wiki-qa

作者: microsoft

通过分析源代码文件回答关于代码仓库的问题。当用户询问某个功能如何运作、想要理解某个…时使用。

npx skills add https://github.com/microsoft/skills --skill wiki-qa

Wiki Q&A

Answer repository questions grounded entirely in source code evidence.

When to Activate

  • User asks a question about the codebase
  • User wants to understand a specific file, function, or component
  • User asks "how does X work" or "where is Y defined"

Source Repository Resolution (MUST DO FIRST)

Before answering any question, you MUST determine the source repository context:

  1. Check for git remote: Run git remote get-url origin to detect if a remote exists
  2. Ask the user: "Is this a local-only repository, or do you have a source repository URL (e.g., GitHub, Azure DevOps)?"
    • Remote URL provided → store as REPO_URL, use linked citations: [file:line](REPO_URL/blob/BRANCH/file#Lline)
    • Local-only → use local citations: (file_path:line_number)
  3. Determine default branch: Run git rev-parse --abbrev-ref HEAD
  4. Do NOT proceed until source repo context is resolved

Procedure

  1. Resolve source repo context (see above)
  2. Detect the language of the question; respond in the same language
  3. Search the codebase for relevant files
  4. Read those files to gather evidence
  5. Synthesize an answer with inline linked citations

Response Format

  • Use ## headings, code blocks with language tags, tables, bullet lists
  • Cite sources inline using resolved format:
    • Remote: [src/path/file.ts:42](REPO_URL/blob/BRANCH/src/path/file.ts#L42)
    • Local: (src/path/file.ts:42)
  • Include a "Key Files" table mapping files to their roles (with linked citations in the "File" column)
  • Include at least 1 Mermaid diagram when the answer involves architecture, data flow, or relationships — a diagram makes the answer 10x more useful
  • Use tables for any structured data in the answer (component lists, API endpoints, config options, comparisons)
  • If information is insufficient, say so and suggest files to examine

Rules

  • ONLY use information from actual source files
  • NEVER invent, guess, or use external knowledge
  • Think step by step before answering

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
Set up AI Runway on AKS — from bare cluster to running model. Covers cluster verification, controller install, GPU assessment, provider setup, and first deployment. WHEN: "setup AI Runway", "onboard AKS cluster", "install AI Runway", "airunway setup", "deploy model to AKS", "GPU inference on AKS", "KAITO setup on AKS", "run LLM on AKS", "vLLM on AKS", "set up model serving on AKS", "AI Runway controller".
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