“Vercel”

Update the primary SDK dependencies of harness packages.

Create or edit package README.md files in the AI SDK monorepo.

Write, edit, review, or audit user-facing documentation for the eve repository.

Capture API response test fixture.

Guide for adding new AI function examples, for testing specific features against the actual provider APIs.

Build durable backend AI agents with the eve framework.

Drafts and reviews GitHub pull request descriptions for the eve repository.

Takes a finished eve branch from review to merge.

Find an eve Agent Run from a run ID, project, request reference, or approximate time using authorized evidence available to the consumer.

Investigate a specific issue report with strict, evidence-driven diagnosis.

Comprehensive security and correctness audit.

Fill and validate the billing desk's PDF forms, such as refund authorizations.

How to triage an account and verify packaged skill resources with the toolkit CRM extension.

The consuming agent's own guide skill.

When and how to escalate a support case to engineering.

Review docs/prose for Writing Guidelines compliance.

How to be rescued from a lonely island

Invoke whenever writing, changing, reviewing, or sweeping tests in the eve repository.

CLAUDE.md from vercel/next-devtools-mcp: 136 lines covering Project Overview, Build and Development Commands, Testing, Architecture and more.

Backend architecture guidance.

eve framework guidance for durable AI agents and agent-powered applications.

Score how ready a website, domain, or public MCP endpoint is for AI agents using Is Agentic, and read or act on the resulting report.

Default guidance for building AI agents.

Review UI code for Web Interface Guidelines compliance.