Terminal
Terminal/Skill
Digs through logs, traces, errors, sessions and metrics to find the root cause of a bug or unexpected behavior, with cited evidence.
By LaunchDarkly
Works with
npx skills add launchdarkly/ai-tooling --skill investigateYou are conducting a cross-product investigation. Real investigations almost always touch more than one product — a log error leads into traces, a slow trace reveals a failing span, a failing span correlates with a specific session. Walk the evidence until you have a concrete root cause.
This skill requires the remotely hosted LaunchDarkly MCP server to be configured in your environment.
Required MCP tools:
query-logs — fetch paginated log entriesquery-traces — fetch paginated trace/span entriesquery-error-groups — fetch error groups with stack traces and frequencyquery-sessions — fetch session replays with user detailsquery-aggregations — bucketed aggregations across a product type for trends and countsquery-timeline-events — pull the chronological event timeline within a sessionget-keys — discover valid attribute/grouping keys for a product typequery-logs, query-aggregations, query-traces, query-error-groups, and query-sessions, using the findings of each to sharpen the next.query-logs, query-traces, query-error-groups, and query-sessions tools return at most 50 entries per call. For larger datasets, run a query-aggregations query first to aggregate, then narrow with targeted fetches.logs.md — when the investigation touches logs (error messages, level=error filters, service log patterns)traces.md — when analyzing request flow, latency, or span relationshipserrors.md — when looking at error groups, stack traces, exception frequencysessions.md — when reconstructing user journeys or correlating frontend behavior with backend eventsmetrics.md — when aggregating across a large dataset or building a chartquery-aggregations with group_by — don't paginate through individual records. Use get-keys to discover the right grouping dimension first.get-keys before attribute filters. Attribute names vary across product types and services (spanName vs span_name, hasErrors vs has_errors). One get-keys call upfront prevents wasted queries with wrong field names.python3 or jq to extract the specific slice you need.If a tool isn't available in your environment, the corresponding MCP server may not be connected — surface that rather than working around it.