Skip to content

Claude Skills, Prompts, Projects, Subagents, and MCP: A Complete Guide to Differences and Selection

To master Claude Code, understanding the differences between the five mechanisms (Skills, Prompts, Projects, Subagents, MCP) is essential. This guide explains each role and implementation steps for engineers tasked with implementing Claude in their organizations.

Target Audience

  • Individual developers and tech leads starting with Claude Code
  • Engineers and SREs tasked with Claude implementation in organizations
  • Those using ...

Summary in One Sentence Each

MechanismOne-Sentence Description
Prompts"Verbal instructions" given on the spot
Skills"Standard procedures" used repeatedly
Projects"Project folders" with documentation and history
Subagents"Specialist team members" with roles and permissions
MCP"Wiring" to connect internal systems and SaaS

Decision Criteria When in Doubt

  • One-time consultation → Prompts
  • Explaining the same procedure every time → Skills
  • Ongoing discussion about specific product/project → Projects
  • Want to separate permissions by role → Subagents
  • Need direct access to GitHub or databases → MCP

What is Skills: Procedural Manuals and Knowledge Folders

A mechanism for organizing repeatable work procedures and specialized knowledge in reusable form. It packages instructions, metadata, scripts and other resources, loading them progressively only when needed, enabling context conservation (progressive disclosure).

Use cases: Security check procedures, deployment steps, coding standard verification

First Steps

  1. Create a .claude/skills directory in your Claude Code repository root
  2. Create a file like SECURITY_REVIEW.skill.md and template "when, what code, how to check"
  3. Verify the log on the Claude Code side until the Skill is actually invoked

Common Mistakes

Creating too many Skills becomes unmanageable. Start with 3-5 and only promote procedures you actually repeat

What is Prompts: One-Time Instructions

One-time instructions given directly in conversation. Execute immediately with flexible instructions, but aren't saved.

Use cases: "Rewrite this code for Python 3.12 compatibility", "Create 3 test cases for this function"

First Steps

  • Start with Prompts only, and promote to Skills when you notice repeating the same explanation

Key Point

Consider promoting to Skills or Projects when repeating the same task 3+ times

What is Projects: Workspace with Knowledge Base

A workspace that maintains project-specific knowledge and context. Preserves conversation history and context for referencing past decisions in long-term development. Features 200K context + RAG integration to extend project knowledge.

Use cases: API specification management, design document storage, implementation discussion history

First Steps

  1. Create a Project from Claude's left menu
  2. Upload only 3-5 specifications/README/design documents used in that project
  3. Add just one instruction like "This project prioritizes ◯◯ perspective" and test behavior

Common Mistakes

Throwing everything into Projects reduces searchability. Focus only on highly relevant materials

What is Subagents: Mechanism for Task Division as Specialist Teams

A mechanism for combining multiple AI agents specialized in specific domains. Each has independent context and tool permissions, functioning not as mere "role labels" but as units of permission design.

Use cases: Frontend/backend/testing division of labor, parallel development of complex features

First Steps

  1. When using Claude Code, create one Subagent just for test execution or static analysis
  2. Set limited permissions to prevent unexpected behavior
  3. Review operation logs and adjust permission design

Common Mistakes

Creating too many granular Subagents makes behavior unpredictable. For simple tasks, a single Prompt is more efficient

What is MCP: Connection Layer to External Systems

A connection layer for integrating with external databases and APIs. Enables integration with external data and systems Claude alone cannot access. As an open standard, it can be used from clients other than Claude and consolidates integration with multiple tools into a single protocol.

Use cases: GitHub API integration, database access, cloud service integration

First Steps

  1. Install just one official MCP server (e.g., @modelcontextprotocol/server-filesystem)
  2. Add server information to Claude Code configuration file
  3. Start with simple file operations

Common Mistakes

Connecting everything to MCP causes governance breakdown. Start with read-only access

Comparing the Five Mechanisms

What They Preserve / How Long They Persist

MechanismWhat It PreservesHow Long It Persists
PromptsOne conversation turn of contextWithin one chat only
SkillsProcedures, know-how, scriptsReusable across all projects
ProjectsDocuments, history, settingsContinuous per project
SubagentsRole prompts + permissionsContinuous per agent
MCPConnection definitionsContinuous between server/client

Selection by Scenario

ScenarioRecommended Mechanism
One-time questionPrompts
Repetitive taskSkills
Long-term projectProjects
Complex task divisionSubagents
External system integrationMCP

These mechanisms can be combined. You can incorporate Skills into Projects, fetch external data with MCP, and execute parallel work with Subagents.

Where to Start: Implementation Steps

  1. Step 1: Start with Prompts only Use chat + Projects to identify repetitive tasks

  2. Step 2: Promote repetitive tasks to Skills Identify long prompts you type repeatedly and promote them to Skills

  3. Step 3: Separate long-term/team projects with Projects Consolidate specifications, README, design documents to maintain project-specific context

  4. Step 4: Implement permission separation/parallelization with Subagents Create one Subagent just for test execution or static analysis to learn permission design

  5. Step 5: Connect internal systems/external SaaS with MCP Connect existing GitHub/DB/SaaS via MCP and integrate into "production workflow"

Summary

By understanding when to use each of the five mechanisms, you can efficiently leverage Claude Code. Start with simple Prompts, promote repetitive tasks to Skills, and utilize Projects and MCP as your project grows.

Official Documentation