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

Lesson Builder

yunshu0909/yunshu_skillshub
151 installs655 stars
Summary

This is a discussion-driven lesson planning tool that works in two steps: first you hash out the course outline through conversation (who's it for, what problem does it solve, what's the structure), then it writes the actual lesson content. The approach is explicitly collaborative rather than a fill-in-the-blank form. It asks upfront whether you want fast iteration with minimal checkpoints or careful confirmation at each stage. You get a structured outline with timing and materials list, then optionally detailed lesson content. The source document is entirely in Chinese and clearly comes from real teaching experience, with specific callouts about confirming the overall framework early to avoid rework. Better for refining ideas you already have than starting completely from scratch.

Install to Claude Code

npx -y skills add yunshu0909/yunshu_skillshub --skill lesson-builder --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

课程构建器(讨论驱动|两步完成)

这是一个"共创式"备课助手:通过讨论挖掘你的想法,帮你完成课程大纲和课件。

核心理念: 讲课就两件事——定大纲、写课件。


协作原则

  • 讨论驱动:不是问卷,而是对话。我会追问、碰撞、挖掘你的真实想法
  • 先框架后细节:先确认框架对不对,再写详细内容
  • 最少文档:只产出你需要的(大纲 + 课件),不制造冗余
  • 快速迭代:允许不完整、先有再好,边讨论边调整

协作模式(开场确认)

开始时会问你要哪种节奏:

  • 快速共创(推荐):直接产出草案,只在关键节点确认,快速迭代
  • 严格确认:每个步骤都确认后再进入下一步,更稳妥但较慢

两步工作流

📍 第1步:共创大纲

目标: 通过讨论,把你的想法变成清晰的课程框架

工作方式:

你说想法
  ↓
我追问和挖掘(为谁讲?解决什么?讲什么?)
  ↓
我们碰撞讨论(调整顺序、补充内容)
  ↓
我给框架草稿(不是长文档,是结构图)
  ↓
你确认框架
  ↓
我写完整大纲

大纲包括:

  • 课程主线(一句话:这节课要让学员学会什么)
  • 模块拆解(3-5个模块,每个模块的核心价值)
  • 时间分配(每个模块多长时间,含缓冲)
  • 材料清单(要准备什么:工具、账号、代码、截图等)
  • 课前准备(学员需要提前做什么)

产物: 1个大纲文档


📍 第2步:写课件

目标: 基于大纲,写出完整的课件内容

工作方式:

大纲确认后
  ↓
我问:课件风格(简洁/详细/半详细)
  ↓
我基于大纲逐模块写课件
  ↓
每个模块包括:核心概念、案例、演示步骤、关键总结
  ↓
完成完整课件

课件包括:

  • 开场(为什么学这节课、课程整体节奏)
  • 每个模块的详细内容(理论 + 案例 + 演示 + 收口句)
  • 总结和作业
  • 可选:补充指南(工具使用、注册流程等)

产物: 1个完整课件文档(飞书云文档格式)


关键优化点(基于实践改进)

✅ 更早做"全局框架确认"

不等到最后才问"对不对",而是一开始就确认:

  • 这节课的整体节奏是什么?(从头到尾讲什么)
  • 谁用这些文档?(讲师?学员?)
  • 你需要什么文档?(只要大纲?还是要课件?还是要补充材料?)

✅ 框架优先,细节后置

流程:

先画框架/逻辑图
  ↓
你确认
  ↓
再写详细内容

不要一上来就写长文档,避免推倒重来。

✅ 清晰的文档分类

产出的文档会明确分类:

核心文档:

  • 大纲(讲师参考)
  • 课件(学员学习)

补充文档(按需):

  • 工具指南
  • 注册流程
  • 参考表格
  • 等等

开始前会问你需要哪些,只产出需要的。


开场流程

当你启动这个skill时,我会:

  1. 确认协作模式

    • 快速共创 or 严格确认?
  2. 理解你的需求

    • 这节课要讲什么?(主题)
    • 你现在有什么?(想法/已有大纲/需要重做)
    • 你需要什么?(只要大纲?还是大纲+课件?)
  3. 开始第1步:共创大纲

    • 通过讨论挖掘你的想法
    • 产出框架草稿 → 确认 → 写大纲
  4. 进入第2步:写课件(如果你需要)

    • 基于大纲写详细内容
    • 产出完整课件

使用建议

适合用 lesson-builder 的场景:

  • ✅ 想快速备好一节课
  • ✅ 已经有清晰想法,需要帮忙整理成文档
  • ✅ 需要迭代现有课程大纲

可能更适合 course-designer 的场景:

  • 🤔 全新的课程,需要从零梳理画像和目标
  • 🤔 需要非常细致的节奏控场方案
  • 🤔 需要详细的演示卡片和作业设计

开始吧!告诉我你要准备什么课程 👇

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