Copilot 应用入门：指令、技能与 MCP 配置
GitHub 博客发布面向初学者的教程，介绍如何让 GitHub Copilot 应用理解自己代码库的约定与流程。文中给出四种做法：用 .github/copilot-instructions.md 以及 .github/instructions 下带 applyTo 的路径级文件写自定义指令；用 .github/skills 下含 SKILL.md（可附脚本）的文件夹把可重复流程打包成 Agent Skills；用 .github/agents 定义可承担跨文件更大任务的 custom agent；以及通过 MCP 服务器把 Copilot 连接到外部工具和数据，例如用 Playwright 在浏览器中实际操作并验证应用。文章还建议先挑一条常被重复解释的约定开始，并提到社区仓库 Awesome Copilot 提供现成的指令、技能与智能体可供参考和改写。
对日常使用 Copilot 的开发者来说，把项目约定写进仓库能减少反复说明与纠正；这也说明上下文配置正在成为 AI 编程工具的常规用法。
Context matters when you’re working with AI. Every codebase has its own house rules: how components are structured, which scripts to run, and which conventions apply to different frameworks and file types.
Copilot can help you make changes across a project, but it works best when it knows those rules, too. Much of that knowledge can live inside the repository, so Copilot can pick it up automatically instead of requiring you to explain the same standards, scripts, and workflows every time you start a new task.
In this installment of our GitHub Copilot app for Beginners series, we’ll look at four ways to tailor how Copilot works with your project:
- Custom instructions communicate the conventions Copilot should follow.
- Agent skills package repeatable procedures.
- Custom agents bring specialized guidance to larger tasks.
- Model Context Protocol (MCP) servers connect Copilot to external tools and data sources, expanding what it can do.
Let’s look at how each one works and how they can work together.
#GitHub#GitHub Copilot#Model Context Protocol#Playwright#Awesome Copilot