Run vercel-plugin eval scenarios in Vercel Sandboxes instead of local WezTerm panels. Provisions ephemeral microVMs with Claude Code + plugin pre-installed, runs benchmark prompts, extracts hook artifacts, and produces coverage reports.
This skill does not declare a tool allowlist. The agent host applies whatever default tools are available at runtime.
SKILL.md / Manifest
https://raw.githubusercontent.com/vercel-labs/vercel-plugin/main/.claude/skills/benchmark-sandbox/SKILL.mdRegistry
github (via claudemarketplaces.com)