Matt Pocock's skills
Security scan passedMatt Pocock's everyday engineering skills: grilling sessions, specs and tickets, TDD, bug diagnosis, code review and writing for agents.

By GitHub
GitHub’s AI coding agent in your editor, terminal, GitHub and the Copilot app
GitHub Copilot is GitHub's AI coding agent. It works in your editor (VS Code, Visual Studio, JetBrains IDEs and more), in the terminal with Copilot CLI, on GitHub as a cloud agent that works on tasks in the background and opens pull requests, and in the GitHub Copilot desktop app. On paid plans you can also assign tasks to third-party agents such as Claude and Codex. What you can add - MCP servers, hosted or local: in VS Code with an Add to VS Code link or mcp.json, or in Copilot CLI with `copilot mcp add` (saved to ~/.copilot/mcp-config.json). Hosted servers can take headers such as an API key. Organizations can control which servers are allowed. - Agent Skills: folders with a SKILL.md in ~/.copilot/skills or ~/.agents/skills, or .github/skills, .claude/skills or .agents/skills in a repository. - Plugins in the Agent Plugins open standard or Copilot's own format, which also reads Claude plugin manifests. Install them from marketplaces such as copilot-plugins, awesome-copilot and Anthropic's claude-code with `copilot plugin install`, or in the GitHub Copilot app and VS Code. How it connects In your editor and Copilot CLI, it starts local servers on your computer and reaches hosted ones over the internet. Plans Free to start. Pro, Pro+, Max, Business and Enterprise plans add the cloud agent, code review and more usage.
The plugin and skill formats this agent installs.
listings install here.
Nobody has shared how they use GitHub Copilot yet.
No reviews yet. Used GitHub Copilot? Say how it went.
Write a review694 listings install here.
Matt Pocock's everyday engineering skills: grilling sessions, specs and tickets, TDD, bug diagnosis, code review and writing for agents.
Skills that make your coding agent brainstorm, plan, test-drive, debug and review its work before it calls the job done.
Quality audit of a whole repo: bugs, security holes, what breaks under real load, risky code without tests, slow paths,…
List every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger.
Show ponytail's measured savings (code, cost, speed) from the benchmark.
Quick reference for ponytail levels, skills and commands.