GitHub Copilot Starter

Ask the user for the following information if not provided:

1. Primary Language/Framework: (e.g., JavaScript/React, Python/Django, Java/Spring Boot, etc.)
2. Project Type: (e.g., web app, API, mobile app, desktop app, library, etc.)
3. Additional Technologies: (e.g., database, cloud provider, testing frameworks, etc.)
4. Development Style: (strict standards, flexible, specific patterns)
5. GitHub Actions / Coding Agent: Does the project use GitHub Actions? (yes/no — determines whether to generate copilot-setup-steps.yml)

Configuration Files to Create

Based on the provided stack, create the following files in the appropriate directories:

1. .github/copilot-instructions.md

Main repository instructions that apply to all Copilot interactions. This is the most important file — Copilot reads it for every interaction in the repository.

Use this structure:

2. .github/instructions/ Directory

Create specific instruction files:

• {primaryLanguage}.instructions.md - Language-specific guidelines
• testing.instructions.md - Testing standards and practices
• documentation.instructions.md - Documentation requirements
• security.instructions.md - Security best practices
• performance.instructions.md - Performance optimization guidelines
• code-review.instructions.md - Code review standards and GitHub review guidelines

3. .github/skills/ Directory

Create reusable skills as self-contained folders:

• setup-component/SKILL.md - Component/module creation
• write-tests/SKILL.md - Test generation
• code-review/SKILL.md - Code review assistance
• refactor-code/SKILL.md - Code refactoring
• generate-docs/SKILL.md - Documentation generation
• debug-issue/SKILL.md - Debugging assistance

4. .github/agents/ Directory

Always create these 4 agents:

• software-engineer.agent.md
• architect.agent.md
• reviewer.agent.md
• debugger.agent.md

For each, fetch the most specific match from awesome-copilot agents. If none exists, use the generic template.

Agent Attribution: When using content from awesome-copilot agents, add attribution comments:

5. .github/workflows/ Directory (only if user uses GitHub Actions)

Skip this section entirely if the user answered “no” to GitHub Actions.

Create Coding Agent workflow file:

• copilot-setup-steps.yml - GitHub Actions workflow for Coding Agent environment setup

CRITICAL: The workflow MUST follow this exact structure:

• Job name MUST be copilot-setup-steps
• Include proper triggers (workflow_dispatch, push, pull_request on the workflow file)
• Set appropriate permissions (minimum required)
• Customize steps based on the technology stack provided

Content Guidelines

For each file, follow these principles:

MANDATORY FIRST STEP: Always use the fetch tool to research existing patterns before creating any content:

1. Fetch specific instruction from awesome-copilot docs: https://github.com/github/awesome-copilot/blob/main/docs/README.instructions.md (opens in a new tab)
2. Fetch specific agents from awesome-copilot docs: https://github.com/github/awesome-copilot/blob/main/docs/README.agents.md (opens in a new tab)
3. Fetch specific skills from awesome-copilot docs: https://github.com/github/awesome-copilot/blob/main/docs/README.skills.md (opens in a new tab)
4. Check for existing patterns that match the technology stack

Primary Approach: Reference and adapt existing instructions from awesome-copilot repository:

• Use existing content when available - don’t reinvent the wheel
• Adapt proven patterns to the specific project context
• Combine multiple examples if the stack requires it
• ALWAYS add attribution comments when using awesome-copilot content

Attribution Format: When using content from awesome-copilot, add this comment at the top of the file:

Examples:

Secondary Approach: If no awesome-copilot instructions exist, create SIMPLE GUIDELINES ONLY:

• High-level principles and best practices (2-3 sentences each)
• Architectural patterns (mention patterns, not implementation)
• Code style preferences (naming conventions, structure preferences)
• Testing strategy (approach, not test code)
• Documentation standards (format, requirements)

STRICTLY AVOID in .instructions.md files:

• ❌ Writing actual code examples or snippets
• ❌ Detailed implementation steps
• ❌ Test cases or specific test code
• ❌ Boilerplate or template code
• ❌ Function signatures or class definitions
• ❌ Import statements or dependency lists

CORRECT .instructions.md content:

• ✅ “Use descriptive variable names and follow camelCase”
• ✅ “Prefer composition over inheritance”
• ✅ “Write unit tests for all public methods”
• ✅ “Use TypeScript strict mode for better type safety”
• ✅ “Follow the repository’s established error handling patterns”

Research Strategy with fetch tool:

1. Check awesome-copilot first - Always start here for ALL file types
2. Look for exact tech stack matches (e.g., React, Node.js, Spring Boot)
3. Look for general matches (e.g., frontend agents, testing skills, review workflows)
4. Check the docs and relevant directories directly for related files
5. Prefer repo-native examples over inventing new formats
6. Only create custom content if nothing relevant exists

Fetch these awesome-copilot directories:

• Instructions: https://github.com/github/awesome-copilot/tree/main/instructions (opens in a new tab)
• Agents: https://github.com/github/awesome-copilot/tree/main/agents (opens in a new tab)
• Skills: https://github.com/github/awesome-copilot/tree/main/skills (opens in a new tab)

Awesome-Copilot Areas to Check:

• Frontend Web Development: React, Angular, Vue, TypeScript, CSS frameworks
• C# .NET Development: Testing, documentation, and best practices
• Java Development: Spring Boot, Quarkus, testing, documentation
• Database Development: PostgreSQL, SQL Server, and general database best practices
• Azure Development: Infrastructure as Code, serverless functions
• Security & Performance: Security frameworks, accessibility, performance optimization

File Structure Standards

Ensure all files follow these conventions:

YAML Frontmatter Template

Use this structure for all files:

Instructions (.instructions.md):

Skills (SKILL.md):

Agents (.agent.md):

Execution Steps

1. Gather project information - Ask the user for technology stack, project type, and development style if not provided
2. Research awesome-copilot patterns:
   • Use the fetch tool to explore awesome-copilot directories
   • Check instructions: https://github.com/github/awesome-copilot/tree/main/instructions (opens in a new tab)
   • Check agents: https://github.com/github/awesome-copilot/tree/main/agents (opens in a new tab) (especially for matching expert agents)
   • Check skills: https://github.com/github/awesome-copilot/tree/main/skills (opens in a new tab)
   • Document all sources for attribution comments
3. Create the directory structure
4. Generate main copilot-instructions.md with project-wide standards
5. Create language-specific instruction files using awesome-copilot references with attribution
6. Generate reusable skills tailored to project needs
7. Set up specialized agents, fetching from awesome-copilot where applicable (especially for expert engineer agents matching the tech stack)
8. Create the GitHub Actions workflow for Coding Agent (copilot-setup-steps.yml) — skip if user does not use GitHub Actions
9. Validate all files follow proper formatting and include necessary frontmatter

Post-Setup Instructions

After creating all files, provide the user with:

1. VS Code setup instructions - How to enable and configure the files
2. Usage examples - How to use each skill and agent
3. Customization tips - How to modify files for their specific needs
4. Testing recommendations - How to verify the setup works correctly

Quality Checklist

Before completing, verify:

• Not done: All authored Copilot markdown files have proper YAML frontmatter where required
• Not done: Language-specific best practices are included
• Not done: Files reference each other appropriately using Markdown links
• Not done: Skills and agents include relevant descriptions; include MCP/tool-related metadata only when the target Copilot environment actually supports or requires it
• Not done: Instructions are comprehensive but not overwhelming
• Not done: Security and performance considerations are addressed
• Not done: Testing guidelines are included
• Not done: Documentation standards are clear
• Not done: Code review standards are defined

Workflow Template Structure (only if GitHub Actions is used)

The copilot-setup-steps.yml workflow MUST follow this exact format and KEEP IT SIMPLE:

KEEP WORKFLOWS SIMPLE - Only include essential steps:

Node.js/JavaScript:

Python:

Java:

AVOID in workflows:

• ❌ Complex configuration setups
• ❌ Multiple environment configurations
• ❌ Advanced tooling setup
• ❌ Custom scripts or complex logic
• ❌ Multiple package managers
• ❌ Database setup or external services

INCLUDE only:

• ✅ Language/runtime setup
• ✅ Basic dependency installation
• ✅ Simple linting (if standard)
• ✅ Basic test running
• ✅ Standard build commands