AI Agent Workflow Collection

Use when the user wants to list or search AI Observability conversations, inspect generations, manage evaluators (create, test, delete), set up evaluation rules, check scores, or browse evaluator templates. Trigger on phrases like "list conversations", "search generations", "what did the agent do", "debug LLM conversation", "create evaluator", "set up evaluation rule", "test evaluator", "check scores", "evaluate generation quality", or "set up online evaluation".

Create a custom web dashboard (React + Vite + Express) inside your sandbox to visualize the agent's Turso database. The dashboard is served on port 3847 and the user sees it live in the "App" tab in Gooseworks. Use when the user asks for a dashboard, visualization, chart, metric view, or any custom UI powered by their agent's data.

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".

Diagnose Entity Graph problems: missing entities, missing edges, disconnected clusters, or filtering issues. Use when the user reports that Entity Graph doesn't look right, services are missing, edges aren't appearing, or environments can't be filtered. Triggers for: "entity graph is empty", "services missing from entity graph", "no edges in entity graph", "disconnected services", "can't filter entity graph", "entity graph not working", "diagnose entity graph", "debug knowledge graph".

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.

Run a narrated, read-only demo tour of gcx for customer or colleague presentations. Showcases the breadth of gcx across every Grafana Cloud product area — resources, datasources, metrics, logs, traces, SLOs, alerts, synthetic monitoring, IRM, k6, fleet, and more. All commands are strictly read-only. Trigger when the user says "demo gcx", "show off gcx", "customer demo", "gcx tour", or "/gcx-demo".

(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 when the user explicitly wants typed Go stub files, generated resource skeletons, or grafana-foundation-sdk builder boilerplate for dashboards or alert rules. This is scaffolding only; for designing or creating a usable dashboard with datasource discovery and snapshot iteration, use the create-dashboard skill instead. Triggers on "generate stub", "dashboard stub", "create alert rule stub", "foundation-sdk builder", or "builder boilerplate".

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".

Use for operational management of existing Grafana dashboards: list, get, search, create or update from an already-authored manifest, delete, inspect and restore versions, pull/push/validate/promote dashboard resource files, manage dashboard folders, or render PNG snapshots. Do NOT use when the task involves adding new panels, variables, or annotations — those require discovering real metrics or log schema, so use create-dashboard instead. For designing or creating a new dashboard, or for material visual/dashboard UX changes, also use create-dashboard.

Use when porting a Grafana Cloud product from grafana-cloud-cli (gcx) to gcx, when a bead task references gcx provider migration, or when user says "migrate provider", "port from gcx", "port oncall", "port k6". Not for building providers from scratch — use /add-provider for that.

Use when the user is triaging what is actively paging in Grafana OnCall, or asks about active alert groups, acknowledging or silencing or resolving fires, on-call queue, or "what's paging right now". Trigger on phrases like "what's paging", "on-call alerts", "ack this", "silence the page", "what's firing in OnCall", "show me active pages", or any reference to OnCall alert groups. For root cause of why a Grafana alert rule is evaluating (rule-side, pre-routing) use investigate-alert. For schedules, integrations, or escalation chains use the gcx skill.

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.

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.