A quick guide to use GitHub Copilot CLI (tested with v1.0.2) + a sample SDD (Specification-Driven Development) project
The full workshop guide is available in docs/workshop/.
Slide decks for each module are in docs/slides/ (powered by Marp):
- VS Code — Install the Marp for VS Code extension (pre-installed in Dev Container), open any slide
.mdfile, and click the preview icon (orMarp: Open Preview to the Side). - Browser (direct preview) —
npx @marp-team/marp-cli docs/slides/02-modes.md --preview - Browser (server-client) —
npx @marp-team/marp-cli docs/slides/ --serverthen visit http://localhost:8080 - Export to PDF/PPTX —
npx @marp-team/marp-cli docs/slides/02-modes.md -o slides.pdf
This repo includes a .devcontainer configuration for a fully isolated workshop environment:
- Open this repo in VS Code
- Click "Reopen in Container" when prompted (or run
Dev Containers: Reopen in Containerfrom the command palette) - All prerequisites (Node.js, npm, git, gh) are pre-installed
This is the recommended approach — it avoids polluting your host machine and ensures a consistent environment for all participants.
If you prefer not to use the Dev Container, you can follow the workshop directly on your machine (requires Node.js 22+).
To try out the workshop without affecting your local environment, use Docker:
-
Create the tryout folder (if it doesn't exist):
mkdir -p tryout
-
Start the container:
# Set HOST_PROJECT_PATH to your project location (required if running inside a devcontainer) # export HOST_PROJECT_PATH=/path/to/101-copilot-cli-sdd docker run -it \ --name copilot-workshop \ -v "${HOST_PROJECT_PATH:-$(pwd)}/tryout":/workspace \ -w /workspace \ ubuntu:24.04 \ bash
-
Inside the container, install prerequisites:
# Basic tools apt-get update && apt-get install -y curl git jq gh # Install uv (Python package manager) curl -LsSf https://astral.sh/uv/install.sh | sh source $HOME/.local/bin/env # Install nvm and Node.js LTS curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.40.1/install.sh | bash source ~/.bashrc nvm install --lts
Useful Docker commands:
| Action | Command |
|---|---|
| Reconnect to stopped container | docker start -ai copilot-workshop |
| Open parallel shell | docker exec -it copilot-workshop bash |
| Remove container when done | docker rm copilot-workshop |
This workshop uses AI-assisted development tools. We follow Microsoft's Responsible AI principles, which are grounded in six core values:
- Fairness — AI systems should treat all people fairly
- Reliability & Safety — AI systems should perform reliably and safely
- Privacy & Security — AI systems should be secure and respect privacy
- Inclusiveness — AI systems should empower everyone and engage people
- Transparency — AI systems should be understandable
- Accountability — People should be accountable for AI systems
Remember: AI is a tool, not an authority. Always review, test, and validate AI-generated code before committing. You are responsible for every line in your codebase.
For detailed guidance on applying these principles in practice, see docs/responsible-ai.md.