The AI agent ecosystem in plain language, what each piece is and how it fits with the rest.
An MCP server is a small program that exposes tools, data and actions to an AI agent over the Model Context Protocol, so the agent can do things like query a database, browse the web or open a pull request.
An agent skill is a reusable instruction set that teaches an AI agent how to perform a specific task, packaged so you can install it with one command and have the agent pick up the capability.
An AI agent is a system that uses a language model to plan and take actions toward a goal, calling tools, reading results and deciding the next step in a loop, rather than just answering a single question.
An AI workflow is a chain of steps, often several model calls and tools wired together, that turns an input into a finished output, with checkpoints where a human can review along the way.
A prompt template is a reusable, parameterised instruction for a language model, a proven wording you fill in and reuse, rather than writing the prompt from scratch each time.
The Model Context Protocol (MCP) is an open standard for connecting AI agents to external tools and data through a common interface, so any compatible client can use any compatible server.
Claude skills are reusable instruction sets — SKILL.md files — that teach Claude Code and other Claude-powered agents how to do a specific task, installed with one command so the agent picks up the capability automatically.
SKILL.md is the plain-markdown file that defines an agent skill: a short description of when the skill applies plus the instructions the agent should follow, in the format Claude Code and other skills-compatible agents read.