Agent skill · data analytics · jeremylongshore
glean-observability
Track: documents indexed per run (total + new + updated + deleted),
Why this skill is useful
Provides specific metrics and alerting rules for monitoring Glean's indexing and search performance that the AI wouldn't reliably generate on its own.
What it needs
Requires glean account access. About 3k tokens when loaded. Last updated 2026-08-07. 2,604 stars on the source repository.
What this skill does
Glean Observability Overview Glean aggregates enterprise knowledge across dozens of connectors, making indexing health and search quality the two pillars of observability. Monitor connector sync status to catch stale content before users notice, track search latency to maintain sub-second responses, and measure zero-result rates to identify coverage gaps. Degraded indexing silently erodes search relevance, so proactive alerting is essential. Key Metrics Metric Type Target Alert Threshold -------- ------ -------- ----------------- Search latency p95 Histogram < 400ms > 1s Zero-result query rate Gauge < 5% > 10% Documents indexed per run Counter Stable +/-5% Drop > 20% Connector sync errors Counter 0 > 3 per hour Stale content ratio Gauge < 10% > 25% (>30 days old) Indexing throughput Gauge > 1000 docs/min < 500 docs/min Instrumentation Health Check Dashboard Alerting Rules Structured Logging Error Handling Signal Meaning Action -------- --------- -------- Connector sync failure Source API down or creds expired Check connector config, rotate tokens Zero-result spike Missing content or bad query parsing Audit indexed sources, check synonyms Indexing doc count drop Source deletion or API pagination bug Compare source counts, review API logs Search latency > 1s Overloaded cluster or complex queries Check Glean status page, review query patterns Prerequisites A data-minimization policy for logs and traces, metric owners, alert routes, retention limits, and an approved restricted evidence destination. Synthetic probes for availability, freshness, and both authorized and denied access outcomes. Correlation IDs and configuration revisions that let responders connect signals without logging query text, titles, snippets, identities, or credentials. Instructions 1. Instrument aggregate request, error, latency, freshness, queue, and ACL-probe metrics at the connector and datasource boundary. 2. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills jeremylongshore/glean-observability--90c04a