今日热榜中文

How to choose an AI development tool

Understand Codex, Claude Code, Gemini CLI, Cursor and GitHub Copilot. Choose an assistant for your workflow, then add compatible skills or MCP tools.

Choose an assistant before adding plugins

An AI development tool is where you give tasks and review the results. Skills supply reusable task instructions; MCP connects assistants to external tools. A compatible assistant still needs to use them, so start with how you want to work.

Prefer working in a terminal?

A terminal is the window where you run project commands. Codex, Claude Code and Gemini CLI provide terminal workflows for understanding code, making changes and running checks. Each also has its own other entry points or extension options.

Want to review changes in an editor?

Cursor provides its own AI editor and coding agent. GitHub Copilot works in supported editors and GitHub surfaces. Codex and Claude Code also have editor entry points; consider whether you want to keep your existing workflow.

Decide with a small task

These introductions use official documentation, not installation tests or scores from this website. Available features, models and costs depend on current official guidance and your account.

  1. Pick a task whose result you can check, such as explaining a function, fixing a known error or adding tests for a module.
  2. Check account access, entry points, permissions and setup requirements, then follow the official guide.
  3. Review the changes and check results before deciding to continue or add plugins.

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