vercel-plugin-eval

Verify Vercel plugin hook behavior and skill injection during live Claude Code sessions.

1|Updated Apr 19, 2026
One-click install
npx skills add https://github.com/arthtyagi/onloop --skill vercel-plugin-eval-arthtyagi
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: vercel-plugin-eval
Source: https://github.com/arthtyagi/onloop/tree/main/.agents/skills/vercel-plugin-eval
Command: npx skills add https://github.com/arthtyagi/onloop --skill vercel-plugin-eval-arthtyagi

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you verify that a Vercel plugin behaves correctly in real Claude Code sessions, catching hook failures, missing injections, deduplication bugs, and coverage gaps before they reach users.

Core Features & Use Cases

  • Live Session Evaluation: Launch and observe real agent sessions so you can confirm hook execution in the same environment where the plugin will actually run.
  • Debug Log Inspection: Monitor session logs in real time to validate session start, prompt submission, tool usage, post-tool validation, and session end behavior.
  • Deduplication and Coverage Reporting: Compare injection events against atomic claim files and compile a structured report of coverage, issues, and validation outcomes.
  • Use Case: A maintainer wants to test whether a new plugin release injects the right skills exactly once per scenario and produces a clean coverage summary across multiple runs.

Quick Start

Run a live Claude Code eval session with the plugin installed, then inspect the debug logs and claim files to confirm hook firing, deduplication, and coverage.

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 Vercel plugin hook behavior in live Claude Code sessions?

To verify Vercel plugin hook behavior in live Claude Code sessions, you launch a live evaluation session with the plugin installed, then monitor real-time debug logs to inspect session start, prompt submission, tool usage, and session end execution.

What is the best way to test plugin deduplication and skill injection correctness?

Testing plugin deduplication and skill injection correctness involves comparing injection events against atomic claim files during an active eval session to confirm hooks fire exactly once per scenario and identify any duplicate injection bugs.

How does debug log inspection work for Claude Code plugin evaluation?

Debug log inspection for Claude Code plugin evaluation works by monitoring session logs in real time to validate lifecycle hook execution, post-tool validation behavior, and trace injection failures before they reach end users.

Can I generate a structured coverage report for registered Vercel plugin hooks?

You can generate a structured coverage report for registered Vercel plugin hooks by running a live eval session, tracking hook firing events against claim files, and compiling validation outcomes and coverage gaps into a summary.

Does Vercel plugin evaluation require real-time debug log monitoring?

Vercel plugin evaluation requires real-time debug log monitoring because it is the mechanism used to confirm session lifecycle hooks execute correctly, validate tool-triggered injections, and catch missing validation output during the live session.

Why are my Vercel plugin hooks failing to inject skills during Claude Code sessions?

Vercel plugin hooks may fail to inject skills due to lifecycle execution errors or deduplication bugs; running a live Claude Code eval session with debug log inspection and claim-file comparison isolates the failing hook and coverage gap.