GitHub Copilot

Getting code suggestions in your IDE with GitHub Copilot

Key Combination	Action
`Tab`	Accept the suggestion
`Option (⌥) or Alt` + `]`	See next suggestion
`Option (⌥) or Alt` + `[`	See previous suggestion
`Ctrl` + `Enter`	Show multiple suggestions in a new tab
`Command` + `→`	Accept Next Word

Smart actions: To submit prompts via the context menu, right click in your editor, select Copilot in the menu that appears, then select one of the actions. Smart actions can also be accessed via the sparkle icon that sometimes appears when you select a line of code.

AI-powered chat conversations with GitHub Copilot
@workspace has context about the code in your workspace and can help you navigate it, finding relevant files or classes.
@vscode knows about commands and features in the VS Code editor itself, and can help you use them.
@terminal has context about the integrated terminal shell and its contents.
@github has knowledge about your GitHub repositories, issues, pull requests, and topics, and can also perform web searches using the Bing API.

Extensions can also contribute chat participants to provide specialized help for their domain. You can install these extensions from GitHub Marketplace and from Visual Studio Code Marketplace.

Command	Description
`/explain`	Explain the selected code
`/fix`	Propose a fix for problems in the selected code
`/tests`	Generate unit tests for the selected code
`/new`	Scaffold code for a new workspace or new file
`/clear`	Start a new chat

AI-powered chat conversations with GitHub Copilot
#codebase: the contents of the current workspace. It includes information about the files and folders in your workspace, as well as any settings or configurations specific to that workspace.
#file: Include a specific file as context in the chat.
#selection: the visible source code in the active editor.
#terminalLastCommand: the active terminal’s last run command.
#terminalSelection: the active terminal’s selection.
#editor: the code in the active editor. The editor content is implicitly included in the Chat view context.
#vscodeAPI: use VS Code API references to answer questions about VS Code extension development.

Prompt engineering for GitHub Copilot - GitHub Docs
Start general, then get specific
Give examples
- Unit tests can also serve as examples. Before writing your function, you can use Copilot to write unit tests for the function. Then, you can ask Copilot to write a function described by those unit tests.
Break complex tasks into simpler tasks
Avoid ambiguity
Indicate relevant code
- open any relevant files and close irrelevant files
Experiment and iterate
Keep history relevant
Follow good coding practices
- Use Copilot to help your code follow best practices. For example, ask Copilot to add comments or to break a large function into smaller functions.
Using extensions to integrate external tools with Copilot Chat - GitHub Docs
Example prompts for Copilot Chat - GitHub Docs
Refactoring code with GitHub Copilot - GitHub Docs