Name: launchdarkly-metric-choose
Rating: 93.6 (1 reviews)
Author: launchdarkly

launchdarkly-metric-choose

Choose the right metrics for a LaunchDarkly experiment, guarded rollout, or release policy. Use when the user wants to know which metrics to use, which is the primary metric for an experiment, what guardrails to add, or which events to monitor in a rollout. Surfaces what will auto-attach from existing release policies before making additional recommendations.

1.16x

Quality

92%

Does it follow best practices?

Impact

92%

1.16x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Evaluation results

100%

16%

Choosing Metrics for a Feature Flag Experiment

Experiment metric recommendation with typed secondaries and CUPED warning

Criteria

Without context

With context

Hypothesis framing

60%

100%

Single primary metric

100%

Primary success direction

100%

Guardrail metric present

100%

Counter-metric present

100%

Supporting signal present

62%

100%

Event health check

100%

CUPED + percentile warning

100%

No release policy fetch

100%

Next steps guidance

87%

100%

Advisory only

100%

95%

21%

Safeguarding a Backend Service Migration

Guarded rollout metric selection with release policy surfacing

Criteria

Without context

With context

Release policy fetch

40%

70%

Auto-attached metrics surfaced

91%

Reliability bias

90%

100%

Metric count limit

100%

Domain-specific metric

100%

Pushback on product metrics

100%

Event health check

40%

90%

Recommendation format

87%

100%

No experiment workflow

100%

Next steps guidance

90%

100%

82%

Establishing Project-Wide Rollout Safety Standards

Release policy metric selection with context kind mismatch and scope guidance

Criteria

Without context

With context

Existing policy surfaced

70%

100%

Max 3 metrics recommended

100%

Pushback on 5 metrics

58%

Stable event history requirement

20%

50%

Context kind mismatch warning

100%

Scope condition explanation

100%

Recommends reliable candidates

100%

30%

Next steps guidance

37%

87%

Advisory only

100%

No experiment workflow applied

100%

Repository: launchdarkly/ai-tooling
Commit: 24e9c7e

Evaluated: about 7 hours ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Choosing Metrics for a Feature Flag Experiment Safeguarding a Backend Service Migration Establishing Project-Wide Rollout Safety Standards

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.