Stats
Actions
Tags
From faultline
Inspects Faultline APM traces — lists slow endpoints or drills into a specific trace's span breakdown, flagging N+1 queries and dominant spans.
How this skill is triggered — by the user, by Claude, or both
Slash command
/faultline:traceThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Investigate APM traces using `list_traces` and `get_trace`.
Investigate APM traces using list_traces and get_trace.
Decide which mode from $ARGUMENTS:
No args or an endpoint string (e.g. UsersController#show):
list_traces with slow_only: true and the endpoint filter if one was given.id | endpoint | duration_ms | db_runtime_ms | db_query_count | created_at.get_trace directly on the slowest one if a single result.A numeric trace id:
get_trace with id.If either tool returns "APM is disabled. Set enable_apm = true to use trace tools.", tell the user to set c.enable_apm = true in their Faultline initializer. If it returns "APM tables not present", the migration hasn't been run yet.
npx claudepluginhub dlt/faultline --plugin faultlineAnalyzes OpenTelemetry distributed traces from Axiom to find traces by ID, errors, latency, or service. Helps debug distributed system issues.
Investigates distributed application performance via PostHog APM / OpenTelemetry spans — trace ID lookup, slow span analysis, error-rate trends, latency distributions, service/attribute exploration.
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.