vercel-plugin-eval

Run live Claude Code sessions to evaluate vercel-plugin hooks and coverage.

Updated May 31, 2026
One-click install
npx skills add https://github.com/ChristineTham/lp --skill vercel-plugin-eval-christinetham
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: vercel-plugin-eval
Source: https://github.com/ChristineTham/lp/tree/main/.agents/skills/vercel-plugin-eval
Command: npx skills add https://github.com/ChristineTham/lp --skill vercel-plugin-eval-christinetham

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Run live eval sessions against the vercel-plugin to verify hook behavior, skill injection, dedup correctness, and coverage. Launches real Claude Code sessions via WezTerm, monitors debug logs, and produces a structured coverage report.

Core Features & Use Cases

  • Launch real Claude Code sessions with the plugin installed, monitor debug logs in real-time to verify hook firing and dedup.
  • Generate a structured coverage report detailing injections, hooks, and outcomes for auditability.
  • Use in QA scenarios to validate integration stability and coverage across repeated runs.

Quick Start

Run a fresh eval session against the vercel-plugin, then inspect the resulting logs and coverage output.

Frequently Asked Questions about vercel-plugin-eval

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

FAQPage Schema
How do I verify Claude Code hook behavior during plugin development?

You can verify hook behavior by running live eval sessions that launch real Claude Code instances with the plugin installed, monitor debug logs in real-time, and generate a structured coverage report detailing hook firing, injections, and outcomes.

What is live eval for plugin QA and how does it work?

Live eval for plugin QA is an automated process that runs real Claude Code sessions via WezTerm to test integration stability. It monitors debug logs and produces a structured coverage report across multiple runs for auditability and dedup accuracy validation.

How do I test dedup accuracy and skill injection across multiple runs?

You test dedup accuracy and skill injection by executing deterministic invocation patterns across multiple runs. The eval process monitors real-time debug logs to verify hook firing and generates a structured coverage report for auditability.

Does live eval testing work with WezTerm for monitoring Claude Code debug logs?

Yes, live eval testing works with WezTerm to launch real Claude Code sessions and monitor debug logs in real-time. This setup allows you to inspect hook firing, skill injection, and dedup correctness directly during the evaluation.

Can I generate a coverage report for hook firing and skill injection outcomes?

Yes, you can generate a structured coverage report detailing injections, hooks, and outcomes for auditability. The report is produced automatically after running live eval sessions, providing a structured output across multiple runs.