Manages Grafana Cloud resources via the gcx CLI. 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,…
Creates, updates, pulls, pushes, and deletes Synthetic Monitoring checks from YAML via gcx. Use also when the user gives a URL or hostname to monitor. For check health use synth-check-status. For a failing check use synth-investigate-check.
Inspects and manages Grafana Agent Observability resources via gcx: conversations, generations, experiments, evaluators, rules, scores, templates. Use to search or export conversations, debug an LLM conversation, or manage evaluators. For guided production…
Review someone else's gcx pull request, produce a ranked report with a verdict, and optionally post it to GitHub as line-anchored inline comments. Covers what to report, in what order, when to stop, how to rank over-engineering findings, how to judge whether…
Prepare a contribution to the gcx repository: report or fix a bug, update documentation, or propose and implement a code change. Use inside a gcx checkout for contribution routing, planning, implementation and self-review; operating a Grafana instance uses…
Investigates application problems and incidents with Grafana metrics, logs, and traces via gcx: errors, latency, regressions, blast radius, trace comparison with baselines. Accepts alert payloads, dashboard links, and trace IDs. For alert rule semantics use…
(Experimental) Runs an end-to-end observability rollout for an application on Grafana Cloud via gcx: instrumentation, SLOs, alerts, synthetic checks, k6, IRM, dashboards, cost, GitOps. Use to set up monitoring for a service from scratch. For LLM apps use…
Instruments a developer's own LLM app or repairs missing generations and empty Performance charts in Grafana Agent Observability. Applies confirmed changes and verifies generation ingest, traces, and metrics. Excludes coding-agent telemetry plugins. For…
Sets up production evaluation for a deployed AI agent in Agent Observability: online eval rules and guards (redact PII, block tools), based on its code and live traffic. Applies via gcx after confirmation. Not for pre-ship tests (use agento11y-test-starter).
Builds a starter offline test suite for an AI agent before it ships: test cases from its code, scoring advice, and a runner stub. Use when the agent has no real traffic yet. Not for tenant evaluators, rules, or guards (use agento11y-prod-setup).
Designs and creates Grafana dashboards with gcx, with `gcx dashboards snapshot` as a visual feedback loop. Use to build a new dashboard, add panels, variables, or annotations, or redesign a dashboard. Not for inventory, audit, or pull/push of existing…
Diagnoses Entity Graph (knowledge graph) problems: missing entities or services, missing edges, disconnected clusters, environment filters that do not work. Use when the Entity Graph is empty or looks wrong.
Runs a narrated, read-only demo tour of gcx across Grafana Cloud products for customer or colleague presentations. Use for "demo gcx", "gcx tour", or "customer demo".
Generates typed Go stubs and grafana-foundation-sdk builder boilerplate for dashboards and alert rules. Use only when the user asks for stubs or builder boilerplate. To design a usable dashboard, use create-dashboard.
Converts existing Grafana dashboards to Go builder code via gcx (dashboards as code). Use to import, migrate, or reverse-engineer a live dashboard into code. For YAML/JSON resource files, use manage-dashboards.
Investigates a Grafana alert rule: why it is firing or pending, its scope, and its impact. Use for a named alert rule or "why is this alert firing". For active OnCall pages (ack, silence, resolve) use oncall-triage.
Manages existing Grafana dashboards via gcx: list, search, get, audit panels, queries, datasources, and variables; apply a finished manifest; delete; versions and restore; pull/push/validate files; folders; PNG snapshots. Not for new dashboards, panels, or…
Triages active Grafana OnCall alert groups via gcx: list, inspect, acknowledge, silence, resolve. Use for "what's paging" or the on-call queue. For why an alert rule fires use investigate-alert. For schedules, integrations, or escalation chains use the gcx…
Scaffolds a new Go project for Grafana resources as code with `gcx dev scaffold`. Use to start a new dashboards-as-code repo or gcx project. Not for installing or connecting gcx (use setup-gcx).
Installs and configures gcx: contexts, authentication, connection to Grafana Cloud or on-premise Grafana, env var overrides for CI/CD, default datasources. Use for first-time setup, or when gcx fails with auth or connection errors (401, 403, connection…
Checks Grafana SLO health, error budget, and burn rate via gcx, with timeline graphs. Use for "how are my SLOs doing" or the status of one SLO. For a breaching SLO use slo-investigate. For tuning use slo-optimize. For SLO definitions use slo-manage.
Diagnoses a breaching Grafana SLO via gcx: root cause, dimensional breakdown, alert rule correlation, runbooks. Use when an SLO is breaching or burning its error budget. For a status overview use slo-check-status. For tuning use slo-optimize.
Creates, updates, pulls, pushes, and deletes Grafana SLO definitions via gcx, with dry-run validation and GitOps sync. For SLO health use slo-check-status. For a breaching SLO use slo-investigate.
Analyzes Grafana SLO timeline trends via gcx and gives advisory recommendations: objective tuning, alert sensitivity, labels, windows. Use for "optimize my SLO" or "should I change my SLO objective". For status use slo-check-status. To change definitions use…
Shows Synthetic Monitoring check health via gcx: inventory, pass/fail and success rate per check, success-rate timelines. Use for "are my checks healthy" or a named check. For a failing check use synth-investigate-check. To create or change checks use…
Diagnoses why a Synthetic Monitoring check fails: probe failures, failure scope, per-probe breakdown, root cause. Use for "why is my check failing" or "check is down". For status use synth-check-status. To create or change checks use synth-manage-checks.
Tag and release a new gcx version. Use when the user wants to cut a release, tag a version, run the release process, or says "release patch/minor/major".
Research, interview, and develop an engineering RFC from an idea, notes, or an existing draft. Use when asked to create or substantially develop an RFC; ordinary questions and small document edits do not need this workflow.
Review an engineering RFC before it is shared or accepted. Checks its claims against code and documentation, its scope against the originating request, repository rules, internal consistency and template structure, then reports author decisions, fixes and…
Reconcile an existing engineering RFC with implemented changes and verification evidence, including PoCs and verified implementation work. Run when explicitly instructed to update an RFC after verified implementation.
Regenerate the gcx marketing bento-box slide (slide.html) with verified commands from the current codebase. Builds a fresh binary and reflects against the actual command tree. Use when the user says "regenerate slide", "update slide", "generate slide", or…
Turn an idea or rough notes into a reviewable gcx feature proposal through a short interview. Use when asked to propose, draft, or file a feature or improvement.