benchmark-sandbox

Official

Run Vercel plugin evals in sandboxes.

Authorvercel-labs
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill automates the process of evaluating the Vercel plugin within isolated, ephemeral environments, ensuring robust testing and performance analysis without impacting local development setups.

Core Features & Use Cases

  • Automated Evals: Runs Vercel plugin benchmark scenarios in Vercel Sandboxes (microVMs).
  • 3-Phase Pipeline: Executes BUILD, VERIFY (with agent-browser), and DEPLOY phases for comprehensive testing.
  • Structured Scoring: Utilizes a 'haiku' model for structured JSON scoring after each phase.
  • Use Case: Developers can automatically test how the Vercel plugin integrates with new Vercel features by running a suite of benchmark scenarios in clean, reproducible sandbox environments.

Quick Start

Run the benchmark sandbox eval with default scenarios using bun run .claude/skills/benchmark-sandbox/run-eval.ts.

Dependency Matrix

Required Modules

None required

Components

scripts

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: benchmark-sandbox
Download link: https://github.com/vercel-labs/vercel-plugin/archive/main.zip#benchmark-sandbox

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.