Catch perf regressions before users do
Introduce performance budgets and regression detection using benchmarks and/or production telemetry so regressions become reviewable events, not customer complaints.
Create a skill called "Performance Regression Guardrails". Ask me for: - The top user journeys / hot paths - Current observability/benchmark tooling Output: - A minimal benchmark plan (scenarios + metrics) - Budget thresholds and alerting approach - CI integration strategy (PR vs nightly) - A PR checklist for performance-sensitive changes
Performance regressions are common after upgrades and refactors. This recipe sets up
a small, stable performance suite that monitors key metrics over time.
Cut pipeline time with caching, parallelism, and smarter triggers
Reduce CI wall-clock time by implementing dependency caching, parallelization/sharding, and filtering out unnecessary pipeline runs.
Make tests fast enough that devs actually run them
Reduce test runtime by separating unit/integration/e2e, improving isolation, enabling parallelism, and running the right tests at the right time.
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.