Stats: query_loki_stats — log volume and rate analysis
Integration with Other Skills
Skill
Integration
pyats-health-check
Cross-reference pyATS health data with Grafana metrics and dashboards
pyats-routing
Correlate OSPF/BGP state changes with Grafana metric timelines
gait-session-tracking
Record all Grafana queries and findings in GAIT audit trail
slack-network-alerts
Grafana alerts fed through Slack + NetClaw for automated investigation
servicenow-change-workflow
Annotate Grafana dashboards during change windows; correlate incidents with CRs
te-network-monitoring
Pair ThousandEyes path data with Grafana infrastructure metrics
aws-cloud-monitoring
Compare Grafana dashboards with CloudWatch data for hybrid visibility
markmap-viz
Visualize Grafana alert rule hierarchies as mind maps
Context Window Management
Grafana dashboards can be large JSON documents. Use these strategies:
Always start with get_dashboard_summary — lightweight overview, not full JSON
Use get_dashboard_property with JSONPath for specific fields
Avoid get_dashboard_by_uid unless you need the complete dashboard definition
Use get_dashboard_panel_queries to extract just the query definitions
Important Rules
Prefer read-only operations — use search_dashboards, get_dashboard_summary, query_prometheus, query_loki_logs, list_alert_rules before any write operations
Token-efficient queries — use get_dashboard_summary over get_dashboard_by_uid, use time ranges to limit Prometheus/Loki result size
GAIT audit mandatory — record all Grafana queries, dashboard modifications, alert changes, and incident updates
No secrets in queries — never embed credentials or sensitive data in PromQL/LogQL expressions
Error Handling
Auth fails (401/403): Check GRAFANA_URL and GRAFANA_SERVICE_ACCOUNT_TOKEN in ~/.openclaw/.env. Verify service account has Editor role or required RBAC permissions.
Datasource not found: Use list_datasources to discover available datasource UIDs and names.
PromQL/LogQL errors: Use list_prometheus_metric_names or list_loki_label_names to discover valid metric/label names before querying.
Dashboard not found: Use search_dashboards to find dashboards by title before using UID-based tools.
Rate limiting: Grafana may rate-limit API requests; space out large query batches.