今日热榜中文

How to use this directory

Learn how MCP tools, reusable skills and editor plugins differ, how to find a project, and what to check before setup.

Start with the task

Choose MCP tools when you want an AI assistant to research, use a browser or connect to a database. Choose skills for repeatable task instructions, or editor plugins for help inside the software where you write code.

What are the three types?

MCP is a protocol for connecting AI assistants to external tools. You need an assistant that supports the tool’s connection method.

Skills provide reusable task instructions, sometimes with scripts or other files. A compatible AI assistant still needs to execute them.

Editor plugins run inside your coding editor to add chat, completions or suggested edits. Supported editors and models vary by project.

How do I find a plugin?

  1. Search a plugin name, project name or task. Search covers projects listed here, not the entire web.
  2. Narrow the list by type and use case. Update filters use the latest code push; star ranking uses all-time GitHub stars.
  3. Open an introduction to understand its purpose, intended users and requirements. Follow the setup and usage link to the project’s documentation.

What should I check before setup?

Check compatible editor or assistant versions, runtimes, model connections and required accounts in the project’s documentation. Grant external tools only the permissions your task needs.

Public source code does not make every connected service free. Models or external services may charge fees. This directory does not install plugins for you, and each project has not been installed and tested here.

Do stars measure quality?

GitHub stars indicate interest, not installs, active users or a score from this website. A popular project may still be the wrong fit for your task.

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