Blacksmith

Connects Claude to Blacksmith CI's internal web API for debugging test failures and monitoring builds. Query workflow runs with filters for status, branch, or PR. Analyze test results with tools like get_failed_tests, get_flaky_tests, and compare_test_runs to spot regressions between branches. Search logs, track test history, and check cache usage across repositories. Authentication works through Chrome cookie extraction if you're logged into app.blacksmith.sh, otherwise pass a session token manually. Useful when you're triaging CI failures and want to ask "why did this run fail" or "which tests are flaky this week" instead of clicking through dashboards.