Testing Commands
A curated collection of 3 testing commands for building with AI coding agents.
Command
Fix Failing Test
Diagnose and fix a failing test by finding the real root cause.
/fix-failing-test[test name or path]
Command
Run Evals
Run the project's LLM evaluation suite (DeepEval, promptfoo, or RAGAS) and report scores against thresholds before a merge.
/run-evals<eval suite path / config, or the feature to evaluate>
Command
Write Tests
Generate tests covering the happy path and edge cases for the given target.
/write-tests[file or function]