Benchmark Testing

If you're building or testing a plugin system that injects skills into Claude Code sessions, this automates the tedious part: spinning up multiple isolated test projects, installing your plugin in each, and launching separate WezTerm tabs with crafted prompts. The workflow emphasizes technology-agnostic prompts that describe products rather than naming frameworks, so you can see which skills your plugin actually triggers. It includes working command templates with all the gotchas (unset CLAUDECODE, use spawn not split-pane, wait 10 seconds between launches) and nine example prompts ranging from recipe platforms to dog walking SaaS. Useful if you're doing QA on skill injection logic and need reproducible test harnesses instead of manual tab juggling.

Install to Claude Code

npx -y skills add vercel-labs/vercel-plugin --skill benchmark-testing --agent claude-code