Analyze Test Run

If you're running integration tests in GitHub Actions and need to understand why things failed, this skill downloads artifacts, parses JUnit XML and skill reports, and produces a comprehensive breakdown of test results, skill invocation rates, and confidence scores. It goes further by filing GitHub issues for each failure with actual root cause analysis, pulling context from agent metadata and test logs to categorize problems like skills not being invoked, deployment failures, or quota exhaustion. The skill even checks for duplicate issues before filing. Built for the Microsoft Azure Copilot team's workflow, it tracks the three-skill deployment chain for azure-deploy tests specifically. Saves you from manually digging through artifacts and logs to figure out what went wrong and where.

Install to Claude Code

npx -y skills add microsoft/github-copilot-for-azure --skill analyze-test-run --agent claude-code