Glossary
Terms used in the guides and notes.
Agent skill
A folder of instructions and optional supporting files that teaches an agent how to carry out a specific, repeatable task.
AGENTS.md
A plain-Markdown file of repository-wide working instructions that several coding agents read at the start of a session.
Frontmatter
The YAML block between opening and closing --- lines at the top of SKILL.md that carries a skill's metadata.
MCP server
A Model Context Protocol endpoint or process that exposes tools, resources or prompts an agent can call.
Plugin manifest
The metadata file that identifies a plugin package and, depending on the host, the components it bundles.
Plugin marketplace
A catalog or distribution source where users find and install plugin packages for a given host.
Progressive disclosure
Loading a skill's metadata first, its full instructions on activation, and any supporting files only when needed.
Skill activation
The point when an agent judges a discovered skill relevant and loads its instructions into the current task.
SKILL.md
The required Markdown file that defines a skill's name, description and instructions.
Subagent
A separately run agent, given a bounded task and its own working context, that returns a result to whoever delegated it.