What problem does it solve?
After running the repository's example workflow, contributors need to verify that every example actually behaved correctly, not just exited with code zero. This Skill inspects the completed run's logs and source files to validate behavior, classify failures, and explain skips without ever executing or controlling any process.
Core Features & Use Cases
- Behavioral validation: Compares each exit-zero example's log against its intended flow in source code, confirming expected tool calls, approvals, handoffs, streamed output, and generated artifacts.
- Failure and skip classification: Categorizes non-zero exits as repository failures, expected example failures, external dependency restrictions, or environment limits, and classifies every skip by its recorded reason.
- Freshness and completeness checks: Detects stale, incomplete, or still-running logs and refuses to analyze them, directing the user to finish the manual pnpm run first.
- Use Case: After running
pnpm examples:workflow:start, ask the Skill to review the latest logs; it reports one line per example with evidence, plus separate lists of failures, intentional skips, and environment restrictions.
Quick Start
Use the examples-run-analysis skill to inspect the latest completed example run logs and tell me which examples genuinely passed, which failed, and which were skipped.
