Agent Skills are modular capability definitions that package domain-specific guidance, tools, and patterns for recurring agent tasks.

Subagents are narrowly scoped AI assistants that can be invoked by a primary agent to perform specific subtasks more efficiently.

Hooks are automation points tied to lifecycle events that let teams enforce checks, trigger scripts, or modify behavior around agent actions.

Slash Commands are user-invoked commands that start with a slash and execute predefined workflows, tools, or agent behaviors.

Approval Modes are policy settings that control which operations an agent can run automatically and which require explicit human approval.

Non-interactive Mode executes agent workflows in a command-driven context without live chat interactions, useful for automation and pipelines.

A canvas agent is an AI assistant that edits, refines, and structures a website directly on the design canvas while keeping the work editable.

In AI-assisted website creation, canvas agent helps teams move faster without losing control of structure, content, performance, or editable design details.

A prompt loop happens when a designer repeatedly asks an AI for changes without being able to directly edit or control the resulting design.

In AI-assisted website creation, prompt loop helps teams move faster without losing control of structure, content, performance, or editable design details.

Auto-branching automatically separates agent or team changes into branches so the original project stays clean while work is reviewed.

In collaborative Framer workflows, auto-branching helps teams move faster without losing control of structure, content, performance, or editable design details.

An agent workflow is a sequence of AI-assisted steps for planning, editing, reviewing, and shipping work in a digital project.

An agent workflow breaks complex website work into smaller actions such as scanning pages, updating CMS items, improving layout, and reviewing changes. Clear workflows help teams use AI without giving up control over quality or publishing decisions.

Conversational editing is the process of changing a website through natural-language feedback instead of direct manual edits alone.

Conversational editing lets a user describe what should change and have an agent update the project. It works best when each request names the target clearly and the agent keeps the result editable for follow-up refinements.