This walks you through adding LaunchDarkly track() calls to measure user actions in experiments. It detects whether you're using a server-side or client-side SDK (critical because the signatures differ), finds existing patterns in your codebase to mirror, helps you place the call in the right spot, and verifies events are flowing using the LaunchDarkly MCP server. The workflow is thorough, maybe more than you need if you already know the SDK, but genuinely useful if you're instrumenting your first metric or debugging why events aren't showing up. One thing to remember is that track() calls only count in experiments when a flag evaluation happens first, so the event can be correlated to a participant.
npx skills add https://github.com/launchdarkly/agent-skills --skill launchdarkly-metric-instrument