CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

70

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

77%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 a highly actionable, well-sequenced workflow with genuine feedback loops and verification gates — exemplary on actionability and workflow clarity. Its weaknesses are repetition of the same guidance in multiple sections (hurting token efficiency) and a monolithic single-file layout where the SDK instrumentation guide and measure-type reference could be split into separate reference files.

Suggestions

Move the Step 2b SDK instrumentation sub-workflow (~70 lines) into a references/instrumentation.md and keep a one-line pointer plus the trigger conditions in SKILL.md, cutting the main file roughly by a quarter.

Merge the 'Measure Type Reference' section with Step 5's explanation — the measureType-to-API translation is stated twice; state it once.

Remove redundant restatements: the confirm-before-create rule appears in Step 4's 'STOP HERE' paragraph, again at the top of Step 5, and parts of 'Important Context' repeat earlier guidance.

DimensionReasoningScore

Conciseness

The body is mostly efficient — dense decision tables, exact tool names, no explaining of concepts Claude already knows — but includes avoidable repetition: the measureType-to-API translation is stated twice (Step 5 and the 'Measure Type Reference' section), the confirm-before-create rule is restated in Step 4's 'STOP HERE' paragraph and again at the top of Step 5, and 'Important Context' reiterates earlier points. This fits the 3 anchor (mostly efficient but could be tightened) rather than 2, since there are no padded or tutorial-style sections.

3 / 5

Actionability

Fully executable guidance throughout: exact MCP tool signatures ('create-metric(projectKey, key, name, kind, ...)' with per-parameter constraints), concrete track() snippets ('ldClient.track('event-key', null, numericValue)'), per-build-tool env var names (VITE_LD_CLIENT_SIDE_ID, REACT_APP_..., NEXT_PUBLIC_...), and a read-back verification checklist. Specific examples cover the common cases, matching the 5 anchor.

5 / 5

Workflow Clarity

A clear 6-step sequence with explicit validation checkpoints and feedback loops: a hard confirmation gate ('STOP HERE... Do not call any API'), an instrumentation sub-workflow that re-checks list-metric-events to confirm events are flowing before proceeding, a duplicate check via list-metrics before creation, and a get-metric read-back verification with a 5-point checklist. This matches the 5 anchor; there are no missing checkpoints for the risky steps.

5 / 5

Progressive Disclosure

No bundle files exist; everything is inlined in a ~290-line SKILL.md. Sectioning is clear (Prerequisites, Workflow steps, reference tables), but secondary material — the ~70-line SDK instrumentation guide (Step 2b) and the Measure Type Reference table — sits inline where it could live in one-level-deep reference files. This fits the 3 anchor (some structure, content that could be separate is inline) rather than 4, since the file is well past the size where the no-references simple-skill exception applies.

3 / 5

Total

16

/

20

Passed

Description

92%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 a strong example: it states concrete capabilities in third-person imperative voice, gives an explicit 'Use when...' clause rich with natural trigger phrases, and is tightly scoped to LaunchDarkly metrics. The only minor gap is a couple of missing natural synonyms (e.g. 'KPI') in the trigger list.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Create a LaunchDarkly metric that measures what matters', 'Instruments the event first when needed (including SDK setup and .env)', 'creates and verifies the metric' — with comprehensive coverage of the skill's scope. It matches the 5 anchor (multiple specific concrete actions) rather than 4, which is reserved for lists with minor coverage gaps.

5 / 5

Completeness

Explicitly answers both: 'what' (create a metric, instrument the event first including SDK setup and .env, then create and verify) and 'when' ('Use when the user wants to create a metric, track an event, measure page views, button clicks, conversion, latency, error rate...'). Both are concrete and explicit, matching the 5 anchor.

5 / 5

Trigger Term Quality

'create a metric, track an event, measure page views, button clicks, conversion, latency, error rate, or any custom numeric or binary outcome' gives good natural-phrase coverage. Not 5 because a few plausible user phrasings (e.g. 'KPI', 'success metric', 'funnel') are missing; not 3 because the present terms are the natural things a user would say, not generic jargon.

4 / 5

Distinctiveness Conflict Risk

The 'LaunchDarkly' qualifier plus metric/event-specific triggers ('track an event', 'button clicks', 'error rate') carve a clear niche with minimal risk of firing for unrelated analytics or feature-flag skills. It does not fall to 4 because no closely related competing skill shares these triggers.

5 / 5

Total

19

/

20

Passed

Validation

100%

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
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.