What problem does it solve? Choosing an architecture and scaffolding a new AI agent involves many decisions about frameworks, session durability, tools, and channel integrations. This Skill provides default guidance for building agents with eve, Vercel's filesystem-first framework for durable AI agents, so you start from a proven structure instead of assembling one from scratch. ## Core Features & Use Cases - Agent Scaffolding: Initializes new eve agent projects via npx eve@latest init and points to versioned docs shipped in node_modules/eve/docs as the source of truth. - Slack Agent Stack: Defines the expected Slack stack — eve runtime, @vercel/connect for credentials and webhook verification, SLACK_CONNECTOR, and the /eve/v1/slack trigger path — and defers to the Slack Agent Skill for setup wizards. - Clear Boundaries: Prevents misuse of Vercel Agent (reserved for code review and incident investigation), avoids duplicating the Slack Agent Skill, and forbids hardcoding credentials or provider API keys. - Use Case: Ask to build a Slack agent that answers channel questions, and the Skill guides scaffolding an eve project with Vercel Connect handling Slack auth instead of manually wiring Bolt or Chat SDK. ## Quick Start Ask the assistant to build an agent, for example: build me an agent that triages support tickets using eve.
