skills.rest
sharad07072007
sharad07072007COMMUNITY
Explore all skills by this author →
GitHub

benchmark-testing

Creates isolated test projects and launches WezTerm panes running Claude Code to benchmark vercel-plugin skill injection.

Updated Sep 10, 2026
Search Tags:#automation#testing#claude code#plugin#benchmark#wezterm#skill injection
One-click install
npx skills add https://github.com/sharad07072007/paras --skill benchmark-testing-sharad07072007
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: benchmark-testing
Source: https://github.com/sharad07072007/paras/tree/main/.agents/plugins/vercel/.claude/skills/benchmark-testing
Command: npx skills add https://github.com/sharad07072007/paras --skill benchmark-testing-sharad07072007

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Validating that a Claude Code plugin correctly injects skills across realistic scenarios requires manual setup of many test projects, which is slow and error-prone. This Skill automates creating isolated benchmark directories, installing the vercel-plugin, and launching parallel Claude Code sessions with crafted prompts. ## Core Features & Use Cases - Isolated Test Project Setup: Creates numbered test directories under a base path and installs the vercel-plugin into each via npx add-plugin. - Parallel Session Launching: Spawns WezTerm tabs running Claude Code with correct flags (--cwd, --settings .claude/settings.json, unset CLAUDECODE) and 10-second staggered launches. - Technology-Agnostic Prompt Library: Provides nine ready-made prompts (recipe platform, trivia game, status page, etc.) designed to trigger specific skill injections without naming technologies. - Use Case: A plugin maintainer changes skill-trigger logic and needs to verify that prompts like a multiplayer trivia game still inject the expected vercel-storage and nextjs skills across nine parallel test sessions. ## Quick Start Ask the agent to set up benchmark test projects for the vercel-plugin and launch Claude Code sessions in WezTerm panes using the example prompts.

Frequently Asked Questions about benchmark-testing

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

FAQPage Schema
How do I test Claude Code plugin skill injection?▼

Create isolated test directories, install the plugin into each with npx add-plugin, then launch Claude Code sessions with crafted prompts. This Skill automates that workflow using WezTerm panes and a library of technology-agnostic prompts.

How to run multiple Claude Code sessions in WezTerm?▼

Use wezterm cli spawn with --cwd set to the target directory, unset CLAUDECODE to avoid nested-session errors, and pass --settings .claude/settings.json. Wait 10 seconds between launches and prefer spawn over split-pane, which runs out of space after about four panes.

Why should benchmark prompts avoid naming specific technologies?▼

Naming technologies like Next.js or Stripe bypasses the plugin's inference logic, defeating the test's purpose. Prompts should describe the product and features so the plugin itself decides which skills to inject.

Why does Claude Code fail with a nested-session error in WezTerm?▼

The error occurs when the CLAUDECODE environment variable is set inside an existing session. Unset CLAUDECODE before launching the new session to prevent the nested-session detection from blocking startup.

How do I clean up benchmark test directories after testing?▼

Remove the entire base directory with rm -rf ~/dev/vercel-plugin-testing. Each test project is self-contained, so deleting the base directory removes all installed plugins and generated files.

Related Skills

Explore More Software Engineering Skills→
vinhnguyenn020325-cmdvinhnguyenn020325-cmd

vercel-plugin-eval

Execute Claude Code sessions to validate Vercel plugin hooks and generate coverage reports.

Community
Intermediate
vercel-labsvercel-labs
246

vercel-plugin-eval

Run live Claude Code eval sessions for the vercel-plugin and generate coverage reports.

Official
Advanced
vercel-labsvercel-labs
246

benchmark-testing

Create and launch benchmark test projects for Vercel plugin skill injection.

Official
Intermediate
Git-FgGit-Fg

claude-cli

Automates Claude Code CLI invocations for headless sessions and JSON output.

Community
Advanced