Back to directory

Awesome GitHub Copilot

A community-maintained collection of custom agents, instructions, skills, hooks, workflows and plugins for customizing GitHub Copilot, browsable on a companion website with search and filtering.

Awesome GitHub Copilot

Awesome GitHub Copilot organizes its resources into agents (specialized Copilot agents that integrate with MCP servers), instructions (coding standards applied automatically by file pattern), skills (self-contained folders with instructions and bundled assets), and plugins (curated bundles of agents and skills for specific workflows), plus a cookbook of copy-paste recipes for the Copilot APIs.

A companion website offers full-text search and filtering across the collection and a Learning Hub with guides covering agents, skills, instructions, hooks, agentic workflows and MCP servers. The repository also publishes a machine-readable llms.txt listing of all agents, instructions and skills for use by AI agents.

Plugins install directly through the Copilot CLI or VS Code plugin marketplace once it is registered. The collection is community-contributed, so the project advises inspecting an agent and its documentation before installing it.

More in Agent skills

See all 581
  • Provenance gate

    github.com

    A deterministic authorization gateway that sits between an AI agent and its tools, tracing where each parameter of a side-effect call came from, and blocking the call or asking a human when the source does not check out.

  • A markdown framework of system rules that restates Isaac Asimov's Four Laws of Robotics as a set of prioritized loss calculations for large-language-model agents to follow, published as a discovery file for agents and crawlers to read.

  • Vitruvius

    github.com

    An engineering research agent that runs a discover, read, synthesize, verify and review loop over technical questions, reading sources directly rather than inferring from titles, and publishing its own scored verifier benchmark, weaknesses included.