CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

97

1.16x
Quality

100%

Does it follow best practices?

Impact

92%

1.16x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

100%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a tight, actionable workflow that adds only non-obvious domain knowledge, with explicit validation checkpoints and well-signaled references to sibling skills. It earns full marks across all four content dimensions.

DimensionReasoningScore

Conciseness

Lean and efficient; it conveys LaunchDarkly-specific knowledge Claude does not already have (auto-attach from release policies, CUPED/percentile incompatibility, context-kind matching) with no filler or elementary concept explanation. Every token earns its place.

3 / 3

Actionability

Provides concrete MCP calls ("list-release-policies(projectKey)"), typed secondary-metric tables, and specific numeric guidance ("2–3 metrics maximum", "More than five creates false positive rollback risk"). Recommendations are copy-ready and decision-oriented.

3 / 3

Workflow Clarity

A clear 5-step sequence with explicit validation checkpoints: cross-referencing list-metrics with list-metric-events for event health, warning on at-risk metrics, and flagging context-kind mismatches, CUPED/percentile conflicts, and mid-experiment restarts. Error-recovery guidance is concrete ("Instrument the event before including it, or remove it").

3 / 3

Progressive Disclosure

Single-file skill with no bundle directories; the body is well-organized into prerequisites, workflow, important context, and related skills. The only references are one-level-deep pointers to sibling skills (metric-create, metric-instrument), clearly signaled and easy to navigate. Per the simple-skill scoring note, this warrants a 3.

3 / 3

Total

12

/

12

Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, trigger-rich, complete, and well-scoped to its niche. It names concrete actions across three contexts and pairs each with an explicit 'Use when' clause in third-person voice.

DimensionReasoningScore

Specificity

Lists multiple concrete actions across three distinct contexts — "Choose the right metrics for a LaunchDarkly experiment, guarded rollout, or release policy" and names specific sub-tasks (primary metric, guardrails, events to monitor). Matches the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

Clearly answers both what ("Choose the right metrics...") and when with an explicit "Use when the user wants to know..." clause listing several trigger conditions. Both halves are present and explicit; third-person voice is maintained throughout.

3 / 3

Trigger Term Quality

Uses natural user phrasings such as "which metrics to use", "which is the primary metric for an experiment", "what guardrails to add", and "which events to monitor in a rollout" — the kinds of questions a user would actually voice. Good coverage of natural terms, not just jargon.

3 / 3

Distinctiveness Conflict Risk

Scoped narrowly to LaunchDarkly metric selection with context-specific triggers (primary metric, guardrails, auto-attached release-policy metrics), making it unlikely to fire for unrelated skills. Clear niche with distinct triggers.

3 / 3

Total

12

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 2 suspicious

Warning

Total

15

/

16

Passed

Repository
launchdarkly/ai-tooling
Reviewed

Table of Contents

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.