From lensflare-desktop
Analyzes Lensflare traces span-by-span, explaining timing, errors, and parent/child structure. Use for debugging slow requests, error post-mortems, or production traces via trace ID.
How this skill is triggered — by the user, by Claude, or both
Slash command
/lensflare-desktop:analyze-traceThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
1. If the user supplied a `traceId`, use it. Otherwise call `lensflare:queryTelemetry` to find a relevant trace (filter by `serviceName`, time, or attributes). Pick the trace whose root span has the highest `durationUs` or whose `status = "error"`.
traceId, use it. Otherwise call lensflare:queryTelemetry to find a relevant trace (filter by serviceName, time, or attributes). Pick the trace whose root span has the highest durationUs or whose status = "error".lensflare:getTrace with the resolved datasetId and traceId. If it returns null, double-check the traceId with queryTelemetry (traceId = "<id>") before reporting back.summary.spanCount and summary.erroredSpanCount. If errors exist, lead with them: name + service + durationUs.spans in order. Highlight the longest span, the deepest chain, and any span whose status = "error" or whose duration is more than 50% of its parent's.relatedEvents only when they materially explain a failure (e.g. an exception event on the failing span).attributes.http.status_code = 500 and serviceName = \"api\"".npx claudepluginhub voidhashcom/lensflare --plugin lensflare-desktopAnalyzes OpenTelemetry distributed traces from Axiom to find traces by ID, errors, latency, or service. Helps debug distributed system issues.
Analyzes a single MLflow trace to debug, investigate, root-cause errors, or understand behavior. Parses trace JSON with spans, status codes, inputs/outputs, and assessments.
Investigates distributed application performance via PostHog APM / OpenTelemetry spans — trace ID lookup, slow span analysis, error-rate trends, latency distributions, service/attribute exploration.