CtrlK
BlogDocsLog inGet started
Tessl Logo

launchdarkly-metric-instrument

Instrument a LaunchDarkly metric event in a codebase by adding a track() call. Use when the user wants to wire up an event, instrument an action for a metric, add tracking to a feature, or confirm that an event is flowing to LaunchDarkly.

68

Quality

83%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Risky

Do not use without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

77%

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

This is a strong, well-structured skill with a clear 5-step workflow, concrete code examples, and good verification/troubleshooting guidance. Its main weaknesses are the missing bundle file (references/sdk-track-patterns.md is referenced four times but doesn't exist) and some verbosity in the Important Context section that could be tightened. Overall it provides highly actionable guidance for instrumenting LaunchDarkly metric events.

Suggestions

Provide the referenced 'references/sdk-track-patterns.md' bundle file — it's referenced four times and is critical for per-language SDK examples, initialization patterns, and package names.

Trim the 'Important Context' section by removing explanations of SDK buffering/flushing behavior (Claude knows this) and converting to a compact bullet list of gotchas specific to LD's track() semantics.

DimensionReasoningScore

Conciseness

The skill is mostly efficient and well-structured, but includes some unnecessary explanation (e.g., the 'Important Context' section explains concepts like event buffering and flush behavior that Claude would know from SDK docs). The workflow steps are reasonably tight but could be trimmed in places — for instance, the 'Find the Right Placement' section's example dialogue and the verbose verification troubleshooting table add bulk.

2 / 3

Actionability

The skill provides concrete, executable code examples for both server-side and client-side SDKs, specific MCP tool invocations, a clear troubleshooting table with specific checks, and exact patterns to follow. The guidance is specific enough to be copy-paste ready and covers edge cases like wrapper patterns and metricValue usage.

3 / 3

Workflow Clarity

The 5-step workflow is clearly sequenced with explicit validation in Step 5, including a troubleshooting checklist for when verification fails. The workflow includes a confirmation checkpoint in Step 3 before writing code, and the verify step has a clear feedback loop (check → diagnose from table → fix → re-verify). The skip condition in Step 2 is also well-handled.

3 / 3

Progressive Disclosure

The skill references 'references/sdk-track-patterns.md' multiple times for detailed per-language examples, which is good progressive disclosure design. However, no bundle files were provided, so the referenced file doesn't actually exist in the bundle — this means the references are broken. The main content is well-organized with clear sections, but the Important Context section could arguably be split out.

2 / 3

Total

10

/

12

Passed

Description

89%

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

This is a strong skill description that clearly identifies a narrow, specific use case (LaunchDarkly metric event instrumentation) with an explicit 'Use when' clause covering multiple natural trigger scenarios. The main minor weakness is that the 'what' portion could list additional concrete actions beyond just adding a track() call, but the description is otherwise well-crafted and distinctive.

DimensionReasoningScore

Specificity

The description names a specific domain (LaunchDarkly metric events) and one concrete action (adding a track() call), but it only describes a single action rather than listing multiple specific capabilities like extracting data, configuring metrics, or verifying event flow.

2 / 3

Completeness

Clearly answers both 'what' (instrument a LaunchDarkly metric event by adding a track() call) and 'when' (explicit 'Use when' clause listing four distinct trigger scenarios including wiring up events, instrumenting actions, adding tracking, and confirming event flow).

3 / 3

Trigger Term Quality

Excellent coverage of natural trigger terms: 'instrument', 'metric event', 'track() call', 'wire up an event', 'add tracking', 'LaunchDarkly', 'event is flowing'. These are terms users would naturally use when requesting this kind of work.

3 / 3

Distinctiveness Conflict Risk

Highly distinctive due to the specific LaunchDarkly branding, the track() API call, and the narrow focus on metric event instrumentation. Very unlikely to conflict with generic analytics or feature flag skills.

3 / 3

Total

11

/

12

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.

Validation11 / 11 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.