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

vercel-plugin-eval

Runs live eval sessions against the vercel-plugin to verify hook firing, skill injection, and dedup correctness.

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

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Verifying that a Claude Code plugin's hooks, skill injection, and deduplication logic actually work requires launching real interactive sessions, which is tedious and error-prone to do manually. This Skill standardizes live end-to-end evals of the vercel-plugin with exact commands, monitoring queries, and a structured coverage report. ## Core Features & Use Cases - Live Session Evals: Launches real Claude Code sessions via WezTerm with the plugin installed through npx add-plugin, avoiding pitfalls like claude --print where hooks never fire. - Hook & Dedup Monitoring: Greps debug logs to confirm all 8 registered hooks fire and compares skill injections against atomic claim files to validate dedup correctness. - Coverage Reporting: Maps scenario types (AI chat, monorepo, edge auth, payments) to the 44 plugin skills and writes results to .notes/COVERAGE.md with hook matrices and issue lists. - Use Case: After modifying the vercel-plugin's PreToolUse injection logic, run a kitchen-sink eval session and confirm injections equal claim files with no duplicate skill injections. ## Quick Start Ask the agent to run a vercel-plugin eval session for an AI chat app scenario and produce a coverage report of hook firing and skill dedup.

Frequently Asked Questions about vercel-plugin-eval

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

FAQPage Schema
How do I test that Claude Code plugin hooks actually fire?▼

Launch a real interactive session via WezTerm with the plugin installed, then grep the debug log in ~/.claude/debug for hook success lines like SessionStart, PreToolUse, and PostToolUse. Hooks do not fire with claude --print, so live sessions are required.

How do I verify skill injection dedup in a Claude Code plugin?▼

Compare the count of skillInjection entries in the debug log (divided by three, since each injection logs three times) against the number of atomic claim files in the session's seen-skills directory. Equal counts confirm dedup correctness.

Why don't hooks fire when using claude --print or -p?▼

Print mode runs a non-interactive one-shot completion where the plugin hook lifecycle is not executed and no files are created. Use a real interactive session launched through a terminal multiplexer like WezTerm instead.

How do I trigger hard-to-reach plugin skills like v0-dev or vercel-firewall?▼

Name the technology explicitly in the prompt, since agents do not naturally reach for these skills. For example, say generate components with v0 or use Vercel Firewall for rate limiting to force the injection.

Can I install the plugin by manually writing settings.local.json?▼

No, manual hook wiring and hand-created settings files are prohibited in this eval workflow. Always install with npx add-plugin so hooks are registered exactly as end users experience them.

Related Skills

Explore More Software Engineering Skills→
miles990miles990
20

claude-code-plugin

Guide developers through creating, publishing, and managing Claude Code Plugins.

Community
Advanced
ChristineThamChristineTham

plugin-audit

Analyze Claude Code logs to validate vercel-plugin hook injections.

Community
Intermediate
mazerunner70mazerunner70

Backend Services Layer

Orchestrate backend business logic with Pydantic validation and enforced unit tests.

Community
Advanced
majesticlabs-devmajesticlabs-dev
47

pytest-coder

Automate writing pytest tests with fixtures, parametrization, mocking, and async cases.

Official
Advanced