What problem does it solve? Testing whether a Claude Code plugin correctly injects skills and fires hooks requires real interactive sessions, since print-mode runs never trigger PreToolUse, PostToolUse, or UserPromptSubmit hooks. This Skill provides the exact commands, monitoring queries, and verification checks to run reliable end-to-end evals of the Vercel plugin. ## Core Features & Use Cases - Interactive Eval Launch: Spawns WezTerm panes running Claude Code sessions with the plugin installed via npx add-plugin, using timestamped directories and debug logging. - Injection Monitoring: Checks skill claim directories and debug logs to count injected skills, hook firings, and PostToolUse validation catches. - Code Verification: Greps generated projects for correct patterns such as withWorkflow config, AI Gateway usage, gemini image models, and AI Elements components. - Use Case: Run three parallel eval sessions with natural-language prompts (e.g., a durable content pipeline), then produce a coverage report showing which of the 43 plugin skills triggered and which code patterns need fixing before release. ## Quick Start Launch three benchmark eval sessions for the Vercel plugin using the tarot-deck, interior-designer, and superhero-origin scenarios and report which skills were injected.
