[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-grafana-xk6-docs":3,"mdc--oceeoh-key":36,"related-repo-grafana-xk6-docs":343,"related-org-grafana-xk6-docs":352},{"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":31,"sourceUrl":34,"mdContent":35},"xk6-docs","write k6 load and performance tests","Look up official k6 documentation with `\u003Cbinary> x docs` when writing, debugging, or configuring a k6 test, or reaching for any k6 API, option, executor, or CLI flag. k6 syntax changes between versions, so consult it instead of recalling k6 from memory or searching the web.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},"grafana","Grafana","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fgrafana.jpg",[12,16,19,20],{"name":13,"slug":14,"type":15},"Performance","performance","tag",{"name":17,"slug":18,"type":15},"Documentation","documentation",{"name":9,"slug":8,"type":15},{"name":21,"slug":22,"type":15},"Testing","testing",5,"https:\u002F\u002Fgithub.com\u002Fgrafana\u002Fxk6-docs","2026-07-28T05:37:15.181243",null,1,[29,30],"k6","xk6",{"repoUrl":24,"stars":23,"forks":27,"topics":32,"description":33},[29,30],"User and AI agent-friendly k6 docs.","https:\u002F\u002Fgithub.com\u002Fgrafana\u002Fxk6-docs\u002Ftree\u002FHEAD\u002Finternal\u002Fcli\u002Fskills\u002Fxk6-docs","---\nname: xk6-docs\ndescription: Look up official k6 documentation with `\u003Cbinary> x docs` when writing, debugging, or configuring a k6 test, or reaching for any k6 API, option, executor, or CLI flag. k6 syntax changes between versions, so consult it instead of recalling k6 from memory or searching the web.\n---\n\n# k6 docs\n\nk6 ships its official documentation offline. Read it with `\u003Cbinary> x docs`. It auto-detects the running k6 version, so the docs always match the k6 in use.\n\nStart with [When to use it](#when-to-use-it). The efficient workflow is two batched commands, [Find the slugs](#find-the-slugs-one-command) then [Read the slugs](#read-the-slugs-one-command); [Batch to cut round trips](#batch-to-cut-round-trips) explains why one command beats many.\n\n## When to use it\n\nDo not infer or guess k6 APIs, options, or behavior from memory. The k6 API drifts between versions, so recalled syntax is often subtly wrong. Whenever you write or debug a k6 test, or reach for any k6 API, CLI option, or concept, read `\u003Cbinary> x docs` first and base your answer on what it returns.\n\nDo not search the web or fetch grafana.com for k6 questions. `\u003Cbinary> x docs` needs no network and is matched to the user's exact k6 version, so it is both faster and more accurate than anything online. Make it your only k6 reference.\n\n## Batch to cut round trips\n\nThe docs are a tree of topics. What costs you is round trips, not how many pages you read. So the one rule is: **put many `\u003Cbinary> x docs` invocations in a single shell command**, joined with `&&`. Ten pages in one command is one round trip; ten separate commands is ten.\n\n    \u003Cbinary> x docs a\u002Fone && \u003Cbinary> x docs b\u002Ftwo && \u003Cbinary> x docs c\u002Fthree\n\n`&&` works on Linux, macOS, and Windows. If a slug is wrong it exits non-zero and stops the rest of the chain, so batch slugs you're confident in. Answering a question is two batched commands: find the slugs, then read them.\n\n## Find the slugs (one command)\n\nEvery page has a `group\u002Fchild` address. Read the address the tool prints; never build a slug from a topic's name, because a bare name almost never resolves. Two ways to get exact slugs, both batchable into a single command:\n\n- **Map the area (reliable).** `\u003Cbinary> x docs --depth 2` prints the category tree; add a path to go deeper into one branch:\n\n      \u003Cbinary> x docs \u003Ccategory> --depth 3\n\n  Mapping, and reading a parent page (which lists its children), come straight from the doc tree, so they always show the real child slugs. Reach for this whenever you know roughly where a topic lives, or to browse. One map of the right branch beats mapping the whole tree, and beats mapping several branches one command at a time.\n- **Search when you don't know where it lives (fallback).** `\u003Cbinary> x docs search \u003Cquery>` prints a `group` with its matching `child` lines indented under it; a match reads as the single argument `group\u002Fchild`. Batch one search per topic:\n\n      \u003Cbinary> x docs search \u003Cquery-a> && \u003Cbinary> x docs search \u003Cquery-b>\n\n  Use a distinctive word: a common word matches many pages (noisy) or misses. If a search is noisy or empty, map the nearest category instead.\n\n## Read the slugs (one command)\n\nChain the exact slugs that search or map printed:\n\n    \u003Cbinary> x docs group-a\u002Fchild-x && \u003Cbinary> x docs group-b\u002Fchild-y\n\nReading a parent page prints its own content *and* lists its children, so one slot gives you the page and its sub-map together.\n\n## Gotcha: read the slug the tool printed, don't invent it\n\nA leaf topic usually lives under a category, so its own name alone often will not resolve (\"topic not found\"). Do not reguess a bare name from memory. Take the slug exactly as search or map printed it; if a lookup still misses, search or map again to get the real path rather than guessing another one.\n",{"data":37,"body":38},{"name":4,"description":6},{"type":39,"children":40},"root",[41,50,65,103,109,121,133,138,166,178,188,194,207,299,305,310,319,332,338],{"type":42,"tag":43,"props":44,"children":46},"element","h1",{"id":45},"k6-docs",[47],{"type":48,"value":49},"text","k6 docs",{"type":42,"tag":51,"props":52,"children":53},"p",{},[54,56,63],{"type":48,"value":55},"k6 ships its official documentation offline. Read it with ",{"type":42,"tag":57,"props":58,"children":60},"code",{"className":59},[],[61],{"type":48,"value":62},"\u003Cbinary> x docs",{"type":48,"value":64},". It auto-detects the running k6 version, so the docs always match the k6 in use.",{"type":42,"tag":51,"props":66,"children":67},{},[68,70,77,79,85,87,93,95,101],{"type":48,"value":69},"Start with ",{"type":42,"tag":71,"props":72,"children":74},"a",{"href":73},"#when-to-use-it",[75],{"type":48,"value":76},"When to use it",{"type":48,"value":78},". The efficient workflow is two batched commands, ",{"type":42,"tag":71,"props":80,"children":82},{"href":81},"#find-the-slugs-one-command",[83],{"type":48,"value":84},"Find the slugs",{"type":48,"value":86}," then ",{"type":42,"tag":71,"props":88,"children":90},{"href":89},"#read-the-slugs-one-command",[91],{"type":48,"value":92},"Read the slugs",{"type":48,"value":94},"; ",{"type":42,"tag":71,"props":96,"children":98},{"href":97},"#batch-to-cut-round-trips",[99],{"type":48,"value":100},"Batch to cut round trips",{"type":48,"value":102}," explains why one command beats many.",{"type":42,"tag":104,"props":105,"children":107},"h2",{"id":106},"when-to-use-it",[108],{"type":48,"value":76},{"type":42,"tag":51,"props":110,"children":111},{},[112,114,119],{"type":48,"value":113},"Do not infer or guess k6 APIs, options, or behavior from memory. The k6 API drifts between versions, so recalled syntax is often subtly wrong. Whenever you write or debug a k6 test, or reach for any k6 API, CLI option, or concept, read ",{"type":42,"tag":57,"props":115,"children":117},{"className":116},[],[118],{"type":48,"value":62},{"type":48,"value":120}," first and base your answer on what it returns.",{"type":42,"tag":51,"props":122,"children":123},{},[124,126,131],{"type":48,"value":125},"Do not search the web or fetch grafana.com for k6 questions. ",{"type":42,"tag":57,"props":127,"children":129},{"className":128},[],[130],{"type":48,"value":62},{"type":48,"value":132}," needs no network and is matched to the user's exact k6 version, so it is both faster and more accurate than anything online. Make it your only k6 reference.",{"type":42,"tag":104,"props":134,"children":136},{"id":135},"batch-to-cut-round-trips",[137],{"type":48,"value":100},{"type":42,"tag":51,"props":139,"children":140},{},[141,143,156,158,164],{"type":48,"value":142},"The docs are a tree of topics. What costs you is round trips, not how many pages you read. So the one rule is: ",{"type":42,"tag":144,"props":145,"children":146},"strong",{},[147,149,154],{"type":48,"value":148},"put many ",{"type":42,"tag":57,"props":150,"children":152},{"className":151},[],[153],{"type":48,"value":62},{"type":48,"value":155}," invocations in a single shell command",{"type":48,"value":157},", joined with ",{"type":42,"tag":57,"props":159,"children":161},{"className":160},[],[162],{"type":48,"value":163},"&&",{"type":48,"value":165},". Ten pages in one command is one round trip; ten separate commands is ten.",{"type":42,"tag":167,"props":168,"children":172},"pre",{"className":169,"code":171,"language":48},[170],"language-text","\u003Cbinary> x docs a\u002Fone && \u003Cbinary> x docs b\u002Ftwo && \u003Cbinary> x docs c\u002Fthree\n",[173],{"type":42,"tag":57,"props":174,"children":176},{"__ignoreMap":175},"",[177],{"type":48,"value":171},{"type":42,"tag":51,"props":179,"children":180},{},[181,186],{"type":42,"tag":57,"props":182,"children":184},{"className":183},[],[185],{"type":48,"value":163},{"type":48,"value":187}," works on Linux, macOS, and Windows. If a slug is wrong it exits non-zero and stops the rest of the chain, so batch slugs you're confident in. Answering a question is two batched commands: find the slugs, then read them.",{"type":42,"tag":104,"props":189,"children":191},{"id":190},"find-the-slugs-one-command",[192],{"type":48,"value":193},"Find the slugs (one command)",{"type":42,"tag":51,"props":195,"children":196},{},[197,199,205],{"type":48,"value":198},"Every page has a ",{"type":42,"tag":57,"props":200,"children":202},{"className":201},[],[203],{"type":48,"value":204},"group\u002Fchild",{"type":48,"value":206}," address. Read the address the tool prints; never build a slug from a topic's name, because a bare name almost never resolves. Two ways to get exact slugs, both batchable into a single command:",{"type":42,"tag":208,"props":209,"children":210},"ul",{},[211,245],{"type":42,"tag":212,"props":213,"children":214},"li",{},[215,220,222,228,230,239,243],{"type":42,"tag":144,"props":216,"children":217},{},[218],{"type":48,"value":219},"Map the area (reliable).",{"type":48,"value":221}," ",{"type":42,"tag":57,"props":223,"children":225},{"className":224},[],[226],{"type":48,"value":227},"\u003Cbinary> x docs --depth 2",{"type":48,"value":229}," prints the category tree; add a path to go deeper into one branch:",{"type":42,"tag":167,"props":231,"children":234},{"className":232,"code":233,"language":48},[170],"\u003Cbinary> x docs \u003Ccategory> --depth 3\n",[235],{"type":42,"tag":57,"props":236,"children":237},{"__ignoreMap":175},[238],{"type":48,"value":233},{"type":42,"tag":240,"props":241,"children":242},"br",{},[],{"type":48,"value":244},"Mapping, and reading a parent page (which lists its children), come straight from the doc tree, so they always show the real child slugs. Reach for this whenever you know roughly where a topic lives, or to browse. One map of the right branch beats mapping the whole tree, and beats mapping several branches one command at a time.",{"type":42,"tag":212,"props":246,"children":247},{},[248,253,254,260,262,268,270,276,278,283,285,294,297],{"type":42,"tag":144,"props":249,"children":250},{},[251],{"type":48,"value":252},"Search when you don't know where it lives (fallback).",{"type":48,"value":221},{"type":42,"tag":57,"props":255,"children":257},{"className":256},[],[258],{"type":48,"value":259},"\u003Cbinary> x docs search \u003Cquery>",{"type":48,"value":261}," prints a ",{"type":42,"tag":57,"props":263,"children":265},{"className":264},[],[266],{"type":48,"value":267},"group",{"type":48,"value":269}," with its matching ",{"type":42,"tag":57,"props":271,"children":273},{"className":272},[],[274],{"type":48,"value":275},"child",{"type":48,"value":277}," lines indented under it; a match reads as the single argument ",{"type":42,"tag":57,"props":279,"children":281},{"className":280},[],[282],{"type":48,"value":204},{"type":48,"value":284},". Batch one search per topic:",{"type":42,"tag":167,"props":286,"children":289},{"className":287,"code":288,"language":48},[170],"\u003Cbinary> x docs search \u003Cquery-a> && \u003Cbinary> x docs search \u003Cquery-b>\n",[290],{"type":42,"tag":57,"props":291,"children":292},{"__ignoreMap":175},[293],{"type":48,"value":288},{"type":42,"tag":240,"props":295,"children":296},{},[],{"type":48,"value":298},"Use a distinctive word: a common word matches many pages (noisy) or misses. If a search is noisy or empty, map the nearest category instead.",{"type":42,"tag":104,"props":300,"children":302},{"id":301},"read-the-slugs-one-command",[303],{"type":48,"value":304},"Read the slugs (one command)",{"type":42,"tag":51,"props":306,"children":307},{},[308],{"type":48,"value":309},"Chain the exact slugs that search or map printed:",{"type":42,"tag":167,"props":311,"children":314},{"className":312,"code":313,"language":48},[170],"\u003Cbinary> x docs group-a\u002Fchild-x && \u003Cbinary> x docs group-b\u002Fchild-y\n",[315],{"type":42,"tag":57,"props":316,"children":317},{"__ignoreMap":175},[318],{"type":48,"value":313},{"type":42,"tag":51,"props":320,"children":321},{},[322,324,330],{"type":48,"value":323},"Reading a parent page prints its own content ",{"type":42,"tag":325,"props":326,"children":327},"em",{},[328],{"type":48,"value":329},"and",{"type":48,"value":331}," lists its children, so one slot gives you the page and its sub-map together.",{"type":42,"tag":104,"props":333,"children":335},{"id":334},"gotcha-read-the-slug-the-tool-printed-dont-invent-it",[336],{"type":48,"value":337},"Gotcha: read the slug the tool printed, don't invent it",{"type":42,"tag":51,"props":339,"children":340},{},[341],{"type":48,"value":342},"A leaf topic usually lives under a category, so its own name alone often will not resolve (\"topic not found\"). Do not reguess a bare name from memory. Take the slug exactly as search or map printed it; if a lookup still misses, search or map again to get the real path rather than guessing another one.",{"items":344,"total":27},[345],{"slug":4,"name":4,"fn":5,"description":6,"org":346,"tags":347,"stars":23,"repoUrl":24,"updatedAt":25},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[348,349,350,351],{"name":17,"slug":18,"type":15},{"name":9,"slug":8,"type":15},{"name":13,"slug":14,"type":15},{"name":21,"slug":22,"type":15},{"items":353,"total":543},[354,375,394,414,429,445,458,471,488,503,516,531],{"slug":355,"name":355,"fn":356,"description":357,"org":358,"tags":359,"stars":372,"repoUrl":373,"updatedAt":374},"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},[360,363,366,369],{"name":361,"slug":362,"type":15},"Distributed Tracing","distributed-tracing",{"name":364,"slug":365,"type":15},"Frontend","frontend",{"name":367,"slug":368,"type":15},"Monitoring","monitoring",{"name":370,"slug":371,"type":15},"Observability","observability",1103,"https:\u002F\u002Fgithub.com\u002Fgrafana\u002Ffaro-web-sdk","2026-07-12T07:43:24.63314",{"slug":376,"name":376,"fn":377,"description":378,"org":379,"tags":380,"stars":391,"repoUrl":392,"updatedAt":393},"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},[381,384,387,390],{"name":382,"slug":383,"type":15},"API Development","api-development",{"name":385,"slug":386,"type":15},"Authentication","authentication",{"name":388,"slug":389,"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":395,"name":395,"fn":396,"description":397,"org":398,"tags":399,"stars":391,"repoUrl":392,"updatedAt":413},"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},[400,403,406,407,410],{"name":401,"slug":402,"type":15},"CSV","csv",{"name":404,"slug":405,"type":15},"Data Analysis","data-analysis",{"name":9,"slug":8,"type":15},{"name":408,"slug":409,"type":15},"GraphQL","graphql",{"name":411,"slug":412,"type":15},"JSON","json","2026-07-15T05:34:05.773947",{"slug":415,"name":415,"fn":416,"description":417,"org":418,"tags":419,"stars":426,"repoUrl":427,"updatedAt":428},"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},[420,423,424,425],{"name":421,"slug":422,"type":15},"Agents","agents",{"name":9,"slug":8,"type":15},{"name":367,"slug":368,"type":15},{"name":370,"slug":371,"type":15},430,"https:\u002F\u002Fgithub.com\u002Fgrafana\u002Fgcx","2026-07-25T05:30:40.29622",{"slug":430,"name":430,"fn":431,"description":432,"org":433,"tags":434,"stars":426,"repoUrl":427,"updatedAt":444},"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},[435,436,437,440,443],{"name":421,"slug":422,"type":15},{"name":9,"slug":8,"type":15},{"name":438,"slug":439,"type":15},"Instrumentation","instrumentation",{"name":441,"slug":442,"type":15},"LLM","llm",{"name":370,"slug":371,"type":15},"2026-07-31T05:53:52.580237",{"slug":446,"name":446,"fn":447,"description":448,"org":449,"tags":450,"stars":426,"repoUrl":427,"updatedAt":457},"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},[451,452,455,456],{"name":421,"slug":422,"type":15},{"name":453,"slug":454,"type":15},"Evals","evals",{"name":9,"slug":8,"type":15},{"name":370,"slug":371,"type":15},"2026-07-31T05:53:53.576347",{"slug":459,"name":459,"fn":460,"description":461,"org":462,"tags":463,"stars":426,"repoUrl":427,"updatedAt":470},"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},[464,465,466,469],{"name":421,"slug":422,"type":15},{"name":9,"slug":8,"type":15},{"name":467,"slug":468,"type":15},"QA","qa",{"name":21,"slug":22,"type":15},"2026-07-31T05:53:51.62785",{"slug":472,"name":472,"fn":473,"description":474,"org":475,"tags":476,"stars":426,"repoUrl":427,"updatedAt":487},"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},[477,480,483,486],{"name":478,"slug":479,"type":15},"Dashboards","dashboards",{"name":481,"slug":482,"type":15},"Data Visualization","data-visualization",{"name":484,"slug":485,"type":15},"Design","design",{"name":9,"slug":8,"type":15},"2026-07-25T05:30:46.289717",{"slug":489,"name":489,"fn":490,"description":491,"org":492,"tags":493,"stars":426,"repoUrl":427,"updatedAt":502},"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},[494,497,498,501],{"name":495,"slug":496,"type":15},"Debugging","debugging",{"name":9,"slug":8,"type":15},{"name":499,"slug":500,"type":15},"Incident Response","incident-response",{"name":370,"slug":371,"type":15},"2026-07-18T05:11:10.445428",{"slug":504,"name":504,"fn":505,"description":506,"org":507,"tags":508,"stars":426,"repoUrl":427,"updatedAt":515},"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},[509,510,511,514],{"name":495,"slug":496,"type":15},{"name":9,"slug":8,"type":15},{"name":512,"slug":513,"type":15},"Graph Analysis","graph-analysis",{"name":370,"slug":371,"type":15},"2026-07-25T05:30:39.380934",{"slug":517,"name":517,"fn":518,"description":519,"org":520,"tags":521,"stars":426,"repoUrl":427,"updatedAt":530},"gcx","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},[522,525,526,527],{"name":523,"slug":524,"type":15},"CLI","cli",{"name":9,"slug":8,"type":15},{"name":367,"slug":368,"type":15},{"name":528,"slug":529,"type":15},"Operations","operations","2026-07-31T05:53:50.587304",{"slug":532,"name":532,"fn":533,"description":534,"org":535,"tags":536,"stars":426,"repoUrl":427,"updatedAt":542},"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},[537,538,539],{"name":523,"slug":524,"type":15},{"name":9,"slug":8,"type":15},{"name":540,"slug":541,"type":15},"Presentations","presentations","2026-07-25T05:30:45.282458",80]