Skip to content
agentscamp

Testing Commands

A curated collection of 5 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

Hunt Flaky Tests

Reproduce a flaky test, find the real source of nondeterminism, and fix the cause.

/flaky-test-hunt<suspected test or area (optional)>
Command

Generate E2E Test

Scaffold a resilient end-to-end test for a user flow grounded in the real UI.

/generate-e2e-test<user flow to test>
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]