Name: launchdarkly-experiment-setup
Rating: 68 (1 reviews)
Author: launchdarkly

launchdarkly-experiment-setup

Set up and run experiments in LaunchDarkly. Create experiments with metrics, treatments, and flag config, start iterations to collect data, swap design between iterations, and stop with a winner.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

88%Weight 40%Scale 1-5

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

The body is highly actionable with executable examples and a well-sequenced, validated workflow; its only weakness is minor verbosity and a monolithic structure that could benefit from splitting some reference material out.

Suggestions

Trim the opening paragraph and "Core Principles" where they restate steps already detailed in the Workflow.

Consider moving the exhaustive optional-field reference (holdoutId, dataSource, analysisConfig, etc.) into a separate reference file linked from the main workflow.

Optionally add a compact "happy path" summary at the top to let Claude proceed without reading every step.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of generic concept explanations, though the opening paragraph and "Core Principles" section partly restate workflow steps and could be trimmed.	4 / 5
Actionability	Provides fully executable JSON payloads and concrete tool/field names for create, start, evolve, and stop, covering the common cases copy-paste ready.	5 / 5
Workflow Clarity	Clear 7-step sequence with explicit validation checkpoints (Step 5 verify, winner-required stop) and error-recovery guidance (skipped-field handling, no-stop-without-winner path).	5 / 5
Progressive Disclosure	Well-organized into clear sections and appropriately self-contained with no nested references, though a ~230-line guide with large JSON examples could split exhaustive field reference into a separate file.	4 / 5
	Total	18 / 20 Passed

Description

75%Weight 40%Scale 1-5

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, concrete, and clearly distinct in its niche, but it lacks an explicit "when to use" trigger clause, which limits its completeness score.

Suggestions

Add a "Use when..." clause naming trigger situations, e.g. "Use when setting up A/B tests or feature-flag experiments in LaunchDarkly."

Include common synonyms like "A/B test" or "feature flag test" that users would naturally say.

Explicitly mention the measurable outcome (declaring a winning variation) to strengthen trigger recognition.

Dimension	Reasoning	Score
Specificity	Enumerates multiple concrete actions ("Create experiments with metrics, treatments, and flag config", "start iterations to collect data", "swap design between iterations", "stop with a winner"), giving comprehensive coverage rather than just a few actions.	5 / 5
Completeness	The "what" is clearly stated, but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	Natural domain terms like "experiments", "LaunchDarkly", "metrics", "treatments", and "winner" are present, but common user phrasings like "A/B test" or "feature flag test" are absent.	4 / 5
Distinctiveness Conflict Risk	"LaunchDarkly experiments" is a distinct niche with specific triggers and minimal overlap risk with other skills.	5 / 5
	Total	17 / 20 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: launchdarkly/ai-tooling
Path: skills/experiments/launchdarkly-experiment-setup/SKILL.md
Commit: f85169c

Reviewed: 9 days ago

Table of Contents

Discovery Implementation Validation

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.