Build a Smarter GitHub Copilot Workflow

AI-generated code is most valuable when it follows your project's conventions. Instead of repeating coding rules in every prompt, you can store them in an instruction file. GitHub Copilot automatically uses these instructions when generating code, helping produce more consistent results across the repository.

What instruction files are

Instruction files define general project guidance, such as:

• Coding style
• Naming conventions
• Architecture preferences
• Testing requirements
• Documentation standards

Unlike prompts, instruction files do not perform actions. They simply provide persistent context for Copilot.

How to create an instruction file

1. Create a .github/instructions folder if it does not already exist.
2. Create a Markdown instruction file.
3. Add the development rules you want Copilot to follow.
4. Commit the file with your repository so the whole team benefits.

Example

# .github/instructions/coding.instructions.md

## Coding Standards

- Use C# 13 features where appropriate.
- Prefer dependency injection.
- Write XML documentation for public APIs.
- Use async/await for I/O operations.
- Add unit tests for new functionality.

Once saved, Copilot can use these guidelines whenever it generates code for your project.

Best practices

• Keep instructions concise.
• Separate unrelated topics into multiple files.
• Review them as your project evolves.
• Avoid conflicting rules.

Different folders often require different types of guidance. Documentation, tests, templates, and source code rarely follow identical rules. Custom instruction files allow you to define folder-specific behavior so Copilot adapts automatically depending on where you are working.

When to use custom instructions

Examples include:

• Documentation folders
• Assignment content
• Test projects
• Infrastructure scripts
• Sample applications

How to create custom instructions

1. Create an instruction file in the appropriate location.
2. Describe the expected structure and formatting.
3. Specify any required sections.
4. Define optional content such as starter code or examples.

Example

# assignments.instructions.md

When creating a new assignment:

- Start with a title.
- Add learning objectives.
- Include prerequisites.
- Add step-by-step instructions.
- Finish with review questions.
- Provide starter code when applicable.

Whenever Copilot generates content for assignments, it can follow these requirements automatically.

Best practices

• Keep each instruction focused on one purpose.
• Store instructions close to the content they describe.
• Update them whenever the folder structure changes.
• Avoid duplicating global project rules.

Many development activities involve repeating the same sequence of actions. Prompt files allow you to package those steps into reusable workflows that can be launched directly from Copilot Chat.

Instead of writing a long prompt every time, you simply execute the reusable prompt and let Copilot perform the workflow.

What prompt files can do

A reusable prompt can:

• Ask for missing information
• Create folders
• Generate multiple files
• Apply templates
• Update configuration files
• Reference instruction files

How to create a reusable prompt

1. Create a .github/prompts folder.
2. Create a file ending with .prompt.md.
3. Describe the workflow as numbered steps.
4. Reference templates or instruction files when appropriate.
5. Save the file.

Example

# .github/prompts/new-assignment.prompt.md

Create a new assignment.

1. Ask for the assignment topic if none is provided.
2. Create a new folder in `/assignments`.
3. Generate `assignment.md`.
4. Add starter code if required.
5. Update `config.json`.
6. Verify that all generated files are linked correctly.

You can then invoke it from Copilot Chat using:

/new-assignment

If the required information is missing, Copilot asks follow-up questions before completing the remaining steps.

Best practices

• Design prompts around complete workflows.
• Break complex tasks into numbered steps.
• Reference instruction files instead of repeating guidance.
• Keep prompts reusable rather than project-specific.
• Test prompts regularly as your project evolves.

Templates are a simple way to standardize files that are created repeatedly. Instead of asking GitHub Copilot to generate content from scratch each time, you provide a predefined file containing the desired structure, headings, placeholders, and optional example content. Copilot can then use this template as the starting point, ensuring that every generated file follows the same layout and includes all required sections.

Templates are especially useful for documentation, assignments, design documents, issue reports, meeting notes, tutorials, and many other project artifacts. By combining templates with reusable prompts and instruction files, you can automate repetitive workflows while maintaining consistent quality across your repository.

How to create a template

1. Create a folder to store reusable templates (for example, templates).
2. Create a Markdown file that contains the standard structure.
3. Replace project-specific content with placeholders.
4. Reference the template from a reusable prompt so Copilot knows when to use it.
5. Update the template whenever your standard format changes.

Example

# assignment-template.md

# {{Assignment Title}}

## Learning Objectives

- Objective 1
- Objective 2

## Prerequisites

- Requirement 1

## Instructions

1. Step one
2. Step two

## Starter Code

```python
# Add your solution here

GitHub Copilot can do more than answer general questions. With custom chat modes, you can create specialized AI experiences that guide conversations toward a specific goal. Rather than relying on a generic assistant, a chat mode defines how Copilot should respond, what tools it may use, and which rules it should follow. This makes conversations more consistent and helps the AI stay focused on the task at hand.

Chat modes are ideal for activities such as brainstorming new features, reviewing architecture, planning documentation, or coaching developers. Instead of repeatedly explaining how you want Copilot to behave, you define the behavior once and reuse it whenever needed.

How to create a custom chat mode

1. Create a .github/chatmodes directory if it does not already exist.
2. Add a new file ending with .chatmode.md.
3. Define the chat mode's metadata, including its description and available tools.
4. Describe the response structure you expect Copilot to follow.
5. Add clear rules that limit the scope and style of the conversation.
6. Save the file and select the chat mode from the Copilot Chat interface.

Example

---
description: Brainstorm ideas for new learning assignments
tools:
  - codebase
---

# Response Format

For every response:

1. Summarize the current project or codebase.
2. Suggest 3–5 new ideas.
3. Explain why each idea is valuable.
4. End with one follow-up question.

# Rules

- Keep responses concise.
- Focus on ideas, not implementation details.
- Build on existing project content.
- Always finish with a question.