[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-n8n-debugging-executions":3,"mdc--auds8m-key":51,"related-repo-n8n-debugging-executions":345,"related-org-n8n-debugging-executions":440},{"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":46,"sourceUrl":49,"mdContent":50},"debugging-executions","debug failed n8n workflow executions","Debug failed or wrong-output workflow executions using executions tools. Load when the user reports execution failures, unexpected node output, empty parameter values after a successful run, or a node showing a red or failed expression error.",{"slug":8,"name":8,"logoUrl":9,"githubOrg":10},"n8n","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fn8n.png","n8n-io",[12,14,17,20],{"name":8,"slug":8,"type":13},"tag",{"name":15,"slug":16,"type":13},"Automation","automation",{"name":18,"slug":19,"type":13},"Debugging","debugging",{"name":21,"slug":22,"type":13},"Workflow Automation","workflow-automation",198156,"https:\u002F\u002Fgithub.com\u002Fn8n-io\u002Fn8n","2026-06-30T07:40:45.54",null,59655,[29,30,16,31,32,33,34,35,36,37,38,39,40,41,8,42,43,44,45,22],"ai","apis","cli","data-flow","development","integration-framework","integrations","ipaas","low-code","low-code-platform","mcp","mcp-client","mcp-server","no-code","self-hosted","typescript","workflow",{"repoUrl":24,"stars":23,"forks":27,"topics":47,"description":48},[29,30,16,31,32,33,34,35,36,37,38,39,40,41,8,42,43,44,45,22],"Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.","https:\u002F\u002Fgithub.com\u002Fn8n-io\u002Fn8n\u002Ftree\u002FHEAD\u002Fpackages\u002F@n8n\u002Finstance-ai\u002Fskills\u002Fdebugging-executions","---\nname: debugging-executions\ndescription: >-\n  Debug failed or wrong-output workflow executions using executions tools. Load\n  when the user reports execution failures, unexpected node output, empty\n  parameter values after a successful run, or a node showing a red or failed\n  expression error.\nrecommended_tools:\n  - executions\n  - workflows\n---\n\n# Debugging Executions\n\nUse this skill when debugging workflow execution failures or successful runs\nwith wrong or empty values.\n\n## When the user reports it still fails\n\nRe-run the failing path with `executions(action=\"run\")` (or\n`verify-built-workflow`) and inspect the real result before responding. Do not\nrestate that the workflow is \"fixed\", \"verified\", or \"working\", and do not\nattribute the reported failure to a test-harness artifact, stale state, or \"it\nworks in production\" without a re-run against the failing path. Treat live\nsignals as real: an execution error, partial coverage (`nodesNotReached`), an\nempty node, or a missing node is a real defect to investigate, not something to\nexplain away. If you genuinely cannot re-run the failing path, say so plainly and\nname what is unconfirmed instead of repeating a success claim.\n\n## Testing event-triggered workflows\n\nUse `executions(action=\"run\")` with `inputData` matching the trigger's output\nshape — do not rebuild the workflow with a Manual Trigger. For trigger\n`inputData` shapes, read `knowledge-base\u002Freference\u002Ftrigger-input-data-shapes.md`\nwhen a sandbox workspace is available.\n\n## Failed execution\n\n`executions(action=\"debug\")` already includes `failedNode.resolvedParameters` —\nstart there. That bundle has `parameters` (raw, with expressions intact),\n`resolved` (substituted), `failedExpressions` (those that threw), and\n`emptyResolutions` (those that resolved to `null`\u002F`undefined`\u002F`\"\"` silently).\nThe offending expression is usually visible without a follow-up call. Entries in\neither list tagged with `reason: \"unreconstructable-context\"` are NOT real bugs —\nthey reference variables we don't reconstruct in replay (`$vars`, `$secrets`,\n`$response`, `$request`, `$pageCount`, `$ai`). The value existed at execution\ntime; we just don't have it here.\n\n## Successful execution with wrong or empty value\n\nWhen `debug` doesn't apply because nothing errored, call\n`executions(action=\"get-resolved-node-parameters\", executionId, nodeName)` on the\nnode whose output looks off — **do this unprompted**, don't ask the user for\npermission first. It's a cheap read-only inspection and the only reliable way to\nconfirm whether an empty value came from an expression silently resolving to\nnullish. Check `emptyResolutions` first; most \"this parameter is empty\" cases are\nexpressions resolving to `null`\u002F`undefined`\u002F`\"\"`, not thrown errors.\n",{"data":52,"body":56},{"name":4,"description":6,"recommended_tools":53},[54,55],"executions","workflows",{"type":57,"children":58},"root",[59,67,73,80,110,116,151,157,284,290],{"type":60,"tag":61,"props":62,"children":63},"element","h1",{"id":4},[64],{"type":65,"value":66},"text","Debugging Executions",{"type":60,"tag":68,"props":69,"children":70},"p",{},[71],{"type":65,"value":72},"Use this skill when debugging workflow execution failures or successful runs\nwith wrong or empty values.",{"type":60,"tag":74,"props":75,"children":77},"h2",{"id":76},"when-the-user-reports-it-still-fails",[78],{"type":65,"value":79},"When the user reports it still fails",{"type":60,"tag":68,"props":81,"children":82},{},[83,85,92,94,100,102,108],{"type":65,"value":84},"Re-run the failing path with ",{"type":60,"tag":86,"props":87,"children":89},"code",{"className":88},[],[90],{"type":65,"value":91},"executions(action=\"run\")",{"type":65,"value":93}," (or\n",{"type":60,"tag":86,"props":95,"children":97},{"className":96},[],[98],{"type":65,"value":99},"verify-built-workflow",{"type":65,"value":101},") and inspect the real result before responding. Do not\nrestate that the workflow is \"fixed\", \"verified\", or \"working\", and do not\nattribute the reported failure to a test-harness artifact, stale state, or \"it\nworks in production\" without a re-run against the failing path. Treat live\nsignals as real: an execution error, partial coverage (",{"type":60,"tag":86,"props":103,"children":105},{"className":104},[],[106],{"type":65,"value":107},"nodesNotReached",{"type":65,"value":109},"), an\nempty node, or a missing node is a real defect to investigate, not something to\nexplain away. If you genuinely cannot re-run the failing path, say so plainly and\nname what is unconfirmed instead of repeating a success claim.",{"type":60,"tag":74,"props":111,"children":113},{"id":112},"testing-event-triggered-workflows",[114],{"type":65,"value":115},"Testing event-triggered workflows",{"type":60,"tag":68,"props":117,"children":118},{},[119,121,126,128,134,136,141,143,149],{"type":65,"value":120},"Use ",{"type":60,"tag":86,"props":122,"children":124},{"className":123},[],[125],{"type":65,"value":91},{"type":65,"value":127}," with ",{"type":60,"tag":86,"props":129,"children":131},{"className":130},[],[132],{"type":65,"value":133},"inputData",{"type":65,"value":135}," matching the trigger's output\nshape — do not rebuild the workflow with a Manual Trigger. For trigger\n",{"type":60,"tag":86,"props":137,"children":139},{"className":138},[],[140],{"type":65,"value":133},{"type":65,"value":142}," shapes, read ",{"type":60,"tag":86,"props":144,"children":146},{"className":145},[],[147],{"type":65,"value":148},"knowledge-base\u002Freference\u002Ftrigger-input-data-shapes.md",{"type":65,"value":150},"\nwhen a sandbox workspace is available.",{"type":60,"tag":74,"props":152,"children":154},{"id":153},"failed-execution",[155],{"type":65,"value":156},"Failed execution",{"type":60,"tag":68,"props":158,"children":159},{},[160,166,168,174,176,182,184,190,192,198,200,206,208,214,216,222,223,229,231,237,239,245,247,253,255,261,262,268,269,275,276,282],{"type":60,"tag":86,"props":161,"children":163},{"className":162},[],[164],{"type":65,"value":165},"executions(action=\"debug\")",{"type":65,"value":167}," already includes ",{"type":60,"tag":86,"props":169,"children":171},{"className":170},[],[172],{"type":65,"value":173},"failedNode.resolvedParameters",{"type":65,"value":175}," —\nstart there. That bundle has ",{"type":60,"tag":86,"props":177,"children":179},{"className":178},[],[180],{"type":65,"value":181},"parameters",{"type":65,"value":183}," (raw, with expressions intact),\n",{"type":60,"tag":86,"props":185,"children":187},{"className":186},[],[188],{"type":65,"value":189},"resolved",{"type":65,"value":191}," (substituted), ",{"type":60,"tag":86,"props":193,"children":195},{"className":194},[],[196],{"type":65,"value":197},"failedExpressions",{"type":65,"value":199}," (those that threw), and\n",{"type":60,"tag":86,"props":201,"children":203},{"className":202},[],[204],{"type":65,"value":205},"emptyResolutions",{"type":65,"value":207}," (those that resolved to ",{"type":60,"tag":86,"props":209,"children":211},{"className":210},[],[212],{"type":65,"value":213},"null",{"type":65,"value":215},"\u002F",{"type":60,"tag":86,"props":217,"children":219},{"className":218},[],[220],{"type":65,"value":221},"undefined",{"type":65,"value":215},{"type":60,"tag":86,"props":224,"children":226},{"className":225},[],[227],{"type":65,"value":228},"\"\"",{"type":65,"value":230}," silently).\nThe offending expression is usually visible without a follow-up call. Entries in\neither list tagged with ",{"type":60,"tag":86,"props":232,"children":234},{"className":233},[],[235],{"type":65,"value":236},"reason: \"unreconstructable-context\"",{"type":65,"value":238}," are NOT real bugs —\nthey reference variables we don't reconstruct in replay (",{"type":60,"tag":86,"props":240,"children":242},{"className":241},[],[243],{"type":65,"value":244},"$vars",{"type":65,"value":246},", ",{"type":60,"tag":86,"props":248,"children":250},{"className":249},[],[251],{"type":65,"value":252},"$secrets",{"type":65,"value":254},",\n",{"type":60,"tag":86,"props":256,"children":258},{"className":257},[],[259],{"type":65,"value":260},"$response",{"type":65,"value":246},{"type":60,"tag":86,"props":263,"children":265},{"className":264},[],[266],{"type":65,"value":267},"$request",{"type":65,"value":246},{"type":60,"tag":86,"props":270,"children":272},{"className":271},[],[273],{"type":65,"value":274},"$pageCount",{"type":65,"value":246},{"type":60,"tag":86,"props":277,"children":279},{"className":278},[],[280],{"type":65,"value":281},"$ai",{"type":65,"value":283},"). The value existed at execution\ntime; we just don't have it here.",{"type":60,"tag":74,"props":285,"children":287},{"id":286},"successful-execution-with-wrong-or-empty-value",[288],{"type":65,"value":289},"Successful execution with wrong or empty value",{"type":60,"tag":68,"props":291,"children":292},{},[293,295,301,303,309,311,317,319,324,326,331,332,337,338,343],{"type":65,"value":294},"When ",{"type":60,"tag":86,"props":296,"children":298},{"className":297},[],[299],{"type":65,"value":300},"debug",{"type":65,"value":302}," doesn't apply because nothing errored, call\n",{"type":60,"tag":86,"props":304,"children":306},{"className":305},[],[307],{"type":65,"value":308},"executions(action=\"get-resolved-node-parameters\", executionId, nodeName)",{"type":65,"value":310}," on the\nnode whose output looks off — ",{"type":60,"tag":312,"props":313,"children":314},"strong",{},[315],{"type":65,"value":316},"do this unprompted",{"type":65,"value":318},", don't ask the user for\npermission first. It's a cheap read-only inspection and the only reliable way to\nconfirm whether an empty value came from an expression silently resolving to\nnullish. Check ",{"type":60,"tag":86,"props":320,"children":322},{"className":321},[],[323],{"type":65,"value":205},{"type":65,"value":325}," first; most \"this parameter is empty\" cases are\nexpressions resolving to ",{"type":60,"tag":86,"props":327,"children":329},{"className":328},[],[330],{"type":65,"value":213},{"type":65,"value":215},{"type":60,"tag":86,"props":333,"children":335},{"className":334},[],[336],{"type":65,"value":221},{"type":65,"value":215},{"type":60,"tag":86,"props":339,"children":341},{"className":340},[],[342],{"type":65,"value":228},{"type":65,"value":344},", not thrown errors.",{"items":346,"total":439},[347,362,376,390,397,410,422],{"slug":348,"name":348,"fn":349,"description":350,"org":351,"tags":352,"stars":23,"repoUrl":24,"updatedAt":361},"config-evals","configure workflow evaluations","Builds and maintains configuration-based evaluations on a workflow with the eval-config tool. Use when the user asks to set up, add, view, change, or remove an evaluation, score, grade, or judge a workflow's output, or measure answer quality against a test dataset. This is the only eval form Instance AI handles — it does not touch on-canvas evaluation nodes.",{"slug":8,"name":8,"logoUrl":9,"githubOrg":10},[353,356,357,360],{"name":354,"slug":355,"type":13},"Evals","evals",{"name":8,"slug":8,"type":13},{"name":358,"slug":359,"type":13},"Testing","testing",{"name":21,"slug":22,"type":13},"2026-07-24T05:37:07.398695",{"slug":363,"name":363,"fn":364,"description":365,"org":366,"tags":367,"stars":23,"repoUrl":24,"updatedAt":25},"credential-setup-with-computer-use","configure n8n credentials via browser","Guides n8n credential setup through Computer Use browser tools. Use when a user needs OAuth apps, API keys, client IDs, client secrets, or other credential values from an external service console.",{"slug":8,"name":8,"logoUrl":9,"githubOrg":10},[368,369,372,373],{"name":15,"slug":16,"type":13},{"name":370,"slug":371,"type":13},"Configuration","configuration",{"name":8,"slug":8,"type":13},{"name":374,"slug":375,"type":13},"OAuth","oauth",{"slug":377,"name":377,"fn":378,"description":379,"org":380,"tags":381,"stars":23,"repoUrl":24,"updatedAt":389},"data-table-manager","manage n8n Data Tables","Load before calling data-tables or parse-file. Use for natural standalone requests like \"what data tables do I have?\", \"show\u002Flist my tables\", or \"what columns are in this table?\", and whenever the user asks to list, show, create, inspect, import, seed, query, update, clean up, rename columns in, or delete data tables and rows, especially from CSV\u002FXLSX\u002FJSON attachments. Also load before building or planning workflows that create or write to Data Tables (then load workflow-builder before build-workflow).",{"slug":8,"name":8,"logoUrl":9,"githubOrg":10},[382,385,388],{"name":383,"slug":384,"type":13},"Data Engineering","data-engineering",{"name":386,"slug":387,"type":13},"Database","database",{"name":8,"slug":8,"type":13},"2026-07-27T06:07:14.648144",{"slug":4,"name":4,"fn":5,"description":6,"org":391,"tags":392,"stars":23,"repoUrl":24,"updatedAt":25},{"slug":8,"name":8,"logoUrl":9,"githubOrg":10},[393,394,395,396],{"name":15,"slug":16,"type":13},{"name":18,"slug":19,"type":13},{"name":8,"slug":8,"type":13},{"name":21,"slug":22,"type":13},{"slug":398,"name":398,"fn":399,"description":400,"org":401,"tags":402,"stars":23,"repoUrl":24,"updatedAt":409},"intent-recognition","classify automation requests by control flow","Classifies automation requests using two decisions: anchor (which primitive owns the top-level control flow — workflow-anchored, agent-anchored, needs-clarification, or out-of-scope) and embeds_other (whether the other primitive appears embedded inside — an agent step inside a workflow, or a workflow invoked as an agent tool). Must be used before deciding the intent of any automation request, including compound requests with multiple independent automations, mid-build extensions to an existing workflow or agent, one-off questions or reports that need external systems you cannot query directly, and requests that need clarification before an anchor can be chosen, before choosing workflow-builder, planning, or an agent-oriented design.",{"slug":8,"name":8,"logoUrl":9,"githubOrg":10},[403,406,407,408],{"name":404,"slug":405,"type":13},"Agents","agents",{"name":15,"slug":16,"type":13},{"name":8,"slug":8,"type":13},{"name":21,"slug":22,"type":13},"2026-07-30T05:30:06.772347",{"slug":411,"name":411,"fn":412,"description":413,"org":414,"tags":415,"stars":23,"repoUrl":24,"updatedAt":421},"n8n-cli","manage n8n workflows from the CLI","Use the n8n CLI to manage workflows, credentials, executions, and more on an n8n instance. Use when the user asks to interact with n8n, automate workflows, manage credentials, or operate their instance from the command line.",{"slug":8,"name":8,"logoUrl":9,"githubOrg":10},[416,417,419,420],{"name":15,"slug":16,"type":13},{"name":418,"slug":31,"type":13},"CLI",{"name":8,"slug":8,"type":13},{"name":21,"slug":22,"type":13},"2026-04-06T18:38:40.360123",{"slug":423,"name":423,"fn":424,"description":425,"org":426,"tags":427,"stars":23,"repoUrl":24,"updatedAt":438},"n8n-docs-assistant","retrieve n8n documentation and guidance","Answers n8n product, setup, credential, node, hosting, API, and usage questions from current n8n docs. Load n8n-docs via load_tool before calling it (search \"n8n docs\" if not visible). Use when the user asks how to configure, set up, troubleshoot, or understand n8n behavior, especially credential setup questions opened from the credential modal.",{"slug":8,"name":8,"logoUrl":9,"githubOrg":10},[428,431,432,435],{"name":429,"slug":430,"type":13},"Documentation","documentation",{"name":8,"slug":8,"type":13},{"name":433,"slug":434,"type":13},"Reference","reference",{"name":436,"slug":437,"type":13},"Search","search","2026-07-27T06:07:15.692906",11,{"items":441,"total":545},[442,449,456,462,469,476,483,490,499,511,521,531],{"slug":348,"name":348,"fn":349,"description":350,"org":443,"tags":444,"stars":23,"repoUrl":24,"updatedAt":361},{"slug":8,"name":8,"logoUrl":9,"githubOrg":10},[445,446,447,448],{"name":354,"slug":355,"type":13},{"name":8,"slug":8,"type":13},{"name":358,"slug":359,"type":13},{"name":21,"slug":22,"type":13},{"slug":363,"name":363,"fn":364,"description":365,"org":450,"tags":451,"stars":23,"repoUrl":24,"updatedAt":25},{"slug":8,"name":8,"logoUrl":9,"githubOrg":10},[452,453,454,455],{"name":15,"slug":16,"type":13},{"name":370,"slug":371,"type":13},{"name":8,"slug":8,"type":13},{"name":374,"slug":375,"type":13},{"slug":377,"name":377,"fn":378,"description":379,"org":457,"tags":458,"stars":23,"repoUrl":24,"updatedAt":389},{"slug":8,"name":8,"logoUrl":9,"githubOrg":10},[459,460,461],{"name":383,"slug":384,"type":13},{"name":386,"slug":387,"type":13},{"name":8,"slug":8,"type":13},{"slug":4,"name":4,"fn":5,"description":6,"org":463,"tags":464,"stars":23,"repoUrl":24,"updatedAt":25},{"slug":8,"name":8,"logoUrl":9,"githubOrg":10},[465,466,467,468],{"name":15,"slug":16,"type":13},{"name":18,"slug":19,"type":13},{"name":8,"slug":8,"type":13},{"name":21,"slug":22,"type":13},{"slug":398,"name":398,"fn":399,"description":400,"org":470,"tags":471,"stars":23,"repoUrl":24,"updatedAt":409},{"slug":8,"name":8,"logoUrl":9,"githubOrg":10},[472,473,474,475],{"name":404,"slug":405,"type":13},{"name":15,"slug":16,"type":13},{"name":8,"slug":8,"type":13},{"name":21,"slug":22,"type":13},{"slug":411,"name":411,"fn":412,"description":413,"org":477,"tags":478,"stars":23,"repoUrl":24,"updatedAt":421},{"slug":8,"name":8,"logoUrl":9,"githubOrg":10},[479,480,481,482],{"name":15,"slug":16,"type":13},{"name":418,"slug":31,"type":13},{"name":8,"slug":8,"type":13},{"name":21,"slug":22,"type":13},{"slug":423,"name":423,"fn":424,"description":425,"org":484,"tags":485,"stars":23,"repoUrl":24,"updatedAt":438},{"slug":8,"name":8,"logoUrl":9,"githubOrg":10},[486,487,488,489],{"name":429,"slug":430,"type":13},{"name":8,"slug":8,"type":13},{"name":433,"slug":434,"type":13},{"name":436,"slug":437,"type":13},{"slug":491,"name":491,"fn":492,"description":493,"org":494,"tags":495,"stars":23,"repoUrl":24,"updatedAt":25},"planned-task-runtime","manage n8n task runtimes","Handles system follow-up turns: planned-task-follow-up (synthesize, replan, build-workflow, checkpoint), background-task-completed, running-tasks context, and create-tasks silence rules. Load whenever any of these tags appear or after calling create-tasks.",{"slug":8,"name":8,"logoUrl":9,"githubOrg":10},[496,497,498],{"name":15,"slug":16,"type":13},{"name":8,"slug":8,"type":13},{"name":21,"slug":22,"type":13},{"slug":500,"name":500,"fn":501,"description":502,"org":503,"tags":504,"stars":23,"repoUrl":24,"updatedAt":510},"planning","coordinate multi-artifact workflows","ONLY for coordinated multi-artifact work: multiple workflows with dependencies, shared data-table schema\u002Fmigration across tasks, or the user explicitly asked to review a plan first. Load create-tasks via load_tool before calling it (search \"create tasks\" if not visible). Do NOT use for new one-off workflows, single-workflow edits, verification-only requests, or standalone data-table ops — use workflow-builder or data-table-manager instead.",{"slug":8,"name":8,"logoUrl":9,"githubOrg":10},[505,506,507,509],{"name":15,"slug":16,"type":13},{"name":8,"slug":8,"type":13},{"name":508,"slug":500,"type":13},"Planning",{"name":21,"slug":22,"type":13},"2026-07-27T06:07:16.673218",{"slug":512,"name":512,"fn":513,"description":514,"org":515,"tags":516,"stars":23,"repoUrl":24,"updatedAt":520},"post-build-flow","verify and set up n8n workflows","Handles workflow verification and setup after build-workflow succeeds, or when the message contains workflow-verification-follow-up or workflow-setup-required. Load after direct builds, when verificationReadiness requires action, or on orchestrator verify\u002Fsetup follow-up turns.",{"slug":8,"name":8,"logoUrl":9,"githubOrg":10},[517,518,519],{"name":15,"slug":16,"type":13},{"name":8,"slug":8,"type":13},{"name":21,"slug":22,"type":13},"2026-07-24T05:37:08.421329",{"slug":522,"name":522,"fn":523,"description":524,"org":525,"tags":526,"stars":23,"repoUrl":24,"updatedAt":530},"workflow-builder","build and edit n8n workflows","Load before calling build-workflow. Default path for all single-workflow work: new one-off workflows, existing-workflow edits, verification repairs, and workflow-local data tables. Write or edit a workspace source file, then call build-workflow with filePath. When the workflow creates or writes Data Tables, load data-table-manager first, then this skill. Do not load planning or create-tasks first. Load planning only when multiple coordinated workflows or shared cross-task data tables require a dependency-aware task graph.",{"slug":8,"name":8,"logoUrl":9,"githubOrg":10},[527,528,529],{"name":15,"slug":16,"type":13},{"name":8,"slug":8,"type":13},{"name":21,"slug":22,"type":13},"2026-07-30T05:30:07.798011",{"slug":532,"name":532,"fn":533,"description":534,"org":535,"tags":536,"stars":542,"repoUrl":543,"updatedAt":544},"n8n-agents-official","build AI agents in n8n","Use when building or editing any AI feature in n8n: AI Agents, Text Classifier, Information Extractor, Sentiment Analysis, Summarization Chain, Basic LLM Chain, embeddings, vector stores, single one-shot LLM calls, or AI media generation (image \u002F audio \u002F video) via the native LangChain provider nodes. Triggers on any `@n8n\u002Fn8n-nodes-langchain.*` node, \"agent\", \"chat assistant\", \"LLM with tools\", \"tool calling\", \"fromAi\", \"system prompt\", \"memory window\", \"structured output\", \"outputParser\", \"function calling\", \"RAG\", \"vector store\", \"embeddings\", \"classify with AI\", \"extract fields with LLM\", \"sentiment analysis\", \"summarize with LLM\", \"single LLM call\", chat triggers with files, AI image \u002F video \u002F audio generation, or any multi-turn or one-shot LLM behavior.",{"slug":8,"name":8,"logoUrl":9,"githubOrg":10},[537,538,541],{"name":404,"slug":405,"type":13},{"name":539,"slug":540,"type":13},"LLM","llm",{"name":21,"slug":22,"type":13},319,"https:\u002F\u002Fgithub.com\u002Fn8n-io\u002Fskills","2026-07-08T05:44:47.938896",25]