[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-clickhouse-clickhouse-architecture-advisor":3,"mdc-5xk49x-key":38,"related-repo-clickhouse-clickhouse-architecture-advisor":911,"related-org-clickhouse-clickhouse-architecture-advisor":1023},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":26,"repoUrl":27,"updatedAt":28,"license":29,"forks":30,"topics":31,"repo":33,"sourceUrl":36,"mdContent":37},"clickhouse-architecture-advisor","advise on ClickHouse architectures","MUST USE when designing ClickHouse architectures, selecting between ingestion or modeling patterns, or translating best practices into workload-specific system designs. Complements clickhouse-best-practices with decision frameworks and explicit provenance labels.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},"clickhouse","ClickHouse","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fclickhouse.png",[12,14,17,20,23],{"name":9,"slug":8,"type":13},"tag",{"name":15,"slug":16,"type":13},"Performance","performance",{"name":18,"slug":19,"type":13},"Architecture","architecture",{"name":21,"slug":22,"type":13},"Data Engineering","data-engineering",{"name":24,"slug":25,"type":13},"Database","database",493,"https:\u002F\u002Fgithub.com\u002FClickHouse\u002Fagent-skills","2026-04-15T04:56:34.534001","Apache-2.0",32,[32,8],"agents",{"repoUrl":27,"stars":26,"forks":30,"topics":34,"description":35},[32,8],"The official Agent Skills for ClickHouse and ClickHouse Cloud","https:\u002F\u002Fgithub.com\u002FClickHouse\u002Fagent-skills\u002Ftree\u002FHEAD\u002Fskills\u002Fclickhouse-architecture-advisor","---\nname: clickhouse-architecture-advisor\ndescription: MUST USE when designing ClickHouse architectures, selecting between ingestion or modeling patterns, or translating best practices into workload-specific system designs. Complements clickhouse-best-practices with decision frameworks and explicit provenance labels.\nlicense: Apache-2.0\nmetadata:\n  author: ClickHouse Inc\n  version: \"0.1.0\"\n---\n\n# ClickHouse Architecture Advisor\n\nThis skill adds workload-aware architecture decisioning on top of `clickhouse-best-practices`.\n\n> **Official docs remain the source of truth.**\n> This skill must always prefer official ClickHouse documentation when available.\n\n## Required behavior\n\nBefore producing recommendations:\n\n1. Identify the workload shape\n   - observability\n   - security \u002F SIEM\n   - product analytics\n   - IoT \u002F telemetry\n   - market data \u002F financial services\n   - mixed OLAP with point-lookups\n2. Read the relevant decision rule files in `rules\u002F`\n3. Use `mappings\u002Fdoc_links.yaml` to attach official documentation\n4. Classify every recommendation as:\n   - `official`\n   - `derived`\n   - `field`\n5. Never present field guidance as official guidance\n6. If a recommendation is uncertain, say so explicitly\n\n## Provenance rules\n\n### `official`\nUse this when the recommendation is directly backed by official docs.\n\n### `derived`\nUse this when the recommendation is not stated verbatim in docs but follows logically from documented ClickHouse behavior.\n\n### `field`\nUse this only for experience-based guidance that may be situational.\nWhen using `field`, include:\n- a disclaimer that the advice is heuristic\n- a relevant official doc if one partially applies\n- the reason the advice depends on workload context\n\n## Read these rule files by scenario\n\n### Real-time ingestion design\n1. `rules\u002Fdecision-ingestion-strategy.md`\n2. `rules\u002Fdecision-real-time-preaggregation.md`\n3. Relevant best-practices insert rules\n\n### Time-series and retention design\n1. `rules\u002Fdecision-partitioning-timeseries.md`\n2. Relevant best-practices schema partition rules\n\n### Enrichment and dimension lookups\n1. `rules\u002Fdecision-join-enrichment.md`\n2. Relevant best-practices query join rules\n\n### Mutable state \u002F late-arriving events\n1. `rules\u002Fdecision-late-arriving-upserts.md`\n2. Relevant best-practices mutation avoidance rules\n\n## Output format\n\nStructure responses like this:\n\n```markdown\n## Workload Summary\n- workload:\n- latency target:\n- data shape:\n- primary query patterns:\n- operational constraints:\n\n## Key Decisions\n- ...\n- ...\n\n## Recommendations\n\n### \u003CRecommendation title>\n\n**What**\n...\n\n**Why**\n...\n\n**How**\n...\n\n**Category**\nofficial | derived | field\n\n**Confidence**\nhigh | medium | heuristic\n\n**Source**\n- doc link(s)\n\n**Validation**\n- concrete SQL, metric, or smoke test\n```\n\n## Architecture-specific guidance\n\nPrefer decision frameworks over generic advice. Good responses should:\n- explain tradeoffs\n- identify the likely operating bottleneck\n- separate immediate actions from structural redesign\n- provide target architecture patterns, not just isolated settings\n\n## Full reference\n\nSee `AGENTS.md` for the compiled version and `examples\u002F` for sample outputs.\n",{"data":39,"body":43},{"name":4,"description":6,"license":29,"metadata":40},{"author":41,"version":42},"ClickHouse Inc","0.1.0",{"type":44,"children":45},"root",[46,54,69,84,91,96,209,215,224,229,237,242,250,262,280,286,292,318,324,341,347,364,370,387,393,398,844,850,855,878,884,905],{"type":47,"tag":48,"props":49,"children":50},"element","h1",{"id":4},[51],{"type":52,"value":53},"text","ClickHouse Architecture Advisor",{"type":47,"tag":55,"props":56,"children":57},"p",{},[58,60,67],{"type":52,"value":59},"This skill adds workload-aware architecture decisioning on top of ",{"type":47,"tag":61,"props":62,"children":64},"code",{"className":63},[],[65],{"type":52,"value":66},"clickhouse-best-practices",{"type":52,"value":68},".",{"type":47,"tag":70,"props":71,"children":72},"blockquote",{},[73],{"type":47,"tag":55,"props":74,"children":75},{},[76,82],{"type":47,"tag":77,"props":78,"children":79},"strong",{},[80],{"type":52,"value":81},"Official docs remain the source of truth.",{"type":52,"value":83},"\nThis skill must always prefer official ClickHouse documentation when available.",{"type":47,"tag":85,"props":86,"children":88},"h2",{"id":87},"required-behavior",[89],{"type":52,"value":90},"Required behavior",{"type":47,"tag":55,"props":92,"children":93},{},[94],{"type":52,"value":95},"Before producing recommendations:",{"type":47,"tag":97,"props":98,"children":99},"ol",{},[100,140,151,164,199,204],{"type":47,"tag":101,"props":102,"children":103},"li",{},[104,106],{"type":52,"value":105},"Identify the workload shape\n",{"type":47,"tag":107,"props":108,"children":109},"ul",{},[110,115,120,125,130,135],{"type":47,"tag":101,"props":111,"children":112},{},[113],{"type":52,"value":114},"observability",{"type":47,"tag":101,"props":116,"children":117},{},[118],{"type":52,"value":119},"security \u002F SIEM",{"type":47,"tag":101,"props":121,"children":122},{},[123],{"type":52,"value":124},"product analytics",{"type":47,"tag":101,"props":126,"children":127},{},[128],{"type":52,"value":129},"IoT \u002F telemetry",{"type":47,"tag":101,"props":131,"children":132},{},[133],{"type":52,"value":134},"market data \u002F financial services",{"type":47,"tag":101,"props":136,"children":137},{},[138],{"type":52,"value":139},"mixed OLAP with point-lookups",{"type":47,"tag":101,"props":141,"children":142},{},[143,145],{"type":52,"value":144},"Read the relevant decision rule files in ",{"type":47,"tag":61,"props":146,"children":148},{"className":147},[],[149],{"type":52,"value":150},"rules\u002F",{"type":47,"tag":101,"props":152,"children":153},{},[154,156,162],{"type":52,"value":155},"Use ",{"type":47,"tag":61,"props":157,"children":159},{"className":158},[],[160],{"type":52,"value":161},"mappings\u002Fdoc_links.yaml",{"type":52,"value":163}," to attach official documentation",{"type":47,"tag":101,"props":165,"children":166},{},[167,169],{"type":52,"value":168},"Classify every recommendation as:\n",{"type":47,"tag":107,"props":170,"children":171},{},[172,181,190],{"type":47,"tag":101,"props":173,"children":174},{},[175],{"type":47,"tag":61,"props":176,"children":178},{"className":177},[],[179],{"type":52,"value":180},"official",{"type":47,"tag":101,"props":182,"children":183},{},[184],{"type":47,"tag":61,"props":185,"children":187},{"className":186},[],[188],{"type":52,"value":189},"derived",{"type":47,"tag":101,"props":191,"children":192},{},[193],{"type":47,"tag":61,"props":194,"children":196},{"className":195},[],[197],{"type":52,"value":198},"field",{"type":47,"tag":101,"props":200,"children":201},{},[202],{"type":52,"value":203},"Never present field guidance as official guidance",{"type":47,"tag":101,"props":205,"children":206},{},[207],{"type":52,"value":208},"If a recommendation is uncertain, say so explicitly",{"type":47,"tag":85,"props":210,"children":212},{"id":211},"provenance-rules",[213],{"type":52,"value":214},"Provenance rules",{"type":47,"tag":216,"props":217,"children":218},"h3",{"id":180},[219],{"type":47,"tag":61,"props":220,"children":222},{"className":221},[],[223],{"type":52,"value":180},{"type":47,"tag":55,"props":225,"children":226},{},[227],{"type":52,"value":228},"Use this when the recommendation is directly backed by official docs.",{"type":47,"tag":216,"props":230,"children":231},{"id":189},[232],{"type":47,"tag":61,"props":233,"children":235},{"className":234},[],[236],{"type":52,"value":189},{"type":47,"tag":55,"props":238,"children":239},{},[240],{"type":52,"value":241},"Use this when the recommendation is not stated verbatim in docs but follows logically from documented ClickHouse behavior.",{"type":47,"tag":216,"props":243,"children":244},{"id":198},[245],{"type":47,"tag":61,"props":246,"children":248},{"className":247},[],[249],{"type":52,"value":198},{"type":47,"tag":55,"props":251,"children":252},{},[253,255,260],{"type":52,"value":254},"Use this only for experience-based guidance that may be situational.\nWhen using ",{"type":47,"tag":61,"props":256,"children":258},{"className":257},[],[259],{"type":52,"value":198},{"type":52,"value":261},", include:",{"type":47,"tag":107,"props":263,"children":264},{},[265,270,275],{"type":47,"tag":101,"props":266,"children":267},{},[268],{"type":52,"value":269},"a disclaimer that the advice is heuristic",{"type":47,"tag":101,"props":271,"children":272},{},[273],{"type":52,"value":274},"a relevant official doc if one partially applies",{"type":47,"tag":101,"props":276,"children":277},{},[278],{"type":52,"value":279},"the reason the advice depends on workload context",{"type":47,"tag":85,"props":281,"children":283},{"id":282},"read-these-rule-files-by-scenario",[284],{"type":52,"value":285},"Read these rule files by scenario",{"type":47,"tag":216,"props":287,"children":289},{"id":288},"real-time-ingestion-design",[290],{"type":52,"value":291},"Real-time ingestion design",{"type":47,"tag":97,"props":293,"children":294},{},[295,304,313],{"type":47,"tag":101,"props":296,"children":297},{},[298],{"type":47,"tag":61,"props":299,"children":301},{"className":300},[],[302],{"type":52,"value":303},"rules\u002Fdecision-ingestion-strategy.md",{"type":47,"tag":101,"props":305,"children":306},{},[307],{"type":47,"tag":61,"props":308,"children":310},{"className":309},[],[311],{"type":52,"value":312},"rules\u002Fdecision-real-time-preaggregation.md",{"type":47,"tag":101,"props":314,"children":315},{},[316],{"type":52,"value":317},"Relevant best-practices insert rules",{"type":47,"tag":216,"props":319,"children":321},{"id":320},"time-series-and-retention-design",[322],{"type":52,"value":323},"Time-series and retention design",{"type":47,"tag":97,"props":325,"children":326},{},[327,336],{"type":47,"tag":101,"props":328,"children":329},{},[330],{"type":47,"tag":61,"props":331,"children":333},{"className":332},[],[334],{"type":52,"value":335},"rules\u002Fdecision-partitioning-timeseries.md",{"type":47,"tag":101,"props":337,"children":338},{},[339],{"type":52,"value":340},"Relevant best-practices schema partition rules",{"type":47,"tag":216,"props":342,"children":344},{"id":343},"enrichment-and-dimension-lookups",[345],{"type":52,"value":346},"Enrichment and dimension lookups",{"type":47,"tag":97,"props":348,"children":349},{},[350,359],{"type":47,"tag":101,"props":351,"children":352},{},[353],{"type":47,"tag":61,"props":354,"children":356},{"className":355},[],[357],{"type":52,"value":358},"rules\u002Fdecision-join-enrichment.md",{"type":47,"tag":101,"props":360,"children":361},{},[362],{"type":52,"value":363},"Relevant best-practices query join rules",{"type":47,"tag":216,"props":365,"children":367},{"id":366},"mutable-state-late-arriving-events",[368],{"type":52,"value":369},"Mutable state \u002F late-arriving events",{"type":47,"tag":97,"props":371,"children":372},{},[373,382],{"type":47,"tag":101,"props":374,"children":375},{},[376],{"type":47,"tag":61,"props":377,"children":379},{"className":378},[],[380],{"type":52,"value":381},"rules\u002Fdecision-late-arriving-upserts.md",{"type":47,"tag":101,"props":383,"children":384},{},[385],{"type":52,"value":386},"Relevant best-practices mutation avoidance rules",{"type":47,"tag":85,"props":388,"children":390},{"id":389},"output-format",[391],{"type":52,"value":392},"Output format",{"type":47,"tag":55,"props":394,"children":395},{},[396],{"type":52,"value":397},"Structure responses like this:",{"type":47,"tag":399,"props":400,"children":405},"pre",{"className":401,"code":402,"language":403,"meta":404,"style":404},"language-markdown shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","## Workload Summary\n- workload:\n- latency target:\n- data shape:\n- primary query patterns:\n- operational constraints:\n\n## Key Decisions\n- ...\n- ...\n\n## Recommendations\n\n### \u003CRecommendation title>\n\n**What**\n...\n\n**Why**\n...\n\n**How**\n...\n\n**Category**\nofficial | derived | field\n\n**Confidence**\nhigh | medium | heuristic\n\n**Source**\n- doc link(s)\n\n**Validation**\n- concrete SQL, metric, or smoke test\n","markdown","",[406],{"type":47,"tag":61,"props":407,"children":408},{"__ignoreMap":404},[409,427,442,455,468,481,494,504,517,530,542,550,563,571,597,605,626,635,643,660,668,676,693,701,709,726,735,743,760,769,777,794,806,814,831],{"type":47,"tag":410,"props":411,"children":414},"span",{"class":412,"line":413},"line",1,[415,421],{"type":47,"tag":410,"props":416,"children":418},{"style":417},"--shiki-light:#39ADB5;--shiki-default:#89DDFF;--shiki-dark:#89DDFF",[419],{"type":52,"value":420},"## ",{"type":47,"tag":410,"props":422,"children":424},{"style":423},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[425],{"type":52,"value":426},"Workload Summary\n",{"type":47,"tag":410,"props":428,"children":430},{"class":412,"line":429},2,[431,436],{"type":47,"tag":410,"props":432,"children":433},{"style":417},[434],{"type":52,"value":435},"-",{"type":47,"tag":410,"props":437,"children":439},{"style":438},"--shiki-light:#90A4AE;--shiki-default:#EEFFFF;--shiki-dark:#BABED8",[440],{"type":52,"value":441}," workload:\n",{"type":47,"tag":410,"props":443,"children":445},{"class":412,"line":444},3,[446,450],{"type":47,"tag":410,"props":447,"children":448},{"style":417},[449],{"type":52,"value":435},{"type":47,"tag":410,"props":451,"children":452},{"style":438},[453],{"type":52,"value":454}," latency target:\n",{"type":47,"tag":410,"props":456,"children":458},{"class":412,"line":457},4,[459,463],{"type":47,"tag":410,"props":460,"children":461},{"style":417},[462],{"type":52,"value":435},{"type":47,"tag":410,"props":464,"children":465},{"style":438},[466],{"type":52,"value":467}," data shape:\n",{"type":47,"tag":410,"props":469,"children":471},{"class":412,"line":470},5,[472,476],{"type":47,"tag":410,"props":473,"children":474},{"style":417},[475],{"type":52,"value":435},{"type":47,"tag":410,"props":477,"children":478},{"style":438},[479],{"type":52,"value":480}," primary query patterns:\n",{"type":47,"tag":410,"props":482,"children":484},{"class":412,"line":483},6,[485,489],{"type":47,"tag":410,"props":486,"children":487},{"style":417},[488],{"type":52,"value":435},{"type":47,"tag":410,"props":490,"children":491},{"style":438},[492],{"type":52,"value":493}," operational constraints:\n",{"type":47,"tag":410,"props":495,"children":497},{"class":412,"line":496},7,[498],{"type":47,"tag":410,"props":499,"children":501},{"emptyLinePlaceholder":500},true,[502],{"type":52,"value":503},"\n",{"type":47,"tag":410,"props":505,"children":507},{"class":412,"line":506},8,[508,512],{"type":47,"tag":410,"props":509,"children":510},{"style":417},[511],{"type":52,"value":420},{"type":47,"tag":410,"props":513,"children":514},{"style":423},[515],{"type":52,"value":516},"Key Decisions\n",{"type":47,"tag":410,"props":518,"children":520},{"class":412,"line":519},9,[521,525],{"type":47,"tag":410,"props":522,"children":523},{"style":417},[524],{"type":52,"value":435},{"type":47,"tag":410,"props":526,"children":527},{"style":438},[528],{"type":52,"value":529}," ...\n",{"type":47,"tag":410,"props":531,"children":533},{"class":412,"line":532},10,[534,538],{"type":47,"tag":410,"props":535,"children":536},{"style":417},[537],{"type":52,"value":435},{"type":47,"tag":410,"props":539,"children":540},{"style":438},[541],{"type":52,"value":529},{"type":47,"tag":410,"props":543,"children":545},{"class":412,"line":544},11,[546],{"type":47,"tag":410,"props":547,"children":548},{"emptyLinePlaceholder":500},[549],{"type":52,"value":503},{"type":47,"tag":410,"props":551,"children":553},{"class":412,"line":552},12,[554,558],{"type":47,"tag":410,"props":555,"children":556},{"style":417},[557],{"type":52,"value":420},{"type":47,"tag":410,"props":559,"children":560},{"style":423},[561],{"type":52,"value":562},"Recommendations\n",{"type":47,"tag":410,"props":564,"children":566},{"class":412,"line":565},13,[567],{"type":47,"tag":410,"props":568,"children":569},{"emptyLinePlaceholder":500},[570],{"type":52,"value":503},{"type":47,"tag":410,"props":572,"children":574},{"class":412,"line":573},14,[575,580,586,592],{"type":47,"tag":410,"props":576,"children":577},{"style":417},[578],{"type":52,"value":579},"### \u003C",{"type":47,"tag":410,"props":581,"children":583},{"style":582},"--shiki-light:#E53935;--shiki-default:#F07178;--shiki-dark:#F07178",[584],{"type":52,"value":585},"Recommendation",{"type":47,"tag":410,"props":587,"children":589},{"style":588},"--shiki-light:#9C3EDA;--shiki-default:#C792EA;--shiki-dark:#C792EA",[590],{"type":52,"value":591}," title",{"type":47,"tag":410,"props":593,"children":594},{"style":417},[595],{"type":52,"value":596},">\n",{"type":47,"tag":410,"props":598,"children":600},{"class":412,"line":599},15,[601],{"type":47,"tag":410,"props":602,"children":603},{"emptyLinePlaceholder":500},[604],{"type":52,"value":503},{"type":47,"tag":410,"props":606,"children":608},{"class":412,"line":607},16,[609,615,621],{"type":47,"tag":410,"props":610,"children":612},{"style":611},"--shiki-light:#39ADB5;--shiki-light-font-weight:bold;--shiki-default:#89DDFF;--shiki-default-font-weight:bold;--shiki-dark:#89DDFF;--shiki-dark-font-weight:bold",[613],{"type":52,"value":614},"**",{"type":47,"tag":410,"props":616,"children":618},{"style":617},"--shiki-light:#E53935;--shiki-light-font-weight:bold;--shiki-default:#F07178;--shiki-default-font-weight:bold;--shiki-dark:#F07178;--shiki-dark-font-weight:bold",[619],{"type":52,"value":620},"What",{"type":47,"tag":410,"props":622,"children":623},{"style":611},[624],{"type":52,"value":625},"**\n",{"type":47,"tag":410,"props":627,"children":629},{"class":412,"line":628},17,[630],{"type":47,"tag":410,"props":631,"children":632},{"style":438},[633],{"type":52,"value":634},"...\n",{"type":47,"tag":410,"props":636,"children":638},{"class":412,"line":637},18,[639],{"type":47,"tag":410,"props":640,"children":641},{"emptyLinePlaceholder":500},[642],{"type":52,"value":503},{"type":47,"tag":410,"props":644,"children":646},{"class":412,"line":645},19,[647,651,656],{"type":47,"tag":410,"props":648,"children":649},{"style":611},[650],{"type":52,"value":614},{"type":47,"tag":410,"props":652,"children":653},{"style":617},[654],{"type":52,"value":655},"Why",{"type":47,"tag":410,"props":657,"children":658},{"style":611},[659],{"type":52,"value":625},{"type":47,"tag":410,"props":661,"children":663},{"class":412,"line":662},20,[664],{"type":47,"tag":410,"props":665,"children":666},{"style":438},[667],{"type":52,"value":634},{"type":47,"tag":410,"props":669,"children":671},{"class":412,"line":670},21,[672],{"type":47,"tag":410,"props":673,"children":674},{"emptyLinePlaceholder":500},[675],{"type":52,"value":503},{"type":47,"tag":410,"props":677,"children":679},{"class":412,"line":678},22,[680,684,689],{"type":47,"tag":410,"props":681,"children":682},{"style":611},[683],{"type":52,"value":614},{"type":47,"tag":410,"props":685,"children":686},{"style":617},[687],{"type":52,"value":688},"How",{"type":47,"tag":410,"props":690,"children":691},{"style":611},[692],{"type":52,"value":625},{"type":47,"tag":410,"props":694,"children":696},{"class":412,"line":695},23,[697],{"type":47,"tag":410,"props":698,"children":699},{"style":438},[700],{"type":52,"value":634},{"type":47,"tag":410,"props":702,"children":704},{"class":412,"line":703},24,[705],{"type":47,"tag":410,"props":706,"children":707},{"emptyLinePlaceholder":500},[708],{"type":52,"value":503},{"type":47,"tag":410,"props":710,"children":712},{"class":412,"line":711},25,[713,717,722],{"type":47,"tag":410,"props":714,"children":715},{"style":611},[716],{"type":52,"value":614},{"type":47,"tag":410,"props":718,"children":719},{"style":617},[720],{"type":52,"value":721},"Category",{"type":47,"tag":410,"props":723,"children":724},{"style":611},[725],{"type":52,"value":625},{"type":47,"tag":410,"props":727,"children":729},{"class":412,"line":728},26,[730],{"type":47,"tag":410,"props":731,"children":732},{"style":438},[733],{"type":52,"value":734},"official | derived | field\n",{"type":47,"tag":410,"props":736,"children":738},{"class":412,"line":737},27,[739],{"type":47,"tag":410,"props":740,"children":741},{"emptyLinePlaceholder":500},[742],{"type":52,"value":503},{"type":47,"tag":410,"props":744,"children":746},{"class":412,"line":745},28,[747,751,756],{"type":47,"tag":410,"props":748,"children":749},{"style":611},[750],{"type":52,"value":614},{"type":47,"tag":410,"props":752,"children":753},{"style":617},[754],{"type":52,"value":755},"Confidence",{"type":47,"tag":410,"props":757,"children":758},{"style":611},[759],{"type":52,"value":625},{"type":47,"tag":410,"props":761,"children":763},{"class":412,"line":762},29,[764],{"type":47,"tag":410,"props":765,"children":766},{"style":438},[767],{"type":52,"value":768},"high | medium | heuristic\n",{"type":47,"tag":410,"props":770,"children":772},{"class":412,"line":771},30,[773],{"type":47,"tag":410,"props":774,"children":775},{"emptyLinePlaceholder":500},[776],{"type":52,"value":503},{"type":47,"tag":410,"props":778,"children":780},{"class":412,"line":779},31,[781,785,790],{"type":47,"tag":410,"props":782,"children":783},{"style":611},[784],{"type":52,"value":614},{"type":47,"tag":410,"props":786,"children":787},{"style":617},[788],{"type":52,"value":789},"Source",{"type":47,"tag":410,"props":791,"children":792},{"style":611},[793],{"type":52,"value":625},{"type":47,"tag":410,"props":795,"children":796},{"class":412,"line":30},[797,801],{"type":47,"tag":410,"props":798,"children":799},{"style":417},[800],{"type":52,"value":435},{"type":47,"tag":410,"props":802,"children":803},{"style":438},[804],{"type":52,"value":805}," doc link(s)\n",{"type":47,"tag":410,"props":807,"children":809},{"class":412,"line":808},33,[810],{"type":47,"tag":410,"props":811,"children":812},{"emptyLinePlaceholder":500},[813],{"type":52,"value":503},{"type":47,"tag":410,"props":815,"children":817},{"class":412,"line":816},34,[818,822,827],{"type":47,"tag":410,"props":819,"children":820},{"style":611},[821],{"type":52,"value":614},{"type":47,"tag":410,"props":823,"children":824},{"style":617},[825],{"type":52,"value":826},"Validation",{"type":47,"tag":410,"props":828,"children":829},{"style":611},[830],{"type":52,"value":625},{"type":47,"tag":410,"props":832,"children":834},{"class":412,"line":833},35,[835,839],{"type":47,"tag":410,"props":836,"children":837},{"style":417},[838],{"type":52,"value":435},{"type":47,"tag":410,"props":840,"children":841},{"style":438},[842],{"type":52,"value":843}," concrete SQL, metric, or smoke test\n",{"type":47,"tag":85,"props":845,"children":847},{"id":846},"architecture-specific-guidance",[848],{"type":52,"value":849},"Architecture-specific guidance",{"type":47,"tag":55,"props":851,"children":852},{},[853],{"type":52,"value":854},"Prefer decision frameworks over generic advice. Good responses should:",{"type":47,"tag":107,"props":856,"children":857},{},[858,863,868,873],{"type":47,"tag":101,"props":859,"children":860},{},[861],{"type":52,"value":862},"explain tradeoffs",{"type":47,"tag":101,"props":864,"children":865},{},[866],{"type":52,"value":867},"identify the likely operating bottleneck",{"type":47,"tag":101,"props":869,"children":870},{},[871],{"type":52,"value":872},"separate immediate actions from structural redesign",{"type":47,"tag":101,"props":874,"children":875},{},[876],{"type":52,"value":877},"provide target architecture patterns, not just isolated settings",{"type":47,"tag":85,"props":879,"children":881},{"id":880},"full-reference",[882],{"type":52,"value":883},"Full reference",{"type":47,"tag":55,"props":885,"children":886},{},[887,889,895,897,903],{"type":52,"value":888},"See ",{"type":47,"tag":61,"props":890,"children":892},{"className":891},[],[893],{"type":52,"value":894},"AGENTS.md",{"type":52,"value":896}," for the compiled version and ",{"type":47,"tag":61,"props":898,"children":900},{"className":899},[],[901],{"type":52,"value":902},"examples\u002F",{"type":52,"value":904}," for sample outputs.",{"type":47,"tag":906,"props":907,"children":908},"style",{},[909],{"type":52,"value":910},"html .light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html.light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html.dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}",{"items":912,"total":506},[913,929,943,951,964,982,1005],{"slug":914,"name":914,"fn":915,"description":916,"org":917,"tags":918,"stars":26,"repoUrl":27,"updatedAt":928},"chdb-datastore","accelerate pandas with chDB datastore","Use when the user has tabular data (pandas DataFrame, parquet, csv, Arrow, json) and wants to filter, group, aggregate, join, or speed up slow pandas. Provides chDB DataStore — same pandas API, ClickHouse engine underneath. Also handles reading from S3, MySQL, PostgreSQL, MongoDB, ClickHouse Cloud, Iceberg, Delta Lake as DataFrames and joining across sources. TRIGGER when: user mentions DataFrame, parquet, csv, \"fast pandas\", \"speed up pandas\", or cross-source DataFrame joins; user imports `chdb.datastore` or `from datastore import DataStore`. SKIP this skill for raw SQL syntax (use chdb-sql instead), ClickHouse server administration, or non-Python DataStore API work.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[919,920,923,924,925],{"name":9,"slug":8,"type":13},{"name":921,"slug":922,"type":13},"Data Analysis","data-analysis",{"name":21,"slug":22,"type":13},{"name":15,"slug":16,"type":13},{"name":926,"slug":927,"type":13},"Python","python","2026-04-15T04:56:32.0629",{"slug":930,"name":930,"fn":931,"description":932,"org":933,"tags":934,"stars":26,"repoUrl":27,"updatedAt":942},"chdb-sql","run ClickHouse SQL queries in Python","Use when the user wants to run SQL — especially analytical SQL — on local files (parquet\u002Fcsv\u002Fjson), URLs, S3 paths, or remote databases (Postgres, MySQL, MongoDB, ClickHouse Cloud, Iceberg, Delta Lake) without setting up a server. Provides chDB — embedded ClickHouse SQL in Python with 1000+ functions, Session for stateful multi-step pipelines, parametrized queries, and cross-source joins via `s3()`, `mysql()`, `postgresql()`, `iceberg()`, `deltaLake()`, `remoteSecure()` table functions. TRIGGER when: user wants SQL on parquet\u002Fcsv\u002Ffiles or across remote analytical sources; uses ClickHouse SQL features (window functions, windowFunnel, geoToH3, JSON path ops, Session, parametrized queries); imports `chdb` or calls `chdb.query()`. SKIP this skill for pandas-style DataFrame method-chaining (use chdb-datastore instead) or ClickHouse server administration.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[935,936,937,938,939],{"name":9,"slug":8,"type":13},{"name":921,"slug":922,"type":13},{"name":21,"slug":22,"type":13},{"name":926,"slug":927,"type":13},{"name":940,"slug":941,"type":13},"SQL","sql","2026-04-15T04:56:33.299509",{"slug":4,"name":4,"fn":5,"description":6,"org":944,"tags":945,"stars":26,"repoUrl":27,"updatedAt":28},{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[946,947,948,949,950],{"name":18,"slug":19,"type":13},{"name":9,"slug":8,"type":13},{"name":21,"slug":22,"type":13},{"name":24,"slug":25,"type":13},{"name":15,"slug":16,"type":13},{"slug":66,"name":66,"fn":952,"description":953,"org":954,"tags":955,"stars":26,"repoUrl":27,"updatedAt":963},"review ClickHouse schemas and queries","MUST USE when reviewing ClickHouse schemas, queries, or configurations. Contains 31 rules that MUST be checked before providing recommendations. Always read relevant rule files and cite specific rules in responses.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[956,957,960,961,962],{"name":9,"slug":8,"type":13},{"name":958,"slug":959,"type":13},"Code Review","code-review",{"name":24,"slug":25,"type":13},{"name":15,"slug":16,"type":13},{"name":940,"slug":941,"type":13},"2026-04-06T18:07:18.953931",{"slug":965,"name":965,"fn":966,"description":967,"org":968,"tags":969,"stars":26,"repoUrl":27,"updatedAt":981},"clickhouse-js-node-rowbinary","encode and decode ClickHouse RowBinary streams","Generate TypeScript\u002FJavaScript code that reads\u002Fdecodes AND writes\u002Fencodes ClickHouse RowBinary streams for the ClickHouse HTTP server. Use this skill whenever a user wants to parse or produce `RowBinary`, `RowBinaryWithNames`, or `RowBinaryWithNamesAndTypes`. Node.js only, doesn't cover browsers.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[970,973,974,975,978],{"name":971,"slug":972,"type":13},"API Development","api-development",{"name":9,"slug":8,"type":13},{"name":24,"slug":25,"type":13},{"name":976,"slug":977,"type":13},"JavaScript","javascript",{"name":979,"slug":980,"type":13},"TypeScript","typescript","2026-07-01T08:16:19.314713",{"slug":983,"name":983,"fn":984,"description":985,"org":986,"tags":987,"stars":26,"repoUrl":27,"updatedAt":1004},"clickhouse-managed-postgres-rca","diagnose performance issues on ClickHouse-managed Postgres","MUST USE when investigating performance issues on a ClickHouse-managed Postgres instance. Provides an evidence-based RCA workflow that scrapes the Prometheus endpoint for system signal, pulls per-digest evidence from the Slow Query Patterns API, and recommends (does not apply) a fix.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[988,989,992,995,997,998,1001],{"name":9,"slug":8,"type":13},{"name":990,"slug":991,"type":13},"Debugging","debugging",{"name":993,"slug":994,"type":13},"Monitoring","monitoring",{"name":996,"slug":114,"type":13},"Observability",{"name":15,"slug":16,"type":13},{"name":999,"slug":1000,"type":13},"PostgreSQL","postgresql",{"name":1002,"slug":1003,"type":13},"Prometheus","prometheus","2026-06-08T08:19:31.589978",{"slug":1006,"name":1006,"fn":1007,"description":1008,"org":1009,"tags":1010,"stars":26,"repoUrl":27,"updatedAt":1022},"infra-clickhouse","manage ClickHouse server instances","Sets up and manages ClickHouse using the clickhousectl CLI — installs and runs a local ClickHouse server for development, and creates managed ClickHouse Cloud services for production (authentication, service creation, schema migration, application connection). Use when the user wants to build an application with ClickHouse, set up a local ClickHouse dev environment, create tables and start querying, deploy ClickHouse to production or ClickHouse Cloud, or migrate from a local setup to the cloud.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1011,1014,1015,1016,1019],{"name":1012,"slug":1013,"type":13},"CLI","cli",{"name":9,"slug":8,"type":13},{"name":24,"slug":25,"type":13},{"name":1017,"slug":1018,"type":13},"Deployment","deployment",{"name":1020,"slug":1021,"type":13},"Infrastructure","infrastructure","2026-07-28T06:06:00.02089",{"items":1024,"total":552},[1025,1033,1041,1049,1057,1065,1075,1083,1097,1114,1126,1146],{"slug":914,"name":914,"fn":915,"description":916,"org":1026,"tags":1027,"stars":26,"repoUrl":27,"updatedAt":928},{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1028,1029,1030,1031,1032],{"name":9,"slug":8,"type":13},{"name":921,"slug":922,"type":13},{"name":21,"slug":22,"type":13},{"name":15,"slug":16,"type":13},{"name":926,"slug":927,"type":13},{"slug":930,"name":930,"fn":931,"description":932,"org":1034,"tags":1035,"stars":26,"repoUrl":27,"updatedAt":942},{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1036,1037,1038,1039,1040],{"name":9,"slug":8,"type":13},{"name":921,"slug":922,"type":13},{"name":21,"slug":22,"type":13},{"name":926,"slug":927,"type":13},{"name":940,"slug":941,"type":13},{"slug":4,"name":4,"fn":5,"description":6,"org":1042,"tags":1043,"stars":26,"repoUrl":27,"updatedAt":28},{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1044,1045,1046,1047,1048],{"name":18,"slug":19,"type":13},{"name":9,"slug":8,"type":13},{"name":21,"slug":22,"type":13},{"name":24,"slug":25,"type":13},{"name":15,"slug":16,"type":13},{"slug":66,"name":66,"fn":952,"description":953,"org":1050,"tags":1051,"stars":26,"repoUrl":27,"updatedAt":963},{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1052,1053,1054,1055,1056],{"name":9,"slug":8,"type":13},{"name":958,"slug":959,"type":13},{"name":24,"slug":25,"type":13},{"name":15,"slug":16,"type":13},{"name":940,"slug":941,"type":13},{"slug":965,"name":965,"fn":966,"description":967,"org":1058,"tags":1059,"stars":26,"repoUrl":27,"updatedAt":981},{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1060,1061,1062,1063,1064],{"name":971,"slug":972,"type":13},{"name":9,"slug":8,"type":13},{"name":24,"slug":25,"type":13},{"name":976,"slug":977,"type":13},{"name":979,"slug":980,"type":13},{"slug":983,"name":983,"fn":984,"description":985,"org":1066,"tags":1067,"stars":26,"repoUrl":27,"updatedAt":1004},{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1068,1069,1070,1071,1072,1073,1074],{"name":9,"slug":8,"type":13},{"name":990,"slug":991,"type":13},{"name":993,"slug":994,"type":13},{"name":996,"slug":114,"type":13},{"name":15,"slug":16,"type":13},{"name":999,"slug":1000,"type":13},{"name":1002,"slug":1003,"type":13},{"slug":1006,"name":1006,"fn":1007,"description":1008,"org":1076,"tags":1077,"stars":26,"repoUrl":27,"updatedAt":1022},{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1078,1079,1080,1081,1082],{"name":1012,"slug":1013,"type":13},{"name":9,"slug":8,"type":13},{"name":24,"slug":25,"type":13},{"name":1017,"slug":1018,"type":13},{"name":1020,"slug":1021,"type":13},{"slug":1084,"name":1084,"fn":1085,"description":1086,"org":1087,"tags":1088,"stars":26,"repoUrl":27,"updatedAt":1096},"infra-postgres","manage PostgreSQL database instances","Sets up and manages Postgres using the clickhousectl CLI — runs a local Docker-backed Postgres for development, and creates and operates managed ClickHouse Cloud Postgres services (connections, TLS, runtime config, read replicas, failover, point-in-time restore). Use when the user wants a Postgres or PostgreSQL database for their application, a local Postgres dev environment, psql access, or a managed\u002Fproduction Postgres in ClickHouse Cloud, or mentions moving a local Postgres to production.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1089,1090,1091,1094,1095],{"name":24,"slug":25,"type":13},{"name":1017,"slug":1018,"type":13},{"name":1092,"slug":1093,"type":13},"Docker","docker",{"name":1020,"slug":1021,"type":13},{"name":999,"slug":1000,"type":13},"2026-07-28T06:06:07.151976",{"slug":1098,"name":1098,"fn":1099,"description":1100,"org":1101,"tags":1102,"stars":1111,"repoUrl":1112,"updatedAt":1113},"clickhouse-js-node-coding","build Node.js applications with ClickHouse","Write idiomatic application code with the ClickHouse Node.js client (`@clickhouse\u002Fclient`). Use this skill whenever a user is *building* against the Node.js client — configuring the client, pinging, inserting rows in JSON or raw formats, selecting and parsing results, binding query parameters, managing sessions and temporary tables, working with data types or customizing JSON parsing. Do NOT use for browser\u002FWeb client code.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1103,1106,1107,1108],{"name":1104,"slug":1105,"type":13},"Backend","backend",{"name":9,"slug":8,"type":13},{"name":24,"slug":25,"type":13},{"name":1109,"slug":1110,"type":13},"Node.js","node-js",321,"https:\u002F\u002Fgithub.com\u002FClickHouse\u002Fclickhouse-js","2026-05-06T05:41:40.923776",{"slug":1115,"name":1115,"fn":1116,"description":1117,"org":1118,"tags":1119,"stars":1111,"repoUrl":1112,"updatedAt":1125},"clickhouse-js-node-troubleshooting","troubleshoot ClickHouse Node.js client","Troubleshoot and resolve common issues with the ClickHouse Node.js client (@clickhouse\u002Fclient). Use this skill whenever a user reports errors, unexpected behavior, or configuration questions involving the Node.js client specifically — including socket hang-up errors, Keep-Alive problems, stream handling issues, data type mismatches, read-only user restrictions, proxy\u002FTLS setup problems, or long-running query timeouts. Trigger even when the user hasn't precisely named the issue; vague symptoms like \"my inserts keep failing\" or \"connection drops randomly\" in a Node.js context are strong signals to use this skill. Do NOT use for browser\u002FWeb client issues.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1120,1121,1122,1124],{"name":9,"slug":8,"type":13},{"name":990,"slug":991,"type":13},{"name":1109,"slug":1123,"type":13},"nodejs",{"name":979,"slug":980,"type":13},"2026-04-14T04:56:39.447406",{"slug":1127,"name":1127,"fn":1128,"description":1129,"org":1130,"tags":1131,"stars":1143,"repoUrl":1144,"updatedAt":1145},"clickstack-otel-collector","set up OpenTelemetry collector for ClickHouse","Use when a user wants to wire an OpenTelemetry collector into a Managed ClickStack service on ClickHouse Cloud, either by deploying a new local collector (Docker run or Docker Compose) or by configuring their own existing collector, then send rich synthetic telemetry and verify it is visible in ClickStack.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1132,1133,1136,1139,1140],{"name":9,"slug":8,"type":13},{"name":1134,"slug":1135,"type":13},"Logs","logs",{"name":1137,"slug":1138,"type":13},"Metrics","metrics",{"name":996,"slug":114,"type":13},{"name":1141,"slug":1142,"type":13},"OpenTelemetry","opentelemetry",196,"https:\u002F\u002Fgithub.com\u002FClickHouse\u002Fclickhouse-docs","2026-06-11T08:25:17.959323",{"slug":1147,"name":1147,"fn":1148,"description":1149,"org":1150,"tags":1151,"stars":457,"repoUrl":1160,"updatedAt":1161},"setup","set up ClickHouse MCP server connections","Guides users through setting up the ClickHouse MCP server connection bundled with this plugin. Use when the user first installs the plugin or has trouble connecting to ClickHouse.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1152,1153,1154,1157],{"name":9,"slug":8,"type":13},{"name":24,"slug":25,"type":13},{"name":1155,"slug":1156,"type":13},"Local Development","local-development",{"name":1158,"slug":1159,"type":13},"MCP","mcp","https:\u002F\u002Fgithub.com\u002FClickHouse\u002Fclickhouse-claude-code-plugin","2026-04-19T04:59:29.849185"]