gcx

Specialist agent for diagnosing application issues using Grafana observability data. Invoke when the user reports specific symptoms such as elevated error rates, latency spikes, service degradation, or complete service outages and wants systematic diagnosis using metrics, logs, and Grafana resources. <example>My API is returning 500 errors, help me debug using Grafana</example> <example>Latency has spiked on the checkout service, investigate with Prometheus</example> <example>Our service is completely down, use Grafana to figure out what happened</example> <example>Error rate is elevated on the payment service, find the root cause</example>

Structured diagnostic workflow for debugging application issues using Grafana observability data. Use when the user reports errors, latency spikes, service degradation, HTTP 500s, or wants to investigate why a service is behaving unexpectedly. Triggers for: "my API is returning 500 errors", "latency is spiking", "service seems down", "help me debug using Grafana", "investigate why requests are failing", "something is wrong with my service".

Discover what datasources, metrics, labels, and log streams are available in a Grafana instance. Use when the user asks what data exists, what metrics are available, what services are being monitored, or needs to find a datasource UID.

(Experimental) End-to-end observability setup for Grafana Cloud. Covers instrumentation, SLOs, alerting, synthetic monitoring, k6 load testing, IRM on-call, dashboards, cost optimization, and GitOps export.

Use gcx CLI to manage Grafana Cloud resources. Trigger when the user wants to inspect, create, update, delete, query, or automate any Grafana resource — dashboards, datasources, alerts, SLOs, synthetic checks, oncall, incidents, fleet, k6, knowledge graph, or adaptive telemetry.

Use when the user wants to create new Grafana dashboard or alert rule Go files from scratch, generate typed stubs, add a new dashboard to a project, or write grafana-foundation-sdk builder code. Triggers on "new dashboard", "generate dashboard", "add dashboard", "create alert rule", "generate stub", "foundation-sdk builder", "dashboard as code from scratch".

Use when the user wants to import existing Grafana dashboards as Go code, convert live dashboards to builder code, migrate dashboards to code, or reverse-engineer a dashboard from a Grafana instance. Triggers on "import dashboard", "convert to code", "dashboard as code", "export dashboard".

Investigate Grafana alerts to determine why they are firing, their scope, and impact. Use when the user asks about a specific alert, wants to understand alert behavior, or needs to diagnose why an alert is in a firing or pending state.

Use this skill when the user wants to pull dashboards from Grafana to local files, push local dashboard files to Grafana, create a new dashboard from scratch, validate dashboard files against the Grafana API schema, promote dashboards across environments (dev, staging, production), manage Grafana folders and their associated dashboards, or capture visual snapshots (screenshots/PNG images) of dashboards or individual panels. Also use this skill when the user asks about editing, deleting, or diffing dashboards, about the live development server for iterative dashboard authoring, or wants to render/export a dashboard image.

Use when the user wants to create, update, pull, push, or delete Synthetic Monitoring checks. Trigger on phrases like "create a check", "add a synthetic check", "update check", "pull my SM checks", "push checks", "delete check", or when the user provides a target URL/hostname/domain for monitoring. For check status overview use synth-check-status. For investigating failing checks use synth-investigate-check.

Use when the user wants to create a new Grafana resources-as-code project, start a new dashboards-as-code repo, scaffold a gcx project, or asks "how do I get started with gcx". Triggers on phrases like "new project", "scaffold", "bootstrap", "create project", "get started".

Use this skill to set up gcx, configure authentication, establish a connection to a Grafana instance, and complete first-time configuration. This skill covers Grafana Cloud and on-premise deployments, environment variable overrides for CI/CD, default datasource configuration, and troubleshooting connection and authentication problems.

Use when the user asks about SLO health, wants an overview of all SLOs, or needs status of a specific SLO. Trigger on phrases like "how are my SLOs doing", "SLO status", "check my SLOs", "is my SLO healthy", "SLO budget", "SLO burn rate". For investigating breaching SLOs use slo-investigate. For optimization suggestions use slo-optimize. For creating or modifying SLO definitions use slo-manage.

Use when a specific SLO is breaching or alerting and the user needs to understand why — root cause analysis, dimensional breakdown, alert rule correlation, runbook access. Trigger on phrases like "investigate SLO", "why is my SLO breaching", "SLO error budget burning", "SLO alerting". For SLO status overview use slo-check-status. For creating or modifying SLOs use slo-manage. For optimization suggestions use slo-optimize.

Use when the user wants to create, update, pull, push, or delete SLO definitions. Trigger on phrases like "create an SLO", "update SLO objective", "push SLO", "pull SLOs", "delete SLO", or "GitOps sync SLOs". For checking SLO health or status, use slo-check-status instead. For investigating a breaching SLO, use slo-investigate instead.

Use when the user wants to analyze SLO performance trends and receive improvement recommendations — objective tuning, alerting sensitivity review, label visibility, or window adjustments. Trigger on phrases like "optimize my SLO", "SLO improvement suggestions", "tune my SLO", "SLO performance analysis", or "should I change my SLO objective". For SLO status overview use slo-check-status. For investigating breaching SLOs use slo-investigate. For creating or modifying SLO definitions use slo-manage.

Use when the user asks about Synthetic Monitoring check health, status, or trends. Trigger on phrases like "are my checks healthy", "check status", "synth check", "probe status", or when users mention specific check names or IDs. For investigating failing checks use synth-investigate-check. For creating or managing checks use synth-manage-checks.

Use when the user wants to diagnose why a Synthetic Monitoring check is failing — triage probe failures, classify failure scope, run per-probe breakdown, and identify root cause. Trigger on phrases like "why is my check failing", "investigate synthetic check", "probe failures", "check is down". For check status overview use synth-check-status. For creating or managing checks use synth-manage-checks.