Skip to content
agentscamp

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]