awesome-copilot

Community made agents, instructions, skills, hooks, workflows, and plugins for GitHub Copilot, organized on a searchable website with a Learning Hub.

The repository gathers community contributed instructions, agents, skills, and configurations for GitHub Copilot, described in one line as custom agents, instructions, skills, hooks, workflows, and plugins. A long list of named contributors is printed in the README, which fits a project that lives on community input. The repo is listed with Python and the MIT license, and the site lives at awesome-copilot.github.com.

The website offers full text search and filtering across hundreds of resources, plus a Learning Hub for guides and tutorials. For AI agents there is a machine readable llms.txt file with structured listings of all agents, instructions, and skills. The llms.txt file is meant for machines, the website for people, and the two cover the same ground. The Learning Hub covers core concepts like agents, skills, and instructions, then moves into hooks, agentic workflows, MCP servers, and the Copilot coding agent.

Agents are specialized Copilot agents that integrate with MCP servers. Instructions are coding standards applied automatically by file pattern. Skills are self-contained folders bundling instructions and assets. Plugins are curated bundles of agents and skills, and a cookbook section provides copy paste ready recipes for working with Copilot APIs.

For most users the marketplace is already registered in the Copilot CLI or VS Code, so plugins install directly. Older setups that do not recognize the marketplace need to register it once. The README is blunt about provenance: customizations come from third party developers, so any agent and its documentation should be inspected before installing.

• Source 1 · Project repository
• Source 2 · README