[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-grafana-gcx-observability":3,"mdc-pwswxm-key":34,"related-repo-grafana-gcx-observability":584,"related-org-grafana-gcx-observability":689},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":23,"repoUrl":24,"updatedAt":25,"license":26,"forks":27,"topics":28,"repo":29,"sourceUrl":32,"mdContent":33},"gcx-observability","setup Grafana Cloud observability","(Experimental) End-to-end observability setup for Grafana Cloud using gcx. Covers instrumentation, SLOs, alerting, synthetic monitoring, k6 load testing, IRM on-call, dashboards, cost optimization, and GitOps export. Use when the user wants to set up observability for an application from scratch or run a full observability rollout - phrases like \"set up monitoring\", \"instrument my app\", \"add observability\", or \"onboard my service to Grafana Cloud\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},"grafana","Grafana","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fgrafana.jpg",[12,16,19,22],{"name":13,"slug":14,"type":15},"Observability","observability","tag",{"name":17,"slug":18,"type":15},"Monitoring","monitoring",{"name":20,"slug":21,"type":15},"Deployment","deployment",{"name":9,"slug":8,"type":15},430,"https:\u002F\u002Fgithub.com\u002Fgrafana\u002Fgcx","2026-07-25T05:30:38.282611",null,29,[],{"repoUrl":24,"stars":23,"forks":27,"topics":30,"description":31},[],"A CLI for managing Grafana Cloud resources. Optimized for agentic usage.","https:\u002F\u002Fgithub.com\u002Fgrafana\u002Fgcx\u002Ftree\u002FHEAD\u002Fclaude-plugin\u002Fskills\u002Fgcx-observability","---\nname: gcx-observability\ndescription: >\n  (Experimental) End-to-end observability setup for Grafana Cloud using gcx.\n  Covers instrumentation, SLOs, alerting, synthetic monitoring, k6 load\n  testing, IRM on-call, dashboards, cost optimization, and GitOps export.\n  Use when the user wants to set up observability for an application from\n  scratch or run a full observability rollout - phrases like \"set up\n  monitoring\", \"instrument my app\", \"add observability\", or \"onboard my\n  service to Grafana Cloud\".\nuser-invocable: true\nargument-hint: \"[phases]\"\nallowed-tools: Bash, Read, Write, Edit, Glob, Grep, Agent, AskUserQuestion, TaskCreate, TaskUpdate, TaskList, TaskGet\n---\n\nYou are helping the user implement comprehensive Grafana Cloud observability for their application using a **test-driven** approach. Use `gcx` to automate setup.\n\n**Test-driven observability principle:** Define what \"healthy\" looks like *before* deploying instrumentation. Every signal needs a test that can fail: SLOs express availability\u002Flatency contracts, k6 tests express load requirements with pass\u002Ffail thresholds, and synthetic checks express uptime expectations. Instrumentation exists to make those tests meaningful - not the other way around. Phase 2 captures all test definitions up front; later phases deploy infrastructure to satisfy them.\n\nWork interactively - explain each phase, generate YAML from `gcx resources list-examples \u003Ctype>` where one exists (not every kind ships an example — fall back to `gcx resources list-types \u003Ctype>` and a minimal manifest), confirm before creating anything, and validate success.\n\n**Command discovery:** Before executing any action in a phase, use `gcx \u003Cgroup> --help` to discover the exact commands and flags available. Use `gcx commands --flat -o json` to see all command groups. Never assume a command's exact syntax - always discover it first. For Kubernetes operations, use `kubectl --help` and `kubectl \u003Cverb> --help` to discover the right flags.\n\n**Parallelism rules:**\n- Use `TaskCreate` to register every unit of work before starting anything, so the user can see progress.\n- Use the `Agent` tool to run independent operations concurrently. Launch multiple agents in a single message whenever their inputs don't depend on each other.\n- Within a phase, identify which resources are independent and launch them as parallel agents. Only serialize when there is a true dependency (e.g. a contact point must exist before a notification policy references it).\n- Use background agents (`run_in_background: true`) for slow operations (k8s prep, large exports) so you can continue other work while they run.\n- After all agents in a wave complete, collect results, report to the user, and move on.\n\n---\n\n## Step 1: Select Phases\n\nIf the user passed arguments (`$ARGUMENTS`), use them directly as the selected phases - do not show the menu. `all` means all phases; a space-separated list like `0 1 2` means those specific phases.\n\nOtherwise, show the following menu and ask which phases to run:\n\n```\nGrafana Cloud Observability Setup\n══════════════════════════════════\n\n  Phase 0   Bootstrap              Verify gcx config + stack auth\n  Phase 1   Discovery & Context    Gather app info (clusters, namespaces, journeys)\n  Phase 2   Test Definitions       Define SLOs, k6 thresholds, synthetic checks FIRST\n  Phase 3   Instrumentation        Alloy collector, setup instrumentation, Faro frontend\n  Phase 4   SLO-Based Alerting     Wire alert rules, contact points, policies\n  Phase 5   Synthetic Monitoring   Deploy uptime checks (defined in Phase 2)\n  Phase 6   k6 Load Testing        Deploy load tests + schedules (defined in Phase 2)\n  Phase 7   IRM Setup              Oncall integrations, escalation chains, schedules\n  Phase 8   Custom Dashboards      Dashboards via gcx resources push\n  Phase 9   Cost Optimization      Adaptive metrics\u002Flogs\u002Ftraces for cardinality control\n  Phase 10  GitOps Export          Export managed resources as declarative YAML\n  Phase 11  Observability Review   Validate signals, find gaps, recommend next steps\n\nEnter phases to run (e.g. \"0 1 2\" or \"all\"):\n```\n\nOnce phases are selected, **immediately create a task for every selected phase** using `TaskCreate` before executing anything. This gives the user a live progress view.\n\n---\n\n## Step 2: Execute Selected Phases\n\nPhases have dependencies:\n- Phase 0 must complete before anything else.\n- Phase 1 must complete before Phases 2-11 (provides context).\n- Phase 2 must complete before Phases 3-6 (test definitions drive instrumentation and alerting).\n- Phase 3 should complete before Phase 4 (signals must flow before SLOs are meaningful).\n- Phase 4 must complete before Phase 7 (IRM wires into alerting contact points).\n- Phases 5, 6, 8, 9 are independent of each other and of Phase 7 - run them in parallel after Phase 3.\n- Phase 10 must be last (exports everything created).\n- Phase 11 must be last (validates everything).\n\n**Verification principle:** After every create operation, verify the resource exists and is healthy using list or get. Do not mark a phase completed until all resources pass verification. If a resource fails verification, debug before moving on.\n\n**Idempotency principle:** At the start of every phase, check what already exists before creating anything. If a resource with the expected name already exists, skip creation and go straight to verification. If a phase is partially complete, resume from the first missing resource - never re-create resources that are already healthy.\n\n**Recommended parallel execution plan (after Phases 0-3):**\n\n```\nWave A (parallel): Phases 4, 5, 6, 8, 9\nWave B (after Wave A): Phase 7  (needs Phase 4 contact points)\nWave C (after Wave B): Phases 10, 11  (parallel with each other)\n```\n\nLaunch Wave A agents in a single message. Do not wait for one to finish before starting another.\n\nWithin each phase, also parallelize at the resource level (see the per-phase instructions in references\u002F).\n\n---\n\n## Phase Instructions\n\nThe detailed per-phase instructions (pre-checks, commands, parallel agent breakdowns, verification steps) live in reference files. Read the file covering a phase before executing it - e.g. read `phases-0-3-foundation.md` at the start, and `phases-4-7-alerting.md` when Wave A begins.\n\n| Phases | Read | Covers |\n|--------|------|--------|\n| 0-3 | [references\u002Fphases-0-3-foundation.md](references\u002Fphases-0-3-foundation.md) | Bootstrap, discovery & context, test definitions, instrumentation |\n| 4-7 | [references\u002Fphases-4-7-alerting.md](references\u002Fphases-4-7-alerting.md) | SLO-based alerting, synthetic monitoring, k6 load testing, IRM |\n| 8-11 | [references\u002Fphases-8-11-finalize.md](references\u002Fphases-8-11-finalize.md) | Custom dashboards, cost optimization, GitOps export, review |\n\n---\n\n## Final Summary\n\nAfter all tasks are completed:\n\n1. Call `TaskList` to confirm all tasks are marked completed.\n2. Show a summary table:\n\n```\nResource Type              Count   Status\n─────────────────────────────────────────\nSLOs                         3     ok\nAlerting rule groups         4     ok\nContact points               1     ok\nSynthetic checks             5     ok\nk6 tests                     3     ok\nk6 schedules                 3     ok  (every test must have one)\nIRM integrations             1     ok\nFaro apps                    1     ok  (if frontend stack)\nDashboards                   4     ok\nAdaptive metrics rules       N     ok\nAdaptive logs rules          N     ok\n...\n```\n\n3. Show stack URL from `gcx config view`.\n4. Next recommended action: commit the export directory and add the CI drift-check step.\n",{"data":35,"body":39},{"name":4,"description":6,"user-invocable":36,"argument-hint":37,"allowed-tools":38},true,"[phases]","Bash, Read, Write, Edit, Glob, Grep, Agent, AskUserQuestion, TaskCreate, TaskUpdate, TaskList, TaskGet",{"type":40,"children":41},"root",[42,67,85,106,148,156,210,214,221,250,255,267,286,289,295,300,343,353,363,371,380,385,390,393,399,420,517,520,526,531,553,562],{"type":43,"tag":44,"props":45,"children":46},"element","p",{},[47,50,56,58,65],{"type":48,"value":49},"text","You are helping the user implement comprehensive Grafana Cloud observability for their application using a ",{"type":43,"tag":51,"props":52,"children":53},"strong",{},[54],{"type":48,"value":55},"test-driven",{"type":48,"value":57}," approach. Use ",{"type":43,"tag":59,"props":60,"children":62},"code",{"className":61},[],[63],{"type":48,"value":64},"gcx",{"type":48,"value":66}," to automate setup.",{"type":43,"tag":44,"props":68,"children":69},{},[70,75,77,83],{"type":43,"tag":51,"props":71,"children":72},{},[73],{"type":48,"value":74},"Test-driven observability principle:",{"type":48,"value":76}," Define what \"healthy\" looks like ",{"type":43,"tag":78,"props":79,"children":80},"em",{},[81],{"type":48,"value":82},"before",{"type":48,"value":84}," deploying instrumentation. Every signal needs a test that can fail: SLOs express availability\u002Flatency contracts, k6 tests express load requirements with pass\u002Ffail thresholds, and synthetic checks express uptime expectations. Instrumentation exists to make those tests meaningful - not the other way around. Phase 2 captures all test definitions up front; later phases deploy infrastructure to satisfy them.",{"type":43,"tag":44,"props":86,"children":87},{},[88,90,96,98,104],{"type":48,"value":89},"Work interactively - explain each phase, generate YAML from ",{"type":43,"tag":59,"props":91,"children":93},{"className":92},[],[94],{"type":48,"value":95},"gcx resources list-examples \u003Ctype>",{"type":48,"value":97}," where one exists (not every kind ships an example — fall back to ",{"type":43,"tag":59,"props":99,"children":101},{"className":100},[],[102],{"type":48,"value":103},"gcx resources list-types \u003Ctype>",{"type":48,"value":105}," and a minimal manifest), confirm before creating anything, and validate success.",{"type":43,"tag":44,"props":107,"children":108},{},[109,114,116,122,124,130,132,138,140,146],{"type":43,"tag":51,"props":110,"children":111},{},[112],{"type":48,"value":113},"Command discovery:",{"type":48,"value":115}," Before executing any action in a phase, use ",{"type":43,"tag":59,"props":117,"children":119},{"className":118},[],[120],{"type":48,"value":121},"gcx \u003Cgroup> --help",{"type":48,"value":123}," to discover the exact commands and flags available. Use ",{"type":43,"tag":59,"props":125,"children":127},{"className":126},[],[128],{"type":48,"value":129},"gcx commands --flat -o json",{"type":48,"value":131}," to see all command groups. Never assume a command's exact syntax - always discover it first. For Kubernetes operations, use ",{"type":43,"tag":59,"props":133,"children":135},{"className":134},[],[136],{"type":48,"value":137},"kubectl --help",{"type":48,"value":139}," and ",{"type":43,"tag":59,"props":141,"children":143},{"className":142},[],[144],{"type":48,"value":145},"kubectl \u003Cverb> --help",{"type":48,"value":147}," to discover the right flags.",{"type":43,"tag":44,"props":149,"children":150},{},[151],{"type":43,"tag":51,"props":152,"children":153},{},[154],{"type":48,"value":155},"Parallelism rules:",{"type":43,"tag":157,"props":158,"children":159},"ul",{},[160,174,187,192,205],{"type":43,"tag":161,"props":162,"children":163},"li",{},[164,166,172],{"type":48,"value":165},"Use ",{"type":43,"tag":59,"props":167,"children":169},{"className":168},[],[170],{"type":48,"value":171},"TaskCreate",{"type":48,"value":173}," to register every unit of work before starting anything, so the user can see progress.",{"type":43,"tag":161,"props":175,"children":176},{},[177,179,185],{"type":48,"value":178},"Use the ",{"type":43,"tag":59,"props":180,"children":182},{"className":181},[],[183],{"type":48,"value":184},"Agent",{"type":48,"value":186}," tool to run independent operations concurrently. Launch multiple agents in a single message whenever their inputs don't depend on each other.",{"type":43,"tag":161,"props":188,"children":189},{},[190],{"type":48,"value":191},"Within a phase, identify which resources are independent and launch them as parallel agents. Only serialize when there is a true dependency (e.g. a contact point must exist before a notification policy references it).",{"type":43,"tag":161,"props":193,"children":194},{},[195,197,203],{"type":48,"value":196},"Use background agents (",{"type":43,"tag":59,"props":198,"children":200},{"className":199},[],[201],{"type":48,"value":202},"run_in_background: true",{"type":48,"value":204},") for slow operations (k8s prep, large exports) so you can continue other work while they run.",{"type":43,"tag":161,"props":206,"children":207},{},[208],{"type":48,"value":209},"After all agents in a wave complete, collect results, report to the user, and move on.",{"type":43,"tag":211,"props":212,"children":213},"hr",{},[],{"type":43,"tag":215,"props":216,"children":218},"h2",{"id":217},"step-1-select-phases",[219],{"type":48,"value":220},"Step 1: Select Phases",{"type":43,"tag":44,"props":222,"children":223},{},[224,226,232,234,240,242,248],{"type":48,"value":225},"If the user passed arguments (",{"type":43,"tag":59,"props":227,"children":229},{"className":228},[],[230],{"type":48,"value":231},"$ARGUMENTS",{"type":48,"value":233},"), use them directly as the selected phases - do not show the menu. ",{"type":43,"tag":59,"props":235,"children":237},{"className":236},[],[238],{"type":48,"value":239},"all",{"type":48,"value":241}," means all phases; a space-separated list like ",{"type":43,"tag":59,"props":243,"children":245},{"className":244},[],[246],{"type":48,"value":247},"0 1 2",{"type":48,"value":249}," means those specific phases.",{"type":43,"tag":44,"props":251,"children":252},{},[253],{"type":48,"value":254},"Otherwise, show the following menu and ask which phases to run:",{"type":43,"tag":256,"props":257,"children":261},"pre",{"className":258,"code":260,"language":48},[259],"language-text","Grafana Cloud Observability Setup\n══════════════════════════════════\n\n  Phase 0   Bootstrap              Verify gcx config + stack auth\n  Phase 1   Discovery & Context    Gather app info (clusters, namespaces, journeys)\n  Phase 2   Test Definitions       Define SLOs, k6 thresholds, synthetic checks FIRST\n  Phase 3   Instrumentation        Alloy collector, setup instrumentation, Faro frontend\n  Phase 4   SLO-Based Alerting     Wire alert rules, contact points, policies\n  Phase 5   Synthetic Monitoring   Deploy uptime checks (defined in Phase 2)\n  Phase 6   k6 Load Testing        Deploy load tests + schedules (defined in Phase 2)\n  Phase 7   IRM Setup              Oncall integrations, escalation chains, schedules\n  Phase 8   Custom Dashboards      Dashboards via gcx resources push\n  Phase 9   Cost Optimization      Adaptive metrics\u002Flogs\u002Ftraces for cardinality control\n  Phase 10  GitOps Export          Export managed resources as declarative YAML\n  Phase 11  Observability Review   Validate signals, find gaps, recommend next steps\n\nEnter phases to run (e.g. \"0 1 2\" or \"all\"):\n",[262],{"type":43,"tag":59,"props":263,"children":265},{"__ignoreMap":264},"",[266],{"type":48,"value":260},{"type":43,"tag":44,"props":268,"children":269},{},[270,272,277,279,284],{"type":48,"value":271},"Once phases are selected, ",{"type":43,"tag":51,"props":273,"children":274},{},[275],{"type":48,"value":276},"immediately create a task for every selected phase",{"type":48,"value":278}," using ",{"type":43,"tag":59,"props":280,"children":282},{"className":281},[],[283],{"type":48,"value":171},{"type":48,"value":285}," before executing anything. This gives the user a live progress view.",{"type":43,"tag":211,"props":287,"children":288},{},[],{"type":43,"tag":215,"props":290,"children":292},{"id":291},"step-2-execute-selected-phases",[293],{"type":48,"value":294},"Step 2: Execute Selected Phases",{"type":43,"tag":44,"props":296,"children":297},{},[298],{"type":48,"value":299},"Phases have dependencies:",{"type":43,"tag":157,"props":301,"children":302},{},[303,308,313,318,323,328,333,338],{"type":43,"tag":161,"props":304,"children":305},{},[306],{"type":48,"value":307},"Phase 0 must complete before anything else.",{"type":43,"tag":161,"props":309,"children":310},{},[311],{"type":48,"value":312},"Phase 1 must complete before Phases 2-11 (provides context).",{"type":43,"tag":161,"props":314,"children":315},{},[316],{"type":48,"value":317},"Phase 2 must complete before Phases 3-6 (test definitions drive instrumentation and alerting).",{"type":43,"tag":161,"props":319,"children":320},{},[321],{"type":48,"value":322},"Phase 3 should complete before Phase 4 (signals must flow before SLOs are meaningful).",{"type":43,"tag":161,"props":324,"children":325},{},[326],{"type":48,"value":327},"Phase 4 must complete before Phase 7 (IRM wires into alerting contact points).",{"type":43,"tag":161,"props":329,"children":330},{},[331],{"type":48,"value":332},"Phases 5, 6, 8, 9 are independent of each other and of Phase 7 - run them in parallel after Phase 3.",{"type":43,"tag":161,"props":334,"children":335},{},[336],{"type":48,"value":337},"Phase 10 must be last (exports everything created).",{"type":43,"tag":161,"props":339,"children":340},{},[341],{"type":48,"value":342},"Phase 11 must be last (validates everything).",{"type":43,"tag":44,"props":344,"children":345},{},[346,351],{"type":43,"tag":51,"props":347,"children":348},{},[349],{"type":48,"value":350},"Verification principle:",{"type":48,"value":352}," After every create operation, verify the resource exists and is healthy using list or get. Do not mark a phase completed until all resources pass verification. If a resource fails verification, debug before moving on.",{"type":43,"tag":44,"props":354,"children":355},{},[356,361],{"type":43,"tag":51,"props":357,"children":358},{},[359],{"type":48,"value":360},"Idempotency principle:",{"type":48,"value":362}," At the start of every phase, check what already exists before creating anything. If a resource with the expected name already exists, skip creation and go straight to verification. If a phase is partially complete, resume from the first missing resource - never re-create resources that are already healthy.",{"type":43,"tag":44,"props":364,"children":365},{},[366],{"type":43,"tag":51,"props":367,"children":368},{},[369],{"type":48,"value":370},"Recommended parallel execution plan (after Phases 0-3):",{"type":43,"tag":256,"props":372,"children":375},{"className":373,"code":374,"language":48},[259],"Wave A (parallel): Phases 4, 5, 6, 8, 9\nWave B (after Wave A): Phase 7  (needs Phase 4 contact points)\nWave C (after Wave B): Phases 10, 11  (parallel with each other)\n",[376],{"type":43,"tag":59,"props":377,"children":378},{"__ignoreMap":264},[379],{"type":48,"value":374},{"type":43,"tag":44,"props":381,"children":382},{},[383],{"type":48,"value":384},"Launch Wave A agents in a single message. Do not wait for one to finish before starting another.",{"type":43,"tag":44,"props":386,"children":387},{},[388],{"type":48,"value":389},"Within each phase, also parallelize at the resource level (see the per-phase instructions in references\u002F).",{"type":43,"tag":211,"props":391,"children":392},{},[],{"type":43,"tag":215,"props":394,"children":396},{"id":395},"phase-instructions",[397],{"type":48,"value":398},"Phase Instructions",{"type":43,"tag":44,"props":400,"children":401},{},[402,404,410,412,418],{"type":48,"value":403},"The detailed per-phase instructions (pre-checks, commands, parallel agent breakdowns, verification steps) live in reference files. Read the file covering a phase before executing it - e.g. read ",{"type":43,"tag":59,"props":405,"children":407},{"className":406},[],[408],{"type":48,"value":409},"phases-0-3-foundation.md",{"type":48,"value":411}," at the start, and ",{"type":43,"tag":59,"props":413,"children":415},{"className":414},[],[416],{"type":48,"value":417},"phases-4-7-alerting.md",{"type":48,"value":419}," when Wave A begins.",{"type":43,"tag":421,"props":422,"children":423},"table",{},[424,448],{"type":43,"tag":425,"props":426,"children":427},"thead",{},[428],{"type":43,"tag":429,"props":430,"children":431},"tr",{},[432,438,443],{"type":43,"tag":433,"props":434,"children":435},"th",{},[436],{"type":48,"value":437},"Phases",{"type":43,"tag":433,"props":439,"children":440},{},[441],{"type":48,"value":442},"Read",{"type":43,"tag":433,"props":444,"children":445},{},[446],{"type":48,"value":447},"Covers",{"type":43,"tag":449,"props":450,"children":451},"tbody",{},[452,475,496],{"type":43,"tag":429,"props":453,"children":454},{},[455,461,470],{"type":43,"tag":456,"props":457,"children":458},"td",{},[459],{"type":48,"value":460},"0-3",{"type":43,"tag":456,"props":462,"children":463},{},[464],{"type":43,"tag":465,"props":466,"children":468},"a",{"href":467},"references\u002Fphases-0-3-foundation.md",[469],{"type":48,"value":467},{"type":43,"tag":456,"props":471,"children":472},{},[473],{"type":48,"value":474},"Bootstrap, discovery & context, test definitions, instrumentation",{"type":43,"tag":429,"props":476,"children":477},{},[478,483,491],{"type":43,"tag":456,"props":479,"children":480},{},[481],{"type":48,"value":482},"4-7",{"type":43,"tag":456,"props":484,"children":485},{},[486],{"type":43,"tag":465,"props":487,"children":489},{"href":488},"references\u002Fphases-4-7-alerting.md",[490],{"type":48,"value":488},{"type":43,"tag":456,"props":492,"children":493},{},[494],{"type":48,"value":495},"SLO-based alerting, synthetic monitoring, k6 load testing, IRM",{"type":43,"tag":429,"props":497,"children":498},{},[499,504,512],{"type":43,"tag":456,"props":500,"children":501},{},[502],{"type":48,"value":503},"8-11",{"type":43,"tag":456,"props":505,"children":506},{},[507],{"type":43,"tag":465,"props":508,"children":510},{"href":509},"references\u002Fphases-8-11-finalize.md",[511],{"type":48,"value":509},{"type":43,"tag":456,"props":513,"children":514},{},[515],{"type":48,"value":516},"Custom dashboards, cost optimization, GitOps export, review",{"type":43,"tag":211,"props":518,"children":519},{},[],{"type":43,"tag":215,"props":521,"children":523},{"id":522},"final-summary",[524],{"type":48,"value":525},"Final Summary",{"type":43,"tag":44,"props":527,"children":528},{},[529],{"type":48,"value":530},"After all tasks are completed:",{"type":43,"tag":532,"props":533,"children":534},"ol",{},[535,548],{"type":43,"tag":161,"props":536,"children":537},{},[538,540,546],{"type":48,"value":539},"Call ",{"type":43,"tag":59,"props":541,"children":543},{"className":542},[],[544],{"type":48,"value":545},"TaskList",{"type":48,"value":547}," to confirm all tasks are marked completed.",{"type":43,"tag":161,"props":549,"children":550},{},[551],{"type":48,"value":552},"Show a summary table:",{"type":43,"tag":256,"props":554,"children":557},{"className":555,"code":556,"language":48},[259],"Resource Type              Count   Status\n─────────────────────────────────────────\nSLOs                         3     ok\nAlerting rule groups         4     ok\nContact points               1     ok\nSynthetic checks             5     ok\nk6 tests                     3     ok\nk6 schedules                 3     ok  (every test must have one)\nIRM integrations             1     ok\nFaro apps                    1     ok  (if frontend stack)\nDashboards                   4     ok\nAdaptive metrics rules       N     ok\nAdaptive logs rules          N     ok\n...\n",[558],{"type":43,"tag":59,"props":559,"children":560},{"__ignoreMap":264},[561],{"type":48,"value":556},{"type":43,"tag":532,"props":563,"children":565},{"start":564},3,[566,579],{"type":43,"tag":161,"props":567,"children":568},{},[569,571,577],{"type":48,"value":570},"Show stack URL from ",{"type":43,"tag":59,"props":572,"children":574},{"className":573},[],[575],{"type":48,"value":576},"gcx config view",{"type":48,"value":578},".",{"type":43,"tag":161,"props":580,"children":581},{},[582],{"type":48,"value":583},"Next recommended action: commit the export directory and add the CI drift-check step.",{"items":585,"total":688},[586,599,615,628,643,660,675],{"slug":587,"name":587,"fn":588,"description":589,"org":590,"tags":591,"stars":23,"repoUrl":24,"updatedAt":598},"agento11y","manage Grafana Agent Observability resources","Inspects and manages Grafana Agent Observability resources via gcx: conversations, generations, evaluators, rules, scores, and templates. Use when the user wants to list or search conversations, inspect generations, manage evaluators (upsert, 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\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[592,595,596,597],{"name":593,"slug":594,"type":15},"Agents","agents",{"name":9,"slug":8,"type":15},{"name":17,"slug":18,"type":15},{"name":13,"slug":14,"type":15},"2026-07-25T05:30:40.29622",{"slug":600,"name":600,"fn":601,"description":602,"org":603,"tags":604,"stars":23,"repoUrl":24,"updatedAt":614},"agento11y-instrument","instrument LLM apps for agent observability","Sets up and instruments a developer's own LLM app or agent to send generations and agentic workflow to Grafana Agent Observability (the Agent Observability SDKs) — greenfield setup, fixing broken instrumentation, or filling gaps in existing instrumentation. Uses gcx for the parts a static prompt can't do: `gcx login` \u002F `gcx cloud stacks` to find the stack, and `gcx agento11y agents|conversations|generations` to VERIFY that data actually lands — so it iterates (instrument → run → verify → fix) until generations arrive, not blindly. Reads the app's code, detects language\u002Fframework, classifies instrumentation state (none \u002F partial \u002F broken), then runs a fixed gap checklist whose #1 item is the silent failure no other prompt catches: the SDK emits OTel spans\u002Fmetrics but never creates a TracerProvider\u002FMeterProvider, so without them all metrics go to a no-op and are lost. Also checks agent_version (required for per-version Performance charts), set_result completeness, SYNC vs STREAM, parent_generation_ids DAG links, and workflow-step coverage. Recommends changes citing file:line and, only with explicit confirmation, applies minimal diffs that don't change app behavior. Pulls SDK reference from agento11y's llms.txt rather than restating it, and hands off to `agento11y-test-starter` once data flows. It does NOT write test suites or set up tenant evaluations, rules, or guards — offline test suites are `agento11y-test-starter`, tenant eval rules + guards are `agento11y-prod-setup`; does NOT install coding-agent telemetry plugins (that is llms.txt \"Path A\"); does NOT mint or store credentials or invent endpoints. Trigger on phrases like \"instrument my app\", \"send my agent's traces to Grafana\", \"set up AI observability for my app\", \"my generations aren't showing up\", \"why is Performance empty\", \"add Agent Observability to my code\", \"fix my instrumentation\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[605,606,607,610,613],{"name":593,"slug":594,"type":15},{"name":9,"slug":8,"type":15},{"name":608,"slug":609,"type":15},"Instrumentation","instrumentation",{"name":611,"slug":612,"type":15},"LLM","llm",{"name":13,"slug":14,"type":15},"2026-07-31T05:53:52.580237",{"slug":616,"name":616,"fn":617,"description":618,"org":619,"tags":620,"stars":23,"repoUrl":24,"updatedAt":627},"agento11y-prod-setup","setup production evaluation for AI agents","Sets up production evaluation and guardrails for a DEPLOYED AI agent in Grafana Agent Observability, grounded in the agent's own code and its real ingested traffic. The judgment layer on top of the `agento11y` skill: it reads the agent's source (system prompt, tools, entrypoint) AND samples its live traffic via gcx, checks what evaluators\u002Frules\u002Fguards already exist, then recommends only what's missing — online eval rules (score live conversations for regressions) and guards (warn-first request-path policies that redact \u002F tool-filter and may later be promoted to deny). It drafts reviewable YAML and, only with explicit confirmation, applies via `gcx agento11y`. New guards are drafted in warn mode (safe on live traffic — warn records but never blocks). It DOES create stack-level objects — that is the point — but every write is confirmed. It never rewrites or redeploys the agent. Trigger on phrases like \"set up production evaluation\", \"my agent is in prod what should I evaluate\", \"catch quality regressions\", \"add guardrails to my agent\", \"redact PII from my agent\", \"block dangerous tools\", \"set up online evals and guards\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[621,622,625,626],{"name":593,"slug":594,"type":15},{"name":623,"slug":624,"type":15},"Evals","evals",{"name":9,"slug":8,"type":15},{"name":13,"slug":14,"type":15},"2026-07-31T05:53:53.576347",{"slug":629,"name":629,"fn":630,"description":631,"org":632,"tags":633,"stars":23,"repoUrl":24,"updatedAt":642},"agento11y-test-starter","build and run agent test suites","Use early in an AI-agent project — before ship, before real traffic — to build a starter test suite for the agent and run it offline. Reads the agent's own code (system prompt, tools, task), writes a labeled draft suite of test cases (happy\u002Fedge\u002Fadversarial) grounded in real lines, and recommends how to score each case (the evaluators\u002Fjudges the offline runner uses). Assesses how runnable the agent is: for an easily-invoked agent it generates a runner stub (run_experiment.py) with two holes to fill and can optionally run it (only with permission, only against the endpoint the developer configured); for agents needing a harness or full runtime it points to the existing eval infra. It runs OFFLINE and never creates tenant-level evaluators, rules, or guards — that is `agento11y-prod-setup`, for a deployed agent with real traffic. Trigger on phrases like \"how do I test my agent before shipping\", \"write test cases for my agent\", \"set up tests for my agent\", \"check my agent before prod\", \"I have no traffic yet, how do I evaluate it\", \"test my agent offline\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[634,635,636,639],{"name":593,"slug":594,"type":15},{"name":9,"slug":8,"type":15},{"name":637,"slug":638,"type":15},"QA","qa",{"name":640,"slug":641,"type":15},"Testing","testing","2026-07-31T05:53:51.62785",{"slug":644,"name":644,"fn":645,"description":646,"org":647,"tags":648,"stars":23,"repoUrl":24,"updatedAt":659},"create-dashboard","create Grafana dashboards with gcx","Designs and creates Grafana dashboards with gcx, using `gcx dashboards snapshot` as a visual feedback loop. Use when the user wants to create a new Grafana dashboard, add panels, variables, or annotations to an existing dashboard, design dashboard panels, variables, queries, or layout, or make a material visual redesign. Triggers on \"create dashboard\", \"new dashboard\", \"build dashboard\", \"dashboard for \u003Cservice>\", \"add panels\", \"add variable\", \"add annotation\", \"improve this dashboard\", or \"iterate on a dashboard\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[649,652,655,658],{"name":650,"slug":651,"type":15},"Dashboards","dashboards",{"name":653,"slug":654,"type":15},"Data Visualization","data-visualization",{"name":656,"slug":657,"type":15},"Design","design",{"name":9,"slug":8,"type":15},"2026-07-25T05:30:46.289717",{"slug":661,"name":661,"fn":662,"description":663,"org":664,"tags":665,"stars":23,"repoUrl":24,"updatedAt":674},"debug-with-grafana","investigate application issues with Grafana","Structured workflow for investigating application problems with Grafana observability data (metrics, logs, traces) via gcx. Covers live firefighting AND retrospective incident analysis: incident triage, root-cause analysis, blast-radius checks (did an incident spill into other services), verifying whether a deployment or rollout triggered an incident, finding which service, endpoint, or path owns the most errors or slow requests, checking whether retries or queue backlogs piled up, and quantifying error or latency shares over a time window. Trigger on: \"my API is returning 500 errors\", \"latency is spiking\", \"investigate why requests are failing\", \"triage the incident\", \"blast radius\", \"root cause\", \"did the rollout cause it\", \"which endpoint owns the most 5xx\", \"did retries pile up\", or any request to analyse an earlier incident window using telemetry. For authoring dashboards use create-dashboard; for dashboard inventory use manage-dashboards.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[666,669,670,673],{"name":667,"slug":668,"type":15},"Debugging","debugging",{"name":9,"slug":8,"type":15},{"name":671,"slug":672,"type":15},"Incident Response","incident-response",{"name":13,"slug":14,"type":15},"2026-07-18T05:11:10.445428",{"slug":676,"name":676,"fn":677,"description":678,"org":679,"tags":680,"stars":23,"repoUrl":24,"updatedAt":687},"diagnose-entity-graph","diagnose Grafana Entity Graph issues","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\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[681,682,683,686],{"name":667,"slug":668,"type":15},{"name":9,"slug":8,"type":15},{"name":684,"slug":685,"type":15},"Graph Analysis","graph-analysis",{"name":13,"slug":14,"type":15},"2026-07-25T05:30:39.380934",24,{"items":690,"total":823},[691,708,727,747,754,762,769,776,783,790,797,811],{"slug":692,"name":692,"fn":693,"description":694,"org":695,"tags":696,"stars":705,"repoUrl":706,"updatedAt":707},"faro-setup-web","instrument web apps with Grafana Faro","Instruments a web app with Grafana Faro Web SDK for frontend observability. Use when setting up error tracking, Web Vitals, session monitoring, or distributed tracing in a browser app.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[697,700,703,704],{"name":698,"slug":699,"type":15},"Distributed Tracing","distributed-tracing",{"name":701,"slug":702,"type":15},"Frontend","frontend",{"name":17,"slug":18,"type":15},{"name":13,"slug":14,"type":15},1103,"https:\u002F\u002Fgithub.com\u002Fgrafana\u002Ffaro-web-sdk","2026-07-12T07:43:24.63314",{"slug":709,"name":709,"fn":710,"description":711,"org":712,"tags":713,"stars":724,"repoUrl":725,"updatedAt":726},"configuring-yesoreyeram-infinity-datasource","configure Grafana Infinity data source","Configure the Infinity data source — base URL and allowed hosts, the authentication methods (basic, bearer token, API key, digest, OAuth passthrough, OAuth 2.0 client credentials\u002FJWT, Azure, Azure Blob, AWS), TLS, custom HTTP headers, network and security settings, the custom health check, and provisioning with a config file. Use when a user asks how to set up, configure, or change settings for the Infinity data source; how to authenticate to an API; how to allow hosts; how to provision it as YAML; or how to troubleshoot connection, authentication, or health-check issues.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[714,717,720,723],{"name":715,"slug":716,"type":15},"API Development","api-development",{"name":718,"slug":719,"type":15},"Authentication","authentication",{"name":721,"slug":722,"type":15},"Configuration","configuration",{"name":9,"slug":8,"type":15},1056,"https:\u002F\u002Fgithub.com\u002Fgrafana\u002Fgrafana-infinity-datasource","2026-07-12T07:43:25.939136",{"slug":728,"name":728,"fn":729,"description":730,"org":731,"tags":732,"stars":724,"repoUrl":725,"updatedAt":746},"querying-yesoreyeram-infinity-datasource","query data with Infinity datasource","Build queries with the Infinity data source — the query types (JSON, CSV, TSV, XML, GraphQL, HTML, UQL, GROQ, Google Sheets, Series, Transformations), the parsers (Frontend\u002Fsimple, Backend JSONata, JQ, UQL, GROQ) and which support alerting, the sources (URL, Inline, Reference, Azure Blob, Random walk), output formats (table, timeseries, logs, trace, node graph, dataframe), root selector and columns, computed columns\u002Ffilters\u002Fsummarize, pagination, and template variables. Use when a user asks how to query Infinity; how to fetch JSON\u002FCSV\u002FXML\u002FGraphQL\u002FHTML from a URL or inline; how to select rows and columns; how to transform data with UQL\u002FGROQ\u002FJSONata\u002FJQ; how to make a query work with alerting; how to paginate; or how to use variables in a query.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[733,736,739,740,743],{"name":734,"slug":735,"type":15},"CSV","csv",{"name":737,"slug":738,"type":15},"Data Analysis","data-analysis",{"name":9,"slug":8,"type":15},{"name":741,"slug":742,"type":15},"GraphQL","graphql",{"name":744,"slug":745,"type":15},"JSON","json","2026-07-15T05:34:05.773947",{"slug":587,"name":587,"fn":588,"description":589,"org":748,"tags":749,"stars":23,"repoUrl":24,"updatedAt":598},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[750,751,752,753],{"name":593,"slug":594,"type":15},{"name":9,"slug":8,"type":15},{"name":17,"slug":18,"type":15},{"name":13,"slug":14,"type":15},{"slug":600,"name":600,"fn":601,"description":602,"org":755,"tags":756,"stars":23,"repoUrl":24,"updatedAt":614},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[757,758,759,760,761],{"name":593,"slug":594,"type":15},{"name":9,"slug":8,"type":15},{"name":608,"slug":609,"type":15},{"name":611,"slug":612,"type":15},{"name":13,"slug":14,"type":15},{"slug":616,"name":616,"fn":617,"description":618,"org":763,"tags":764,"stars":23,"repoUrl":24,"updatedAt":627},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[765,766,767,768],{"name":593,"slug":594,"type":15},{"name":623,"slug":624,"type":15},{"name":9,"slug":8,"type":15},{"name":13,"slug":14,"type":15},{"slug":629,"name":629,"fn":630,"description":631,"org":770,"tags":771,"stars":23,"repoUrl":24,"updatedAt":642},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[772,773,774,775],{"name":593,"slug":594,"type":15},{"name":9,"slug":8,"type":15},{"name":637,"slug":638,"type":15},{"name":640,"slug":641,"type":15},{"slug":644,"name":644,"fn":645,"description":646,"org":777,"tags":778,"stars":23,"repoUrl":24,"updatedAt":659},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[779,780,781,782],{"name":650,"slug":651,"type":15},{"name":653,"slug":654,"type":15},{"name":656,"slug":657,"type":15},{"name":9,"slug":8,"type":15},{"slug":661,"name":661,"fn":662,"description":663,"org":784,"tags":785,"stars":23,"repoUrl":24,"updatedAt":674},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[786,787,788,789],{"name":667,"slug":668,"type":15},{"name":9,"slug":8,"type":15},{"name":671,"slug":672,"type":15},{"name":13,"slug":14,"type":15},{"slug":676,"name":676,"fn":677,"description":678,"org":791,"tags":792,"stars":23,"repoUrl":24,"updatedAt":687},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[793,794,795,796],{"name":667,"slug":668,"type":15},{"name":9,"slug":8,"type":15},{"name":684,"slug":685,"type":15},{"name":13,"slug":14,"type":15},{"slug":64,"name":64,"fn":798,"description":799,"org":800,"tags":801,"stars":23,"repoUrl":24,"updatedAt":810},"manage Grafana Cloud resources via gcx","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, or adaptive telemetry.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[802,805,806,807],{"name":803,"slug":804,"type":15},"CLI","cli",{"name":9,"slug":8,"type":15},{"name":17,"slug":18,"type":15},{"name":808,"slug":809,"type":15},"Operations","operations","2026-07-31T05:53:50.587304",{"slug":812,"name":812,"fn":813,"description":814,"org":815,"tags":816,"stars":23,"repoUrl":24,"updatedAt":822},"gcx-demo","present gcx demo tours","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 \"\u002Fgcx-demo\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[817,818,819],{"name":803,"slug":804,"type":15},{"name":9,"slug":8,"type":15},{"name":820,"slug":821,"type":15},"Presentations","presentations","2026-07-25T05:30:45.282458",80]