What problem does it solve?
This Skill centralizes and automates analysis of failing test runs so developers and CI engineers do not need to manually inspect disparate logs and reports to find root causes. It turns pytest, Vitest, Playwright, Wokwi and CI artifacts into concise failure summaries, actionable recommendations, and file-level pointers.
Core Features & Use Cases
- Multi-framework parsing: Parses JUnit XML, HTML Playwright reports, coverage outputs, Wokwi JSON/junit, and plain-text pytest logs to locate failing testcases and stack traces.
- CI artifact handling: Uses gh CLI patterns to list failing runs, download artifacts, and extract logs for comparison between CI and local executions.
- Consolidated reporting: Produces and incrementally updates .claude/reports/Testrunner/test.md with a summary, per-area sections (backend, frontend, E2E, Wokwi), and next-step recommendations.
- Use case: When a GitHub Actions run fails for server-tests, the Skill downloads the unit-test-results artifact, extracts junit-*.xml, highlights failing tests, and suggests focused reproduction commands and likely fixes.
Quick Start
Analyze the failing tests in logs/backend/pytest-results.xml and update .claude/reports/Testrunner/test.md with a concise summary of failures and recommended next steps.