Lean and efficient: assumes Claude knows what RUM and synthetic monitors are, presents tight scoring/normalization tables and heuristics rather than definitional prose, and every section (steps, worked example, anti-patterns, limitations) earns its place.

Provides concrete executable guidance - real API endpoints ('GET /api/v1/synthetics/tests'), CLI commands ('checkly tests list --output json'), explicit scoring tables, path normalization rules, an output format spec, and a monitor-type heuristic with thresholds.

Clear five-step sequence (collect -> score -> inventory -> diff -> emit) with an explicit hard-reject validation gate when no RUM source is available and an anti-patterns table covering failure modes and fixes.

Clear overview with a single one-level-deep, well-signaled reference (references/rum-source-queries.md, verified present) holding the per-source Step 1 queries; external doc links are grouped in a References section for easy navigation.

Lists multiple concrete actions - 'identify high-traffic user journeys that have no synthetic monitor coverage', 'ranks journeys by session volume times business value', 'diffs the ranked list against existing synthetic monitors, and emits a prioritized gap list' - matching the 'multiple specific concrete actions' anchor.

Explicitly answers both what (reads RUM, scores, diffs, emits gap list) and when via the 'Use when an observability stack has RUM instrumented but the team suspects synthetic coverage is sparse, biased toward low-traffic paths...' trigger clause.

Uses natural domain terms practitioners say - 'RUM', 'Real User Monitoring', 'synthetic monitor coverage', 'observability stack', 'synthetic coverage' - with good coverage of the variations an SRE/observability user would actually invoke.

Occupies a clear niche (RUM-to-synthetic gap analysis feeding synthetic-monitor-author) with distinct triggers; unlikely to fire for unrelated skills.