Agent skills vs prompts vs MCP servers vs subagents: which one do you need?

Four words get used for “making the AI do more”, and they are not the same thing. Here is what each one is, when it’s the right choice, and how they work together — explained with one real job built all four ways.

The short answer

Prompts and skills are knowledge. MCP servers are hands. Subagents are extra workers.

Side by side

PromptSkillMCP serverSubagent
What it isText in one messageA folder with SKILL.mdA program exposing toolsA Markdown file defining a role
Who starts itYou, every timeThe AI, when the task matchesThe AI, when it needs the toolThe AI (or you) delegates to it
LastsOne chatEvery chatWhile connectedEvery session
Can carry filesNoYes — templates, scriptsIt is codeInstructions only
Reaches outside the chatNoOnly through toolsYesThrough the tools it's allowed
Own context windowNoNoNoYes
WhereAny chat appClaude app, Claude Code, API; others via the open formatAny MCP clientClaude Code
SetupPasteUpload or copy a folderPaste an address or a commandDrop a file in .claude/agents/

Each one in plain words

Prompt

The instruction you type or paste. Perfect for one-off jobs and for trying something out. Its weakness is memory: the next chat starts from zero, so anything you want every time has to be pasted every time.

Skill (agent skill)

A folder whose SKILL.md starts with a name and a description of when to use it. The AI keeps only that description in view and loads the full instructions — and any files next to them — when your request matches. It is how you stop re-explaining your process. Anthropic published the format as an open standard, which is why “agent skills” and “Claude skills” mean the same thing. More in what Claude skills are.

MCP server

The Model Context Protocol is a shared plug. An MCP server exposes tools — “search issues”, “open this URL”, “run this query” — and any AI app that speaks MCP can call them. It gives the model reach, not judgment: it can now open your pull requests, but it doesn’t know what a good review looks like. That part is a skill.

Subagent

A separate worker with its own instructions, its own tool permissions and its own context window. Your main session hands it a task and gets back a result, not the whole transcript. Use one when a job is big enough to crowd your conversation, or needs tighter permissions.

One job, four ways: a weekly SEO check

Built asWhat you doWhat you get
A promptPaste an SEO-audit prompt and the page text every MondayA decent audit — if you remember the prompt and paste the page
+ a skillInstall an SEO-audit skill onceClaude runs the same checklist every time you ask “check SEO on this page”
+ an MCP serverConnect a crawling serverClaude fetches the live pages itself instead of you pasting them
+ a subagentAdd an SEO specialist subagent in Claude CodeThe whole crawl-and-audit runs in its own context and returns a short report

Each layer removes a step you used to do by hand. The real pieces, all free on AgentAlley:

  1. 1Claude opus as SEO auditorThe prompt version — paste it with your page for a one-off audit.by Musa Toktas · CC0-1.0 · full source on the page
  2. 2SEO auditThe skill version — install once, and Claude audits the same way every time.by coreyhaines31 · MIT · full source on the page
  3. 3Firecrawl MCP ServerThe tool — lets Claude crawl and read the live site itself.by firecrawl · MIT · full source on the page
  4. 4SEO SpecialistThe specialist — a subagent role that owns the whole SEO job.by msitarzewski · MIT · full source on the page

How to choose, in four questions

  1. Will I do this once? Use a prompt.
  2. Will I do it again, the same way? Make it a skill.
  3. Does the AI need to see or change something outside the chat? Connect an MCP server.
  4. Is the job big enough to bury my conversation? Hand it to a subagent.

FAQ

What are agent skills?

Agent skills are folders of instructions — a SKILL.md file plus optional scripts and reference files — that an AI agent loads when a task matches. Anthropic introduced them for Claude and published the format as an open standard, so other agents can read the same folders.

Is a skill better than MCP?

Neither is better; they do different jobs. MCP gives the model a tool it can call. A skill tells it how to do a job, including how to use its tools well. Most real workflows use both.

Is a skill just a saved prompt?

Close, with two differences. Claude decides by itself when to load a skill, based on its description, so you don't paste anything. And a skill can bundle files — templates, examples, scripts — that a pasted prompt can't carry.

When should I use a subagent instead of a skill?

Use a subagent when the job would flood your main conversation — a long code review, a search through a large codebase — or needs different tool permissions. A subagent works in its own context and hands back a summary. A skill works inside the conversation you're in.

Do I need to code to use any of these?

No for prompts, skills in the Claude app, and hosted MCP connectors — all are paste or upload. Local MCP servers and subagents are easiest in Claude Code or Cursor.

Which one should a beginner start with?

Start with a prompt. When you catch yourself pasting the same one repeatedly, turn it into a skill. Add an MCP server when the AI needs to reach something outside the chat. Add subagents last, when sessions get crowded.

Keep going

Updated 24 September 2026.