Glossary
Key terms and definitions for AI agent development, Gemini skills, and the SKILL.md ecosystem.
Agent Skills
Discrete capabilities that an AI agent can invoke to perform specific tasks within a workflow.
SKILL.md
A markdown file format used to declare an agent skill's interface, triggers, and behavioral contract.
MCP (Model Context Protocol)
An open protocol that standardizes how AI models discover and invoke external tools and data sources.
ReAct Loop
A reasoning-and-acting cycle where an AI agent alternates between thinking about a problem and taking actions to solve it.
Antigravity CLI
A command-line tool for scaffolding, testing, and deploying AI agent skills and workflows.
Token Context Window
The maximum number of tokens a language model can process in a single request, encompassing both input and output.
Chain of Thought
A prompting technique that encourages a language model to show its intermediate reasoning steps before arriving at a final answer.
Few-Shot Prompting
A technique where a small number of input-output examples are included in the prompt to guide the model's behavior.
Multi-Agent Orchestration
A design pattern where multiple specialized AI agents collaborate, delegate, and coordinate to complete complex tasks.
RAG (Retrieval Augmented Generation)
A technique that enhances language model responses by retrieving relevant documents from an external knowledge base before generating an answer.
Function Calling
A model capability that allows it to output structured requests to invoke predefined functions or tools rather than only generating text.
Structured Output
A technique for constraining a language model's response to conform to a specific schema such as JSON, ensuring machine-parseable results.