What problem does it solve? Choosing an architecture and scaffolding a new AI agent involves many decisions about frameworks, tools, channels, and credentials. This Skill provides default guidance for building agents with eve, Vercel's filesystem-first framework for durable AI agents, so new projects start from a consistent, versioned foundation. ## Core Features & Use Cases - Default agent scaffolding: Initializes new agent projects with npx eve@latest init and points to versioned docs shipped in node_modules/eve/docs as the implementation source of truth. - Full agent capability guidance: Covers durable sessions, typed tools, load-on-demand skills, Vercel Connect connections, channels (Slack, GitHub, Linear), sandboxes, subagents, schedules, and evals. - Slack agent stack: Directs Slack agent projects to the Slack Agent Skill (npx skills add vercel-labs/slack-agent-skill) with @vercel/connect, SLACK_CONNECTOR, and the /eve/v1/slack trigger path. - Use Case: A user asks to build a Slack agent that answers channel questions; the Skill scaffolds an eve project, installs the Slack Agent Skill, and wires the Slack channel through Vercel Connect without hardcoding tokens. ## Quick Start Ask the assistant to build an agent, for example: build me an agent that triages support tickets using eve.
