From lensflare-desktop
Translates natural-language questions about logs or telemetry into Lensflare queries using lensflare:queryTelemetry, executes them, summarizes results with counts and examples. Activates on 'find logs that…' or prose filters.
How this skill is triggered — by the user, by Claude, or both
Slash command
/lensflare-desktop:query-logsThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
You have access to a structured query language exposed via `lensflare:queryTelemetry`. The full grammar is in that tool's description — read it. Examples:
You have access to a structured query language exposed via lensflare:queryTelemetry. The full grammar is in that tool's description — read it. Examples:
serviceName = "api" and (level in ["error", "fatal"] or status = "error")durationUs >= 1000000message ~= /ECONNRESET/attributes.http.status_code = 500Steps:
lensflare:listDatasets if needed.lensflare:queryTelemetry with limit: 50 (or as requested). Use cursor from usage.nextPageCursor if the user asks for more.serviceName / level. Show a few example records inline (id, level, message or name, timestamp).Never invent fields — call queryTelemetry with no query first if you're unsure; the records show you the available shape.
npx claudepluginhub voidhashcom/lensflare --plugin lensflare-desktopQueries and analyzes Logfire telemetry data — traces, logs, spans, metrics, and SQL results. Invoked automatically when users ask to search, summarize, or debug using Logfire.
Queries OpenSearch logs using PPL for severity filtering, trace correlation, error patterns, and volume analysis in OTEL indices.
Generates LogQL queries, stream selectors, metric queries, and alerting rules for Grafana Loki via interactive workflow handling versions, labels, and use cases like debugging or dashboards.