今日热榜中文

Gemini CLI: explain code and work on files from the terminal

Explore Google Gemini CLI workflows, first tasks and setup steps, plus Agent Skills and MCP extensions.

What does it do?

Gemini CLI brings an AI assistant into the terminal to explain and generate code, work on files and help create tests. You can describe tasks in natural language rather than only using fixed commands.

Which task fits?

If you already run projects from a terminal, try exploring unfamiliar code, organizing project files or adding checks for a module. Check actual changes and command results; a generated answer alone does not establish completion.

How do you get started?

Requirements and access can vary by account and authentication method. Check current official guidance for features and limits.

  1. Follow installation guidance, check the runtime and choose a supported Google service authentication method.
  2. Start in the target project, ask about relevant files and give a task you can check.
  3. Review requested actions, edits and check output before continuing.

How do Agent Skills and MCP fit?

Agent Skills add task instructions and resources. MCP connects local or remote tools and data. These extend the assistant; this directory does not imply that each third-party project has been compatibility-tested here.

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