GUIDE.02 / CHOOSE THE RIGHT AGENT LAYER

AI Agent Skills vs prompts vs MCP:
method, request, and capability.

These terms are often treated as substitutes. They are different layers: a prompt starts a request, a skill supplies a reusable method, MCP connects capabilities and data, and an agent coordinates the work. The useful question is not which one wins—it is which layer your job is missing.

PROMPT
REQUEST
SKILL
METHOD
MCP
CAPABILITY
AGENT
COORDINATION
01 / FOUR LAYERS

Each layer solves a different operating problem.

A reliable setup keeps the boundaries visible. Adding more instructions cannot create a missing system connection, and adding a tool cannot supply a sound decision method.

PROMPT

Express the current request

SCOPE
Conversation or task
PERSISTENCE
Usually one run
PROVIDES
A clear brief, question, constraint, or revision
Use when the method is simple or already shared.
SKILL

Preserve a reusable method

SCOPE
Skill directory
PERSISTENCE
Across recurring jobs
PROVIDES
Triggers, steps, evidence rules, templates, and boundaries
Use when quality depends on following the same reviewable procedure.
MCP / TOOL

Provide data or action

SCOPE
Connected system
PERSISTENCE
While authorized
PROVIDES
Search, files, analytics, CRM, publishing, or another operation
Use when the job needs access the model does not already have.
AGENT

Coordinate the execution

SCOPE
Working session
PERSISTENCE
Across multiple steps
PROVIDES
Planning, delegation, tool calls, state, and handoffs
Use when the job must adapt and move through several decisions.

A common production pattern is: prompt = job brief; skill = operating method; MCP = approved access; agent = coordinator; human = accountable decision owner.

02 / DECISION TEST

Diagnose the missing layer before adding complexity.

Start with the smallest layer that removes the actual failure. Combine layers only when the job requires them.

  1. 01
    The request changes every time

    State the deliverable, audience, evidence, constraints, and acceptance criteria for this run.

    Write a better prompt
  2. 02
    The job repeats but quality drifts

    Package the stable procedure, source rules, checkpoints, output template, and stop conditions.

    Create or install a skill
  3. 03
    The method is sound but data is missing

    Grant only the access needed, then keep the skill responsible for how that capability is used.

    Add an approved MCP connection or tool
  4. 04
    The job crosses several systems and decisions

    Let the agent sequence work while people retain claims, approvals, commitments, and irreversible actions.

    Use an agent to coordinate
03 / CHINA LAUNCH EXAMPLE

One launch job uses all four layers without confusing them.

Imagine a global B2B team preparing a China market launch. The layers work together, but each remains independently reviewable.

PROMPT

Set this launch brief

Specify the market, buyer, deadline, source material, decision, and required output.

SKILL

Control the method

Use competitor research, positioning, localization, campaign brief, and retrospective workflows with evidence gates.

MCP / TOOL

Retrieve approved evidence

Read current files, analytics, or CRM data only through connections the organization has reviewed.

AGENT + HUMAN

Run and govern the sequence

The agent preserves handoffs; named owners approve market claims, brand commitments, and external actions.

04 / FAILURE MODES

Four substitutions that create fragile systems.

Most confusion appears when one layer is forced to perform another layer's job.

LONG PROMPT ≠ SKILL

A long prompt may contain a method, but it is harder to discover, version, inspect, and reuse as an operating asset.

SKILL ≠ ACCESS

Instructions cannot retrieve private data or publish content unless an approved tool and permission provide that capability.

MCP ≠ JUDGMENT

A connection can fetch or change data; it does not define the evidence standard, review method, or business decision.

AGENT ≠ OWNER

Autonomous execution does not transfer accountability for claims, privacy, legal review, commitments, or irreversible actions.

05 / FAQ

Common questions about AI Agent Skills, prompts, and MCP.

01Should I turn every prompt into a skill?

No. Keep one-off or simple requests as prompts. Create a skill when the task recurs and quality depends on a stable method, evidence rule, template, or boundary.

02Does a skill need MCP?

No. Many skills work with user-provided files or public information. Add MCP or another tool only when the job needs approved access or an external action.

03Is MCP a replacement for an API?

MCP is a protocol for exposing tools and context to AI applications. The connected server may still use product APIs underneath; permission and source review remain necessary.

04Can the same skill work in different agents?

Often, if the hosts support compatible Agent Skills conventions. Discovery paths, invocation, reload behavior, and permissions can still differ by host.

NEXT / APPLY THE MODEL

Pick a method, then install it for the host you use.

Browse the practical guide, inspect the skill library, or open the host-specific installation path for Codex, Claude Code, or Cursor.