github/awesome-copilot is the GitHub-blessed awesome list for the Copilot ecosystem — a community-curated catalog of skills, prompts, custom instructions, MCP server integrations, and workflow patterns for developers using GitHub Copilot. The repo functions as the canonical entry point for new Copilot users who want to skip the trial-and-error phase and pick up patterns the community has already validated. As GitHub Copilot evolves toward agent-mode and custom instructions, this list is becoming the durable reference for how the wider community is actually using the product. Trending in May 2026 alongside mattpocock/skills and obra/superpowers as the skill-bundle category becomes a first-class part of the AI-coding stack.
github/awesome-copilot is the GitHub-curated awesome list for the Copilot ecosystem. It catalogs skills, prompts, custom instructions, MCP integrations, and workflow patterns that the wider Copilot community has converged on. Maintained inside the github organization, it functions as the canonical reference for Copilot best practices.
In May 2026, skill bundles dominate GitHub trending. Five of the top fifteen trending repos that week are skill/prompt catalogs: mattpocock/skills, obra/superpowers, anthropics/skills, and now awesome-copilot from GitHub itself. The signal: skill catalogs are no longer a side project; they are part of the official tooling story for every major AI-coding platform.
Browse the README for the section closest to your workflow. Copy patterns into your local ~/.copilot/ or VS Code settings. Submit a PR to add validated patterns of your own.
AI agents that work well with Awesome Copilot.
Production-grade engineering skills for AI coding agents — addyosmani's curated bundle covering Claude Code, Cursor, and Antigravity workflows.
100+ ready-to-use Claude Code agents, commands, hooks, and integrations — installable via CLI or interactive dashboard at aitmpl.com.
Injects up-to-date, version-specific documentation into LLM context — eliminates hallucination from stale training data.