Agents & tools · Glossary term
What is Agent Skill?
A discoverable directory of procedural instructions whose entry point is `SKILL.md`, with optional references, scripts, and assets that a compatible runtime can load in stages.
Why does Agent Skill matter?
It packages reusable task knowledge separately from one conversation while keeping deeper context and deterministic helpers available on demand.
Agent Skill in practice
Publish a compact name and routing description, load the workflow only after activation, and read branch-specific references when the task reaches them.
What is the common confusion about Agent Skill?
Activating a skill supplies context. It does not expose a tool, grant permission, create a sandbox, or prove that the resulting work is correct.
Learn Agent Skill in the course
Start with
- Agent Skills: Portable Contract and Runtime Boundary
A skill is not a long prompt with a better filename. It is a discoverable package of instructions, resources, and executable helpers that enters an agent's context through a runtime contract.
Taught in Phase 13: Tools & Protocols.
Related terms
- Skill BundleThe complete installable skill directory, including `SKILL.md` and every reference, script, asset, fixture, or companion file required by…
- Skill CatalogThe compact model-visible inventory of eligible skills, usually containing routing metadata such as name, description, and an internal…
- Skill InvocationThe runtime-mediated process in which an eligible human, model, application, or other skill selects a skill and causes its instructions to…
- Progressive DisclosureSupplying a person or model with the minimum useful context first, then revealing deeper detail when the task or evidence requires it.
- MCP (Model Context Protocol)An open JSON-RPC protocol for a host to connect to servers that expose tools, resources, prompts, and extensions through defined request,…
Sources
More terms in Agents & tools
- Agent
- Agent Harness
- Agent Memory
- Agent State
- Approval Gate
- Checkpoint
- Compensating Action
- Delegation
- Durable Execution
- Function Calling
- Human-in-the-Loop (HITL)
- MCP (Model Context Protocol)
- Multi Round-Trip Request (MRTR)
- Orchestration
- Planning
- ReAct
- Sandbox
- Skill Bundle
- Skill Catalog
- Skill Discovery
- Skill Invocation
- Stateless MCP
- Structured Output
- Swarm
- Termination Condition
- Tool Contract
This entry comes from glossary/terms.md on GitHub. Browse all 250 glossary terms.