Find the real source of nondeterminism, not just the symptom
Diagnose flaky tests by categorizing nondeterminism (timing, order-dependence, shared state, network, resource contention) and applying targeted fixes.
Create a skill called "Flaky Root Cause Hunter". Given: - A flaky test name/file and recent failure logs - The test type (unit/integration/e2e) and environment (CI/local) Output: - A likely root-cause category and how to confirm it - Concrete fix patterns for that category - A verification plan (stress reruns, seed capture, isolation)
This recipe structures flake debugging so teams stop inflating timeouts and start removing
nondeterminism from tests and environments.
Stop flaky tests from blocking PRs while you fix them
Quarantine known flaky tests into a separate lane so they don't block merges, while preserving visibility and enforcing a fix-by deadline.
Keep end-to-end confidence without the unmaintainable monster
Establish a minimal set of end-to-end tests for critical journeys, backed by contract tests and targeted integration tests, to balance confidence with speed.
Ship new creatives every week without chaos
Creative teams burn out when "we need new ads" arrives as an emergency. This recipe creates a weekly sprint system: inputs, brief template, production checklist, QA, and a testing plan that compounds learning.
Improve retention with scroll-stopping openings
Generates and rewrites hooks optimized for your platform and audience intent. It produces multiple hook styles (curiosity, contrast, payoff-first) and recommends which to test, based on your goals and content type.