Define metrics from Kayba insights, implement them as Python measurement code, run against traces, and iterate until the metrics are clean and meaningful. Trigger when the user says "run stage 3", "define metrics", "build metrics", "compute baselines", or when invoked by the kayba-pipeline orchestrator. Requires eval/stage1_insights_summary.md and eval/stage2_domain_context.md to exist.
$npx -y skills add kayba-ai/agentic-context-engine --skill stage-3-metricsInstalls into the current project.
Run `npx skills use "https://github.com/kayba-ai/agentic-context-engine" --skill "kayba-ai/agentic-context-engine/stage-3-metrics"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/kayba-ai/agentic-context-engine" that are relevant to the current task. Run `npx skills add "https://github.com/kayba-ai/agentic-context-engine"` and select the relevant skills, then follow their instructions.