grafana-lens
Grafana tools for data visualization, monitoring, alerting, security, SRE investigation, and data collection pipeline management via Alloy. Use grafana_query, grafana_query_logs, grafana_query_traces, grafana_create_dashboard, grafana_update_dashboard, grafana_create_alert, grafana_share_dashboard, grafana_annotate, grafana_explore_datasources, grafana_list_metrics, grafana_search, grafana_get_dashboard, grafana_check_alerts, grafana_push_metrics, grafana_explain_metric, grafana_security_check, grafana_investigate, and alloy_pipeline. Trigger when asked about metrics, dashboards, monitoring, alerts, costs, token usage, data visualization, PromQL, Prometheus, LogQL, Loki, log queries, error logs, log search, TraceQL, Tempo, traces, distributed tracing, span search, find slow traces, debug session traces, annotations, deployments, sharing charts, investigating alert notifications, pushing custom data (calendar, git, fitness, finance) to Grafana for visualization, pushing historical data, backfilling metrics, recording past data with timestamps, modifying dashboards, adding panels, removing panels, changing dashboard settings, updating dashboard time range, explain metric, metric trend, what is this metric, how has this changed, is this metric normal, why did my bill spike, cost visibility, security monitoring, security check, security audit, am I being attacked, is my agent compromised, suspicious activity, threat detection, prompt injection detection, set up security alerts, investigate, debug, triage, root cause, what's wrong, why is X broken, anomaly detection, RED method, USE method, alert fatigue, postmortem, incident summary, collect metrics from, monitor my database, monitor my app, scrape endpoint, set up log collection, collect Docker logs, tail log files, collect Kubernetes logs, receive OTLP, set up trace collection, data collection pipeline, Alloy pipeline, pipeline status, pipeline health, node exporter, system metrics, postgres exporter, mysql exporter, redis exporter, syslog, Grafana Alloy.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/awsome-o/grafana-lensWhat This Skill Does
The Grafana Lens skill empowers the OpenClaw AI agent to serve as a comprehensive observability and visualization engineer. It bridges the gap between raw data and actionable insights by providing full-stack interaction with Grafana instances. Whether you are monitoring system health, analyzing financial costs, debugging distributed microservices, or auditing security events, this tool allows for seamless data retrieval and manipulation. It supports PromQL for metrics, LogQL for Loki log aggregation, and TraceQL for Tempo distributed tracing. Beyond mere queries, it can dynamically modify dashboard structures, manage alert routing, and push custom datasets for specialized analysis.
Installation
To install this skill, run the following command in your terminal:
clawhub install openclaw/skills/skills/awsome-o/grafana-lens
Use Cases
- Incident Response & Triage: Use the RED and USE methods to identify why a service is failing. Triage alerts and identify root causes with TraceQL search.
- Cost Optimization: Analyze billing metrics to understand why costs spiked and identify resource over-provisioning.
- Security Auditing: Run security checks to scan for anomalous behavior, potential threats, or unauthorized access attempts.
- Custom Data Visualization: Push external data sources—such as personal finance data, fitness tracker outputs, or Git repository statistics—to generate custom dashboards.
- Alert Management: Automatically configure webhook contact points and investigate firing alerts to minimize alert fatigue.
Example Prompts
- "Why did my AWS bill spike this morning? Use the grafana-lens to check billing metrics."
- "Investigate the current alert in the production namespace and show me the logs for the service that is failing."
- "Push my recent GitHub commit history to Grafana and create a dashboard showing my weekly coding activity."
Tips & Limitations
- Efficiency: Always prioritize direct query answers over dashboard creation. A simple numeric response is more efficient than rendering a URL.
- Datasource Discovery: Never assume a datasource UID. Always invoke
grafana_explore_datasourcesfirst to ensure accuracy. - Contextual Awareness: When investigating errors, use the statistics-first approach. Always query for counts and rates via LogQL before inspecting individual log lines to avoid data overload.
- Naming Conventions: Use the
openclaw_ext_prefix for any custom metrics you push to ensure they remain organized and easily searchable within the Grafana ecosystem.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-awsome-o-grafana-lens": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: external-api, network-access