Build advanced, repeatable GitHub Copilot CLI workflows from review and debugging through end-to-end delivery.
-
Who is this for: Advanced developers who already use GitHub, pull requests, and Copilot fundamentals.
-
What you'll learn: How to run high-signal Copilot CLI workflows with specialization, skills automation, MCP context, and complete PR execution.
-
What you'll build: A reusable Copilot CLI workflow scaffold with instruction files, skill definitions, MCP configuration, and PR-ready artifacts.
-
Prerequisites:
- Completion of GitHub Copilot CLI beginner content.
- Working knowledge of pull requests, branching, and GitHub Actions.
- Ability to run Copilot CLI locally and push commits to GitHub.
- Familiarity with JSON/YAML configuration and API concepts.
-
How long: This exercise takes less than 90 minutes to complete.
In this exercise, you will:
- Use Copilot CLI for advanced code review, debugging, and test generation workflows.
- Create specialized assistant behavior with repository custom instructions.
- Automate repetitive engineering tasks with reusable Copilot CLI skills.
- Connect Copilot CLI to external context using MCP servers.
- Deliver a complete, review-driven feature workflow that combines all capabilities.
Simply copy the exercise to your account, then give your favorite Octocat (Mona) about 20 seconds to prepare the first lesson, then refresh the page.
Having trouble? 🤷
When copying the exercise, we recommend the following settings:
-
For owner, choose your personal account or an organization to host the repository.
-
We recommend creating a public repository, since private repositories will use Actions minutes.
If the exercise isn't ready in 20 seconds, please check the Actions tab.
-
Check to see if a job is running. Sometimes it simply takes a bit longer.
-
If the page shows a failed job, please submit an issue. Nice, you found a bug! 🐛