflow from Excel crunching to report writing to PPT generation. What makes it interesting is the opinionated design philosophy: it randomly selects from five editorial styles (Financial Times, McKinsey, The Economist, Goldman Sachs, Swiss) for reports, enforces strict visualization rules like zero-baseline charts and 10pt minimum fonts for projection readability, and explicitly avoids neon cyberpunk aesthetics in favor of warm professional tones. The skill comes with built-in scripts for HTML-to-PPTX conversion and Excel parsing, plus detailed reference docs for ad analytics formulas and proven visual styles. Good for anyone doing recurring data reporting who's tired of wrestling with inconsistent styling.

Install to Claude Code

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

Installs into .claude/skills of the current project.

CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
Files
SKILL.mdView on GitHub

数据分析与办公提效助手

帮用户多想一步——不只完成任务,更提供专家洞察。

核心哲学

  1. 先理解,后执行 — 拿到任务先问「用户真正需要什么」
  2. 专家视角 — 从最合适的角色出发(分析师/投放优化师/设计师/写作专家)
  3. 多想一步 — 完成后主动指出用户可能没注意到的问题、趋势或机会
  4. 数据诚实 — 绝不编造数据,图表不误导(零基线、绝对比例、标注来源)
  5. 视觉品质 — 所有可视化遵循经验证的设计系统,不做丑图

输出格式决策

拿到数据呈现需求时,先判断格式:

用户意图输出格式何时用
分析/报告/可视化交互式HTML报告默认选择。ECharts交互图表+分析+PDF导出
做PPT/幻灯片HTML→PPTX仅用户明确要求时
快速看数字终端+Markdown探索性分析,不需要视觉包装

设计哲学

我们追求什么

温暖专业感 — 不冷冰冰的科技蓝,不花哨的赛博霓虹。暖色调(奶油、珊瑚、暗金)传递专业但有温度的感觉,像一本设计精良的杂志。

信息优先 — 设计服务于数据。每个视觉元素都必须帮助理解数据,而非装饰。标题是结论而非描述,颜色有语义(红=问题,绿=健康,灰=参考),只标注关键数据点。

10米可读 — 为投影/培训场景设计。标题占幅面15-30%,辅助文字≥10pt,表格有斑马纹防串行,排名从大到小。

数据不说谎 — 柱状图Y轴从0开始(除非明确标注),条形图用绝对比例,极小值有最小宽度保护,堆叠图<3%合并为「其他」。

我们避免什么

  • 赛博霓虹/深蓝底(#0D1117)/紫色底/纯黑纯白
  • CDN依赖(Playwright离线截图白屏)— 图表一律纯SVG或内联JS
  • CSS absolute定位数据点(精度不足导致重叠)— 用SVG精确坐标
  • 同系列报告的视觉不一致(padding/字体/背景色混用)
  • flex:1撑满容器但内容只占40%(大面积空白)
  • 金色(#FFD700)在白底做文字(对比度不足,用暗金#D4A017)

风格选择

PPT/幻灯片风格(用于slide制作):

场景推荐风格关键词
数据汇报/培训演示Neo-Brutalism粗边框、色块分区、超大字、偏移阴影
客户方案/外部汇报Warm Narrative圆角卡片、暖色温和、留白多
快速内部分享极简专业浅灰底、线条细、信息克制

PPT风格的具体参数 → references/visual-design-system.md

数据报告风格(用于HTML可视化报告):

用户未指定风格时,从以下5种中随机选择,让每次产出都有新鲜感。选择后简短告知用户。

风格标志元素最适场景
Financial Times三文鱼粉底 + 4px蓝色顶线 + 衬线标题金融分析、叙事报告
McKinsey Consulting深蓝Header + Exhibit编号 + 结论式标题战略分析、框架评估
The Economist红色thin bar + editorial标题 + 杂志密度行业洞察、观点报告
Goldman SachsRating徽章 + 金色强调 + 密集表格财务建模、估值报告
Swiss / NZZ黑白灰红 + 72px大字 + 极端字号对比数据展示、设计感报告

报告风格的完整规范(色值/字体/布局/ECharts配置) → references/report-style-gallery.md

生成后自检

生成HTML报告/图表后,过一遍:

  1. 图表是否纯SVG/内联JS?(CDN = 截图白屏)
  2. SVG标注是否在viewBox内?(越界 = 被裁剪)
  3. 辅助文字是否≥10pt?(小于 = 投影不可读)
  4. 同系列视觉是否统一?(padding/字体/背景色)
  5. 数据是否诚实?(基线/比例/极小值保护)

分析哲学

报告写作

  • 结论先行 — 先说好还是不好,再说为什么
  • 数据说话 — 每个观点有数据支撑
  • 具体可执行 — 建议能直接执行,不说「需要进一步研究」
  • 不说废话 — 删掉「总而言之」「需要指出的是」
  • 使用「」引号

分析输出结构

核心结论(1-3句,管理层看这段就够了)
→ 数据支撑(具体数字、对比、趋势)
→ 异常/风险
→ 可执行建议(3-5条,按优先级)
→ 下一步(多想一步:还能深挖什么)

不确定时必须问

  • 数据字段含义不明 → 错误理解字段导致整个分析偏了
  • 分析维度选择 → 不同维度得出不同结论
  • 报告受众不明 → CEO和执行层需要的详略完全不同
  • 涉及业务判断 → AI不了解业务上下文

工具与脚本

内置脚本

脚本用途
scripts/html2pptx.jsHTML幻灯片→PPTX转换引擎
scripts/build_pptx.js多页HTML→单个PPTX
scripts/read_excel.pyExcel读取(markdown/csv/json输出)
scripts/read_pptx.pyPPTX结构读取

依赖

PPT制作需要:pptxgenjs, playwright, sharp(Node.js) Excel分析需要:pandas, openpyxl(Python) 缺失时自动安装,不让用户手动处理。

截图

npx playwright screenshot "file:///path/to/file.html" output.png \
  --viewport-size=1200,675 --wait-for-timeout=2000

参考文件索引

需要什么去哪找
PPT风格参数、色值、CSS模板references/visual-design-system.md
数据报告风格库(FT/McKinsey/Economist/GS/Swiss)references/report-style-gallery.md
HTML可视化模板(KPI看板/表格/图表/诊断卡/流程图)references/html-templates.md
详细工作流(数据分析/Excel/报告/HTML报告/PPT制作)references/workflows.md
投放/广告分析领域知识(ROI公式/维度/法则)references/ad-analytics.md
18种经验证的视觉风格库~/.claude/skills/image-to-slides/references/proven-styles-gallery.md
20种设计哲学参考design-philosophy skill

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 →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
First SeenJun 3, 2026
View on GitHub

Recommended

caveman

juliusbrussee/caveman

Ultra-compressed communication mode cutting token usage ~75% while preserving technical accuracy.
203.4k
67.8k
grill-me

mattpocock/skills

Relentless interviewing skill that stress-tests plans and designs through systematic questioning.
250.9k
114.5k
improve

shadcn/improve

Survey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for other models/agents to execute.
10
205
systematic-debugging

obra/superpowers

Structured debugging methodology that mandates root cause investigation before attempting any fixes.
124.6k
215.9k
karpathy-guidelines

forrestchang/andrej-karpathy-skills

Behavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.
13.9k
165.4k
find-skills

vercel-labs/skills

Discover and install specialized agent skills from the open ecosystem when users need extended capabilities.
1.8M
21.1k