Custom Metrics

This walks you through the full lifecycle of custom business metrics in LaunchDarkly: creating metric definitions via API, tracking events through the SDK, and querying results. It's built for measuring things like conversion rates, task success, user satisfaction, or revenue impact from your configs. The skill includes API key auto-detection from Claude's MCP config or environment variables, handles required fields like successCriteria and unit for numeric metrics, and gives you concrete tracking patterns for common scenarios. You'll need a LaunchDarkly API token with writer permissions. It's experimental but covers the practical stuff you'd actually need to instrument custom metrics beyond LaunchDarkly's built-in ones.

skills.sh installs: 1.3K
GitHub stars: 19
last updated: Jul 14, 2026

View on GitHub

Install

$ npx -y skills add launchdarkly/agent-skills --skill custom-metrics --agent claude-code

Installs into .claude/skills of the current project.

Files

Custom Metrics for Configs

Full lifecycle management of custom business metrics: create metric definitions with the MCP server, track events via SDK, retrieve metric data, and manage metrics programmatically.

Prerequisites

LaunchDarkly AI SDK initialized (see sdk-install). The SDK reads LD_SDK_KEY from the environment.
The remotely hosted LaunchDarkly MCP server configured in your environment
A LaunchDarkly API token with the writer role, only to update or delete metrics, or for scripts that can't use MCP
Understanding of built-in agent metrics (see built-in-metrics)

API Access

Use the LaunchDarkly MCP server tools wherever one exists: they authenticate via OAuth and need no token. Create metrics with create-metric, check that events are arriving with get-metric-events, read definitions with get-metrics, and change or remove them with update-metric and delete-metric. For scripts that can't use MCP, ask the user to paste an API access token for this session and substitute it for {api_token} in the examples below. Do not search environment variables, .env files, or agent/MCP config files for credentials.