Last updated 2025-09-03

GitHub-Copilot-Jumpstart - Resources for hackers

Consider this your GitHub Copilot pot of gold to help you quickly get started using GitHub Copilot.

Start with these demo videos

From GitHub - YouTube

• Demo: end-to-end agentic development with GitHub Copilot (5:19) - Your development environment is only a couple of clicks away, requiring no local installation. GitHub Copilot coding agent does more than just suggest code - it helps you triage issues, debug and run tests, and even acts as a peer developer, building code from issues you assign. See how GitHub Copilot keeps developers focused on building!
• How to automate code reviews and testing with GitHub Copilot (4:35) - Code review and verification are just as important today as they were three years ago. GitHub Copilot can help with the process through code review and Autofix, catching both code and security flaws. Copilot lets you review its code and request changes just like you would with any other member of the team!
• Automate debugging with the Playwright MCP server (1:44) - The Playwright MCP server helps Copilot do more than just run tests. It can confirm and resolve bugs too. In this demo, we’ve shared a bug report with Copilot Agent Mode. Copilot used Playwright to reproduce the issue, confirm the bug, explore the project, find the root cause, apply the fix, and verify it worked. MCP servers expand what Copilot Agent Mode can do by giving it new skills as an AI peer programmer. Read the related blog post: How to debug a web app with Playwright MCP and GitHub Copilot

Helpful Blog Posts 

From The GitHub Blog

• 5 tips for writing better custom instructions for Copilot - If you're using GitHub Copilot in your enterprise projects, writing effective custom instructions is no longer optional—it’s essential. This guide shows how a well-crafted copilot-instructions.md file can dramatically improve Copilot’s code suggestions by giving it the context your team already knows but the AI doesn’t. Learn how to turn Copilot into a productive teammate by sharing your tech stack, coding standards, and project structure the right way.
• Prompt engineering for GitHub Copilot Chat - GitHub Docs - A prompt is a request that you make to GitHub Copilot. For example, a question that you ask Copilot Chat, or a code snippet that you ask Copilot to complete. In addition to your prompt, Copilot uses additional context, like the code in your current file and the chat history, to generate a response. Follow the tips in this article to write prompts that generate better responses from Copilot.
• A guide to deciding what AI model to use in GitHub Copilot - In this article we’ll explore a framework—including a few strategies—for evaluating whether any given AI model is a good fit for your use, even as new models continue to appear at a rapid pace.
• Beyond prompt crafting: How to be a better partner for your AI pair programmer - Learn how context-rich development environments improve Copilot’s suggestions and how to foster productive human-AI collaboration. Discover how custom instructions, prompt files and MCP servers are the keys to success when working with your AI pair programmer.
• How to use GitHub Copilot on github.com: A power user’s guide - Discover how GitHub Copilot on github.com is evolving into an AI-native control center for your entire development workflow—enabling you to create, manage, and resolve issues, prototype solutions, and collaborate with agents and colleagues, all through natural language. Learn why this shift goes far beyond coding assistance in your IDE, and how it can accelerate team productivity, streamline problem-solving, and unlock new ways to orchestrate your software projects directly within the GitHub platform.

Key Documentation

From GitHub Copilot documentation

• AI model comparison - GitHub Docs - You are not limited to using the default models for Copilot chat and code completions. You can choose from a selection of other models, each with its own particular strengths. You may have a favorite model that you like to use, or you might prefer to use a particular model for inquiring about a specific subject. See also: Comparing AI models using different tasks
• Customize GitHub Copilot Chat Responses - GitHub Copilot can provide chat responses that are tailored to the way your team works, the tools you use, or the specifics of your project. Instead of repeatedly adding this contextual detail to your chat prompts, you can create files in your repository that automatically add this information for you.
  • Repository custom instructions - Specify repository-wide instructions and preferences tailored to the way your team works, the tools you use, or the specifics of your project. For reusable examples refer to:
    • Customization library - GitHub Docs - Discover a curated collection of customizations, including custom instructions and prompt files (VS Code only), to enhance your GitHub Copilot experience.
    • Introducing the Awesome GitHub Copilot Customizations repo - The Awesome Copilot Repo is a community-driven resource with custom instructions, reusable prompts, and custom chat modes that helps you get consistent AI assistance. In other words, Awesome Copilot helps you get the most out of GitHub Copilot by letting you tailor it to your needs. And even better, the available content in the Awesome Copilot repo will grow and grow as we encourage folks to contribute instructions, prompts, and chat modes they find useful!
  • Personal custom instructions - Receive chat responses that are customized to your personal preferences, across your conversations on the GitHub website. For example, you can choose to always have Copilot Chat respond in a preferred language or with a particular style.
• Using images in Copilot Chat - You can attach images to your chat prompts and then ask Copilot about the images. For example, you can attach:
  • A mockup of the user interface for an application and ask Copilot to generate the code.
  • A flowchart and ask Copilot to describe the processes shown in the image.
  • A screenshot of a web page and ask Copilot to generate HTML for a similar page.
• About GitHub Copilot coding agent - With Copilot coding agent, GitHub Copilot can work independently in the background to complete tasks, just like a human developer. You can assign GitHub issues to Copilot, or ask Copilot to create a pull request.
• About Model Context Protocol (MCP) - Model Context Protocol (MCP) is a protocol that allows you to extend the capabilities of GitHub Copilot by integrating it with other systems. You can use MCP to extend the capabilities of Copilot Chat by integrating it with a wide range of existing tools and services. For example:
  • The GitHub MCP server allows you to use Copilot Chat in your IDE to perform tasks on GitHub.
  • Use the Playwright MCP Server for browsing the internet. Enables LLMs to interact with web pages through structured accessibility snapshots. Useful for web navigation and form-filling, data extraction from structured content, automated testing driven by LLMs, and general-purpose browser interaction for agents.
  • The Azure MCP Server allows you to manage Azure resources, enabling declarative provisioning and integration with AI workflows.

GitHub Samples

Need some additional inspiration? Check out https://github.com/github-samples. We provide a variety of sample projects and walkthroughs to help our community learn and experiment with GitHub. Explore our repositories to find examples and walkthroughs across different programming languages and frameworks and areas of the GitHub platform.