Name: launchdarkly-metric-create
Rating: 75.2 (1 reviews)
Author: launchdarkly

launchdarkly-metric-create

Create a LaunchDarkly metric that measures what matters for an experiment or rollout. Use when the user wants to create a metric, track an event, measure page views, button clicks, conversion, latency, error rate, or any custom numeric or binary outcome. Instruments the event first when needed (including SDK setup and .env), then creates and verifies the metric.

Quality

92%

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

85%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 content is highly actionable with executable code, MCP call signatures, and a clearly sequenced workflow featuring explicit validation checkpoints and a confirmation gate before the create call. Progressive disclosure is clean for a single-file skill. The main weakness is conciseness: it explains some concepts Claude already knows and repeats a few points that could be tightened.

Suggestions

Trim general-knowledge asides Claude already has (e.g. explaining kebab-case, the per-build-tool env variable naming list) and link to LD docs instead of inlining the SDK base-URL block twice.

Consolidate the repeated 'instrument before creating' guidance so it appears once as a rule rather than restated across Step 2, Step 2b intro, and Important Context.

Move the measureType/isNumeric/unitAggregation reference table to a single authoritative spot — it overlaps between Step 4 templates, Step 5 params, and the 'Measure Type Reference' section.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and well-structured, but it teaches general concepts Claude already knows (explaining kebab-case keys, build-tool env naming conventions for Vite/CRA/Next.js, what 'project' means) and repeats some guidance (the SDK base URL logic, the instrumentation-as-default point) that could be trimmed.	3 / 5
Actionability	Provides fully executable, copy-paste-ready guidance: concrete MCP tool call signatures (create-metric with all params), .env variable snippets, SDK init code blocks, and explicit track() call forms — specific examples cover the common cases.	5 / 5
Workflow Clarity	Multi-step process is clearly sequenced (Steps 1–6 with a Step 2b sub-workflow) with explicit validation checkpoints — 're-check list-metric-events to confirm events are flowing', 'Only proceed once the user has explicitly confirmed', and the get-metric verification step — plus a hard STOP gate before the destructive create call.	5 / 5
Progressive Disclosure	Single self-contained SKILL.md with no bundle files, organized into clear sections (Prerequisites, Workflow steps, Reference tables, Important Context) that serve as an overview; well-structured with no nested references, so it navigates easily and earns the top anchor for a single-file skill.	5 / 5
	Total	18 / 20 Passed

Description

100%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, trigger-rich, complete, and distinct: it names concrete actions, lists natural trigger terms a user would say, explicitly states both what and when, and carves a clear LaunchDarkly-specific niche. Voice is consistently third person. It does not over-claim and earns the top anchor on every dimension.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'create a LaunchDarkly metric', 'track an event', 'measure page views, button clicks, conversion, latency, error rate', 'Instruments the event first', 'creates and verifies' — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both what ('Create a LaunchDarkly metric... Instruments the event first... creates and verifies') and when ('Use when the user wants to create a metric, track an event, measure page views...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Covers a rich set of natural trigger phrases users would say ('create a metric', 'track an event', 'measure page views', 'button clicks', 'conversion', 'latency', 'error rate') plus 'experiment or rollout', giving comprehensive coverage of natural terms and synonyms.	5 / 5
Distinctiveness Conflict Risk	Clear niche — LaunchDarkly metric creation — with distinct, domain-specific triggers ('experiment or rollout', 'LaunchDarkly metric', 'event key') that are unlikely to fire for unrelated skills.	5 / 5
	Total	20 / 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/metrics/launchdarkly-metric-create/SKILL.md
Commit: 45fcc25

Reviewed: 2 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.