Attach judges to config variations for automatic LLM-as-a-judge evaluation. Create custom judges, configure sampling rates, and monitor quality scores.
$npx -y skills add launchdarkly/agent-skills --skill online-evalsInstalls into the current project.
Run `npx skills use "https://github.com/launchdarkly/agent-skills" --skill "launchdarkly/agent-skills/online-evals"` 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/launchdarkly/agent-skills" that are relevant to the current task. Run `npx skills add "https://github.com/launchdarkly/agent-skills"` and select the relevant skills, then follow their instructions.