Capabilitiesagent skillsskill files

What Are Agent Skills?

Agent skills are packaged expertise — usually Markdown playbooks — that an AI agent loads when a task needs domain knowledge, separate from the tools it uses to take action.

2 min readUpdated skills.md

Skills are packaged expertise an AI agent can load when a task needs specific know-how. Unlike tools (which do things), skills teach the agent how to approach a class of work — policies, checklists, writing standards, domain procedures.

In modern agent frameworks, skills often live as Markdown files the runtime injects into context only when relevant. That keeps the default prompt lean while still giving the agent deep guidance on demand.

Skills vs. tools

SkillsTools
PurposeWhat the agent knows / how it should workWhat the agent can execute
FormInstructions, playbooks, examplesAPIs, functions, code
LoadedWhen the task matchesWhen the model decides to act
ExampleRefund policy checklistissue_refund API call

A support agent might load a "billing dispute" skill, then call tools to look up the invoice and draft a reply. The skill shapes judgment; the tools change state.

Why skills matter in a blueprint

Deciding what belongs in skills versus tools versus the system prompt is an architecture choice. Overloading the base instructions with every procedure burns context. Putting judgment rules into opaque code makes them hard to review. Skills keep expertise readable and modular — founders and operators can edit them without touching the runtime.

See Tool Use for actions, and Prompt Engineering for how instructions shape behavior.

Blueprint

Your agent starts with a blueprint.

Map the role, tools, and handoffs in plain English — then hand it to a developer or a coding agent.

Build yours free →
Blueprint·Dwg-cta·Rev 01