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.

75

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

High

Do not use without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

92%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.

Excellent instructional content: a well-sequenced five-step workflow with a confirmation gate and a verification feedback loop, fully executable code and tool invocations, and a clean split between the SKILL.md overview and a single well-signaled per-SDK reference. The only weakness is minor redundancy between the intro paragraph, the Step-5 delay note, and the Important Context bullets.

DimensionReasoningScore

Conciseness

The body is dense with non-obvious domain knowledge (server- vs client-side signatures, flush/buffering behavior, flag-evaluation prerequisite, metricValue unit pitfalls) and avoids explaining basics. Minor over-explanation could be trimmed: the opening paragraph restates the five workflow steps, and the Step-5 delay note plus "Important Context" bullets slightly overlap. Matches the anchor "efficient; minor instances of over-explanation that could be trimmed" — not 5 because those few redundant sentences don't each earn their place.

4 / 5

Actionability

Fully executable throughout: concrete search strings ("ldClient.track(", "package.json", "go.sum"), a signature table per SDK type, copy-paste-ready track() snippets for count/value metrics, exact MCP tool invocations, and a specific troubleshooting table with remediation checks. Matches "fully executable; copy-paste ready... specific examples cover the common cases".

5 / 5

Workflow Clarity

Five clearly sequenced steps with explicit checkpoints: a confirmation gate in Step 3 ("Show the candidate location to the user before writing anything"), and a full verify-then-diagnose feedback loop in Step 5 (trigger action → list-metric-events → problem/check table → retry given the ~5 min delay). This matches the anchor-5 example's validate-fix-retry structure. The operation is additive, not destructive/batch, so no cap applies.

5 / 5

Progressive Disclosure

SKILL.md stays at overview level (workflow, decision rules, common cases) and delegates per-language syntax, package names, and initialization examples to a single one-level-deep reference (references/sdk-track-patterns.md, verified to exist, 340 lines) that is clearly signaled four times inline and again in a closing References section with a content description. Matches "clear overview with well-signaled one-level-deep references; content appropriately split".

5 / 5

Total

19

/

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.

A strong description: concrete, third-person, with an explicit 'Use when' clause covering several natural trigger phrasings. It is tightly scoped to a single product operation, giving it excellent distinctiveness and completeness. The only minor gap is a few additional natural synonyms users might say (e.g. 'send events to LaunchDarkly').

DimensionReasoningScore

Specificity

Multiple concrete actions in third-person voice: "Instrument a LaunchDarkly metric event", "adding a track() call", plus the trigger list names distinct operations ("wire up an event", "instrument an action for a metric", "add tracking to a feature", "confirm that an event is flowing"). This matches the anchor "lists multiple specific concrete actions; comprehensive coverage" — the skill has a narrow scope and the description covers it fully. Not a 4 because there is no meaningful gap in coverage for the skill's domain.

5 / 5

Completeness

Explicitly answers both questions with concrete trigger phrases: what — "Instrument a LaunchDarkly metric event in a codebase by adding a track() call"; when — "Use when the user wants to wire up an event, instrument an action..., add tracking..., or confirm that an event is flowing." This matches the anchor-5 good example structurally. Not a 4 because the 'when' clause is already explicit with concrete triggers, not merely present.

5 / 5

Trigger Term Quality

Good natural-phrase coverage: "wire up an event", "instrument an action", "add tracking to a feature", "confirm that an event is flowing", "metric", "LaunchDarkly", "track()". It falls just below the anchor-5 "comprehensive coverage including synonyms" because common user phrasings like "send events to LaunchDarkly", "custom event", or "measure conversions/experiment metrics" are absent.

4 / 5

Distinctiveness Conflict Risk

Clear niche (LaunchDarkly metric instrumentation via track()) with distinct, product-specific triggers; minimal conflict risk with any generic analytics or feature-flag skill. Only a sibling LaunchDarkly skill (e.g. metric creation) could overlap, and the explicit "track()" framing keeps the boundary sharp.

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.