Awesome GitHub Copilot

Canonical version: Awesome GitHub Copilot.

Awesome GitHub Copilot (awesome-copilot.github.com) is GitHub's official, community-driven catalog of resources that extend GitHub Copilot. Maintained by GitHub with community contributions, backed by the github/awesome-copilot repository. It's the de facto marketplace for Copilot customizations across six categories:

  • Agents: custom agents for specialized Copilot experiences
  • Instructions: coding standards and best practices to feed Copilot
  • Skills: self-contained folders with instructions and resources (AI Agent Skills)
  • Plugins: curated plugins organized by theme
  • Canvas Extensions: interactive canvas apps for the GitHub Copilot App (see GitHub Copilot Canvases)
  • Learning Hub: articles and guides

Installation follows the marketplace pattern: copilot plugin install <name>@awesome-copilot, from the GitHub Copilot CLI, the Copilot app, or Visual Studio Code (VSCode). In an enterprise, GitHub Copilot Managed Settings can pin awesome-copilot as a known marketplace (or exclude it via strictKnownMarketplaces).

Canvas extensions

Around 30 canvas extensions at the time of writing, ranging from serious to playful: Artifact Explorer (browse Actions artifacts), Backlog Swipe Triage, Repository Issues Kanban, Daily Focus Board, Work Hub (cross-repo command center), Gesture PR Review (approve PRs with hand gestures), and Agent Arcade (retro mini-games). Two flagship examples by Ayan Gupta (GitHub Developer Advocate):

  • Site Studio (copilot plugin install site-studio@awesome-copilot): a shared canvas to plan, draft, and track a personal website section by section, with the agent authoring content while you watch progress and review every change
  • Java Modernization Studio / AppMod Cockpit (copilot plugin install java-modernization-studio@awesome-copilot): turns Java app modernization into a steerable dashboard with environment checks, severity-ordered assessment findings from .appmod/assessment.json, live plan checklists, CVE/test validation gates, and an autopilot mode. The canvas dispatches prompts to the agent rather than executing logic itself: "the agent does the work; the canvas reflects the result"

References


About Sébastien

Ready to get to the next level?

Found this valuable? Share it with someone who needs it.

Join 6,000+ readers. Get practical systems for knowledge & AI. Free.

Subscribe ✨

Free: Knowledge System Checklist

A clear roadmap to building your own knowledge system. Subscribe and get it straight to your inbox.

6,000+ readers. No spam. Unsubscribe anytime.

Subscribe