code-explainer

作者: microsoft

用通俗易懂的英语解释代码片段,逐步分解代码的功能。非常适合学习、代码审查或编写文档。

npx skills add https://github.com/microsoft/waza --skill code-explainer

Code Explainer

A skill that explains code snippets in clear, educational language. Helps developers understand unfamiliar code, algorithms, and programming patterns.

Skill Activation Triggers

Use this skill immediately when the user asks to:

  • "Explain this code"
  • "What does this function do?"
  • "Break down this algorithm"
  • "Help me understand this snippet"
  • "Walk me through this code"
  • "What's happening in this file?"

Key Indicators:

  • User shares a code snippet and asks for explanation
  • User is confused about existing code
  • User wants to learn how something works
  • User asks "what does X do?" about code

Do NOT use when:

  • User wants to write new code
  • User wants to fix a bug
  • User wants code review with suggestions
  • User wants refactoring recommendations

Quick Reference

PropertyValue
InputCode snippet + optional language hint
OutputPlain language explanation
Best forLearning, onboarding, code comprehension

Explanation Guidelines

Structure

A good code explanation should include:

  1. Overview - One sentence summary of what the code does
  2. Step-by-step breakdown - Walk through the logic
  3. Key concepts - Explain any patterns or techniques used
  4. Example - Show sample input/output if applicable

Tone

  • Educational and approachable
  • Avoid jargon unless explaining it
  • Use analogies when helpful
  • Assume the reader is smart but unfamiliar with this specific code

Language-Specific Tips

LanguageFocus On
PythonList comprehensions, decorators, generators
JavaScriptAsync/await, closures, callbacks
SQLJOINs, subqueries, aggregations
JavaOOP patterns, generics, streams

Examples

Example 1: Python Recursion

User prompt:

Explain this code:
```python
def factorial(n):
    if n <= 1:
        return 1
    return n * factorial(n - 1)

Good response:

This is a recursive function that calculates the factorial of a number.

Overview: It multiplies a number by all positive integers less than it (e.g., 5! = 5 × 4 × 3 × 2 × 1 = 120).

Step by step:

  1. Base case (if n <= 1): If n is 0 or 1, return 1 (since 0! and 1! both equal 1)
  2. Recursive case: Otherwise, multiply n by factorial(n-1)

Example: factorial(4) → 4 × factorial(3) → 4 × 3 × factorial(2) → 4 × 3 × 2 × factorial(1) → 4 × 3 × 2 × 1 = 24

Example 2: JavaScript Async/Await

User prompt:

What does this code do?
```javascript
async function fetchUserData(userId) {
  try {
    const response = await fetch(`/api/users/${userId}`);
    if (!response.ok) throw new Error('User not found');
    return await response.json();
  } catch (error) {
    console.error('Failed:', error);
    return null;
  }
}

Good response:

This is an async function that fetches user data from an API.

Overview: It makes an HTTP request to get a user's data, handles errors gracefully, and returns the result as JSON.

Step by step:

  1. async function - Declares this function will use await for promises
  2. await fetch(...) - Makes HTTP GET request, waits for response
  3. if (!response.ok) - Checks if request succeeded (status 200-299)
  4. await response.json() - Parses response body as JSON
  5. catch block - If anything fails, logs error and returns null

Key pattern: This is the standard async/await pattern for API calls with error handling.

Error Cases

If the user provides:

  • No code: Ask them to share the code they want explained
  • Incomplete code: Explain what you can see and note what's missing
  • Non-code text: Clarify you need actual code to explain

Integration Notes

This skill works well with:

  • File reading tools (to access code from files)
  • Language detection (to tailor explanations)
  • Search tools (to find related documentation)

来自 microsoft 的更多技能

oss-growth
microsoft
OSS增长黑客角色
agent-framework-azure-ai-py
microsoft
使用Microsoft Agent Framework Python SDK(agent-framework-azure-ai)构建Azure AI Foundry代理。在创建使用AzureAIAgentsProvider的持久化代理、使用托管工具(代码解释器、文件搜索、网络搜索)、集成MCP服务器、管理对话线程或实现流式响应时使用。涵盖函数工具、结构化输出和多工具代理。
development
airunway-aks-setup
microsoft
在AKS上设置AI Runway——从裸集群到运行模型。涵盖集群验证、控制器安装、GPU评估、提供商设置和首次部署。适用场景:“设置AI Runway”、“接入AKS集群”、“安装AI Runway”、“airunway设置”、“将模型部署到AKS”、“在AKS上进行GPU推理”、“在AKS上配置KAITO”、“在AKS上运行LLM”、“在AKS上使用vLLM”、“在AKS上设置模型服务”、“AI Runway控制器”。
devops
appinsights-instrumentation
microsoft
使用Azure Application Insights对Web应用进行插桩的指南。提供遥测模式、SDK设置和配置参考。适用场景:如何对应用进行插桩、App Insights SDK、遥测模式、什么是App Insights、Application Insights指南、插桩示例、APM最佳实践。
devops
applicationinsights-web-ts
microsoft
使用Application Insights JavaScript SDK(@microsoft/applicationinsights-web)为浏览器/Web应用添加检测。用于真实用户监控(RUM)——页面视图、点击、AJAX/fetch依赖项、异常、自定义事件,以及与后端OpenTelemetry追踪关联的浏览器端GenAI代理追踪。涵盖SDK加载器脚本和npm设置、框架扩展(React、React Native、Angular)、点击分析、遥测初始化器,以及从浏览器发出的代理/工具/模型跨度所遵循的OTel GenAI语义约定。
devops
azure-ai-anomalydetector-java
microsoft
使用适用于 Java 的 Azure AI 异常检测器 SDK 构建异常检测应用程序。在实现单变量/多变量异常检测、时间序列分析或 AI 驱动的监控时使用。
development
azure-ai-language-conversations-py
microsoft
使用azure-ai-language-conversations Python SDK实现对话语言理解(CLU)。当使用ConversationAnalysisClient分析对话意图和实体、构建NLP功能或将语言理解集成到应用程序中时使用。
development
azure-ai-ml-py
microsoft
Azure Machine Learning SDK v2 for Python。用于机器学习工作区、作业、模型、数据集、计算资源和管道。 触发词:“azure-ai-ml”、“MLClient”、“工作区”、“模型注册表”、“训练作业”、“数据集”。
development