benchmark-testing

Set up isolated directories, install vercel-plugin, and run Claude Code with prompts.

Updated Dec 12, 2025
One-click install
npx skills add https://github.com/global-os/gproxy --skill benchmark-testing-global-os
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: benchmark-testing
Source: https://github.com/global-os/gproxy/tree/main/.agents/skills/benchmark-testing
Command: npx skills add https://github.com/global-os/gproxy --skill benchmark-testing-global-os

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill addresses the need for testing vercel-plugin skill injection across realistic scenarios, allowing users to create and launch benchmark test projects to ensure functionality and performance.

Core Features & Use Cases

  • Isolated Test Projects: Sets up isolated directories for each test scenario.
  • Plugin Installation: Installs the vercel-plugin into each directory.
  • WezTerm Panes: Spawns WezTerm panes running Claude Code with crafted prompts.
  • Use Case: It helps developers test how their vercel-plugin interacts with Claude Code under various prompts, ensuring that the plugin functions correctly in different contexts.

Quick Start

Use the benchmark-testing skill to create a new test project and launch Claude Code with a prompt.

Frequently Asked Questions about benchmark-testing

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I test vercel-plugin skill injection across different scenarios?

To test vercel-plugin skill injection, you can use benchmark testing to set up isolated directories, install the plugin, and execute Claude Code with specific prompts to evaluate behavior under various operational conditions.

What is the best way to simulate realistic test scenarios for Claude Code plugins?

Simulating realistic test scenarios for Claude Code plugins involves launching WezTerm panes running the application with crafted prompts within isolated test project directories to ensure accurate functionality and performance evaluation.

Do I need Claude Code and vercel-plugin installed to run benchmark tests?

Yes, executing benchmark test scenarios requires both Claude Code and the vercel-plugin to be present in your environment, as the testing process relies on injecting the plugin into isolated directories and running the code.

Can I run multiple isolated test projects for vercel-plugin simultaneously?

Yes, the benchmark testing process sets up isolated directories for each test scenario and spawns WezTerm panes, allowing you to monitor multiple isolated test projects running concurrently with distinct prompts.

Why does my vercel-plugin behave differently across various Claude Code prompts?

Vercel-plugin behavior varies across Claude Code prompts because skill injection responses change based on specific operational conditions and crafted prompts applied during the isolated test scenarios.