What problem does it solve? Verifying that a plugin correctly injects the right skills into AI coding sessions requires tedious manual testing across many project types. This Skill automates the entire loop: creating realistic test projects, running skill injection, launching dev servers, verifying they work, and producing actionable gap reports. ## Core Features & Use Cases - Four-Stage Pipeline: Chains runner, verify, analyze, and report stages sequentially, aborting on failure with NDJSON event tracking. - Precise Session Correlation: Uses a run-manifest.json contract to match JSONL conversation logs to projects instead of guessing from directory listings. - Actionable Reports: Generates report.json and report.md with verdicts, missing-skill gaps, and copy-pasteable suggestedPatterns for fixing frontmatter. - Use Case: Run the suite overnight in a loop, then wake up to timestamped reports showing which expected skills (auth, payments, ai-sdk) were never injected, letting you close gaps and watch the verdict trend from fail to pass. ## Quick Start Run the benchmark-e2e skill in quick mode to test the first three projects and show me the improvement report.
