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.

skills.sh installs: 193
GitHub stars: 183
last updated: Jun 3, 2026

View on GitHub

Install

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

Installs into .claude/skills of the current project.

Files

Benchmark Testing

Create isolated test projects that exercise vercel-plugin skill injection with realistic, technology-agnostic prompts.

Workflow

1. Create test directories

BASE=~/dev/vercel-plugin-testing
mkdir -p "$BASE"/{01-slug,02-slug,...}

2. Install the plugin in each directory

for dir in "$BASE"/*/; do
  echo "=== $(basename "$dir") ==="
  cd "$dir" && npx add-plugin https://github.com/vercel/vercel-plugin -s project -y 2>&1 | tail -1
done

This creates .claude/settings.json with enabledPlugins in each directory.

3. Launch Claude Code in WezTerm panes

Critical details that must all be followed:

Use --cwd <absolute-path> to set the working directory
Use unset CLAUDECODE before x to avoid nested-session errors
Use --settings .claude/settings.json (not --settings project) to load the plugin
Use double quotes on the outer -ic string, single quotes around the prompt
Wait 10 seconds between each launch to avoid overwhelming the system
Always use spawn (new tabs) — split-pane runs out of space after ~4 panes