今日热榜中文

GitHub Copilot: AI help within your development workflow

Explore GitHub Copilot suggestions, project questions and task workflows, choose a supported entry point, and check skills and MCP support.

What does it do?

GitHub Copilot provides code suggestions, codebase answers, change review and assigned-task capabilities. It has supported editor, GitHub and terminal entry points, rather than only code completion. Features depend on the entry point and account.

Which task fits?

If you want to keep a supported editor or work around GitHub projects, try code suggestions, a file explanation or review of a focused change. Check the chosen entry point’s support before assigning a multi-step agent task.

How do you get started?

Entry points can differ. Check current account and cost guidance rather than assuming a fixed plan price.

  1. Choose your editor or GitHub workflow from official entry-point guidance.
  2. Complete sign-in and configuration and open a small task. For an organization account, check enabled features.
  3. Review suggestions, edits and actual checks before accepting them.

How do skills and MCP fit?

In supported clients, skills supply task instructions and resources, while MCP connects external systems and tools. Copilot plugins can package these capabilities. Support is not identical everywhere; check the official configuration guidance for your client.

Sources and ranking

This directory lists AI development plugins with public source code and a clear purpose. Browse by task, then open an introduction to learn what a project does, who it is for, and what you need to get started. It covers selected projects, not every AI plugin.

How do the three plugin types differ?

Tool connections (MCP) let AI assistants use external tools such as browsers, code repositories and databases. MCP is the protocol used for these connections.

Reusable skills give a compatible AI assistant instructions and guidance for a particular task.

Editor plugins run inside the software you use to write code, adding AI chat, completions or suggested edits.

How does “Most starred” work?

Projects are sorted by their total GitHub stars. Stars indicate interest; they are not downloads, active users or quality scores. A skill pack counts as one project. Daily star growth is not shown without historical records.

What does “Recently updated” mean?

It uses the most recent code push, which may not be a new release. The 7-day filter checks that project update time; ranking still uses all-time stars. Each introduction shows when its star count was collected. Failed updates keep the last saved data.

Introductions are based on public project documentation. These projects have not each been installed and tested here. Check the project documentation for setup, compatibility and service costs. Refreshing this list only reads saved data; it does not start collection.

UTC+8