[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-n8n-planning":3,"mdc-8nu69g-key":50,"related-org-n8n-planning":932,"related-repo-n8n-planning":1081},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":22,"repoUrl":23,"updatedAt":24,"license":25,"forks":26,"topics":27,"repo":45,"sourceUrl":48,"mdContent":49},"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},"n8n","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fn8n.png","n8n-io",[12,14,17,19],{"name":8,"slug":8,"type":13},"tag",{"name":15,"slug":16,"type":13},"Automation","automation",{"name":18,"slug":4,"type":13},"Planning",{"name":20,"slug":21,"type":13},"Workflow Automation","workflow-automation",198156,"https:\u002F\u002Fgithub.com\u002Fn8n-io\u002Fn8n","2026-07-27T06:07:16.673218",null,59655,[28,29,16,30,31,32,33,34,35,36,37,38,39,40,8,41,42,43,44,21],"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":23,"stars":22,"forks":26,"topics":46,"description":47},[28,29,16,30,31,32,33,34,35,36,37,38,39,40,8,41,42,43,44,21],"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\u002Fplanning","---\nname: planning\ndescription: >-\n  ONLY for coordinated multi-artifact work: multiple workflows with dependencies,\n  shared data-table schema\u002Fmigration across tasks, or the user explicitly asked\n  to review a plan first. Load create-tasks via load_tool before calling it\n  (search \"create tasks\" if not visible). Do NOT use for new one-off workflows,\n  single-workflow edits, verification-only requests, or standalone data-table\n  ops — use workflow-builder or data-table-manager instead.\nrecommended_tools:\n  - create-tasks\n  - workflows\n  - nodes\n  - credentials\n  - data-tables\n  - parse-file\n  - research\n  - ask-user\n---\n\n# Planning\n\nUse this skill to design a dependency-aware task graph in the orchestrator and\nsubmit it with `create-tasks`. Do not spawn another agent and do not use\nincremental plan item tools.\n\nBefore calling `create-tasks`, load it via `load_tool` (search \"create tasks\" if\nit is not visible).\n\n## When NOT to use this skill\n\nStop and use `workflow-builder` + `build-workflow` instead when the request is:\n\n- A new or one-off single workflow, even if it sounds large or unfamiliar\n- An edit to one existing workflow (nodes, expressions, credentials, schedule, Code)\n- Verification, setup, or credential collection for a workflow you just built\n- A workflow-local data table whose schema ships with that same workflow\n- Standalone data-table list\u002Fschema\u002Fquery\u002Fcreate\u002Fmutation work\n\nDo not call `create-tasks` just to get approval, verification, or a checklist for\na single workflow. Workflow verification is automatic from structured build\noutcomes after `build-workflow`.\n\n## When to use this skill\n\nPlanning is only for work that needs coordination: multiple workflows,\ndependencies between workflows, shared data-table schema or migration work across\ntasks, multiple durable artifacts, broad best-practice research across many\nsources, genuinely ambiguous business-process architecture that cannot be\nresolved with one `build-workflow` call, or an explicit user request to review a\nplan first.\n\nIf shared data tables are involved, load `data-table-manager` before this skill\nand carry the relevant table guidance into workflow task specs. Clear\nsingle-workflow builds and existing-workflow edits use `workflow-builder` with\n`build-workflow` directly. Standalone data-table work uses `data-table-manager`\nwith direct `data-tables` and `parse-file` calls.\n\n## Knowledge Base\n\n**Consult the knowledge base before planning.** Read the relevant `.md` guides\nand templates for each technique the request involves (`knowledge-base\u002Findex.json`,\n`knowledge-base\u002Fbest-practices\u002Findex.json`, and linked files). Use\n`workspace_execute_command` with `rg` or `find` under `knowledge-base\u002Ftemplates\u002F`\nto locate matching SDK examples — never load `templates\u002Findex.json` wholesale.\nSkip only for trivial mechanical edits you have already reviewed in this thread.\n\n## Method\n\n1. Decide whether the request is plan-worthy by coordination need, not by\n   whether a workflow is new.\n2. Discover what materially affects the plan with normal tools:\n   `nodes(action=\"suggested\")`, `credentials(action=\"list\")`,\n   `data-tables(action=\"list\")`, `parse-file`, `workflows`, and `research`\n   when relevant.\n\n3. Prefer reasonable assumptions over questions. Ask the user only when the\n   answer would materially change the plan and cannot be discovered.\n4. Build a dependency-aware graph. Producers must come before consumers.\n   Independent tasks should not depend on each other.\n5. Put single workflow-local table requirements inside that workflow task spec.\n   Do not create separate data-table tasks unless the table work is a durable\n   artifact shared across tasks.\n6. Add checkpoint tasks only for exceptional semantic checks that normal\n   workflow verification cannot cover.\n7. Load `create-tasks` via `load_tool` if needed, then call `create-tasks` with\n   `planningContext.source: \"planning-skill\"`,\n   a concise `summary`, optional `assumptions`, `postBuildRunRequested: true`\n   only when the user explicitly asked to run, execute, or test a workflow\n   after building it, and the final task graph.\n8. After calling `create-tasks`, do not write visible text. The approval card is\n   the user-visible surface.\n\n## Task Graph Rules\n\n- Use task kinds exactly as supported: `build-workflow` and `checkpoint`.\n- Each task `id` must be stable and referenced by dependency edges.\n- Each `title` should be short and user-facing.\n- Each `spec` must be the complete executor briefing for that task. The task\n  executor may not see your broader planning notes.\n- For `build-workflow` tasks, make `spec` a structured executor briefing, not\n  freeform prose. Include these labels in this order: `Outcome`,\n  `Trigger mode`, `External systems`, `Required effects`, `Required branches`,\n  `Required data`, `Explicit constraints`, `Empty\u002Finvalid behavior`, and\n  `Done when`.\n- In `Required effects`, list every observable action the user asked for, such\n  as send email, send Telegram, write Google Sheets, create Notion pages, upsert\n  Data Table rows, or post one Slack summary.\n- In `Required branches`, state partial-failure behavior when multiple effects\n  start from the same trigger, and state whether no-results or invalid-input\n  paths need an explicit notification, fallback, log, or no-op.\n- In `Required data`, name fields needed by later conditions, filters, ranking,\n  response messages, or downstream effects, and note when those fields must\n  remain available after side-effect nodes that replace item JSON.\n- In `Explicit constraints`, preserve concrete user-provided resource names,\n  channels, tables, labels, URLs, and required node families or mechanisms. If\n  the user explicitly says to use a node family or mechanism such as HTTP\n  Request, webhook, form, MCP, or a service-native node, treat that as a hard\n  requirement unless it is impossible or contradicts another stated requirement.\n  Do not move those values to assumptions, replace them with placeholders, or\n  silently swap them for a more convenient alternative.\n- In `Empty\u002Finvalid behavior`, distinguish data that invalidates the whole item\n  from data that only affects one requested effect. For multi-effect intake\n  workflows, do not turn a field into a workflow-wide rejection requirement\n  merely because one message or side effect uses it.\n- In `Done when`, write observable acceptance checks, including final actions\n  and branch behavior. Do not write node-by-node wiring or fake user data.\n- If a `build-workflow` task's final deliverable is a supporting sub-workflow,\n  set `isSupportingWorkflow: true` on that task. Do not set it for helper\n  sub-workflows that are only intermediate artifacts inside a larger main\n  workflow task.\n- For `checkpoint` tasks, write structured semantic verification instructions:\n  `Verify trigger mode`, `Verify external systems`, `Verify required effects`,\n  `Verify required branches`, `Verify required data`,\n  `Verify explicit constraints`, `Verify empty\u002Finvalid behavior`, and\n  `Pass condition`. Checkpoints are exceptional; use this structure only when a\n  checkpoint is actually warranted.\n\n## Assumptions And Questions\n\n- Never ask about things tools can discover, such as available credentials,\n  existing data tables, workflow names, node availability, or attached-file\n  structure.\n- Never ask for implementation details such as node choices, column names, or\n  trigger mechanics when a sensible default exists.\n- Never ask for the user's timezone when the current date\u002Ftime section includes\n  it. Use that timezone for schedule times, cron assumptions, and digest windows.\n- Never default resource identifiers the user did not mention, such as Slack\n  channels, calendars, spreadsheets, folders, databases, or recipient lists.\n  Leave them for the builder to resolve or collect through setup.\n- Trust already-collected briefing context. If the conversation or task briefing\n  includes already-collected answers or already-discovered resources, treat them\n  as authoritative and do not ask again for purpose, trigger, integrations,\n  schedule, model, resource, or credential choices already listed there.\n- A question is asked at most once. Once the user has answered, deferred\n  (\"later\"), or skipped it, never re-present it. On a skip or deferral, record a\n  sensible assumption in `planningContext.assumptions` where a default exists\n  (for example a default morning time for a digest), otherwise leave the detail\n  for the builder or setup — do not block on it and do not ask again.\n- If exactly one matching credential exists, assume it and mention the\n  credential name in `planningContext.assumptions`.\n- If no matching credential exists, plan normally. The builder will mock or\n  leave it unresolved and route setup after verification.\n- If multiple matching credentials exist and the user did not name one, ask once\n  with `ask-user` because the choice cannot be discovered.\n- Use credential-backed resource investigation only when it changes the plan,\n  for example validating a named Slack channel that affects the architecture. Do\n  not turn resource lookup into a credential-choice question unless the\n  multiple-credentials rule applies.\n\n## Checkpoints\n\nWorkflow verification is automatic from structured build outcomes. Do not add\nroutine \"verify this workflow\" checkpoint tasks for every workflow.\n\nCheckpoint tasks are exceptional semantic checks. Use them for cross-workflow\ncontracts, confirming a report combines upstream data correctly, validating a\nbusiness invariant across deliverables, or checking a condition that cannot be\ncovered by normal runtime verification.\n\nDo not add checkpoints for routine verification-only work.\n\n## Revisions\n\nIf the user rejects the plan with requested changes, revise surgically, load\n`create-tasks` via `load_tool` if needed, and call `create-tasks` again in the\nsame orchestrator run with\n`planningContext.source: \"planning-skill\"`.\n\nIf the user denies the plan outright, stop. Do not call `create-tasks` again in\nthe same message group.\n",{"data":51,"body":61},{"name":4,"description":6,"recommended_tools":52},[53,54,55,56,57,58,59,60],"create-tasks","workflows","nodes","credentials","data-tables","parse-file","research","ask-user",{"type":62,"children":63},"root",[64,71,85,105,112,133,163,182,188,200,248,254,329,335,479,485,782,788,862,868,873,878,883,889,920],{"type":65,"tag":66,"props":67,"children":68},"element","h1",{"id":4},[69],{"type":70,"value":18},"text",{"type":65,"tag":72,"props":73,"children":74},"p",{},[75,77,83],{"type":70,"value":76},"Use this skill to design a dependency-aware task graph in the orchestrator and\nsubmit it with ",{"type":65,"tag":78,"props":79,"children":81},"code",{"className":80},[],[82],{"type":70,"value":53},{"type":70,"value":84},". Do not spawn another agent and do not use\nincremental plan item tools.",{"type":65,"tag":72,"props":86,"children":87},{},[88,90,95,97,103],{"type":70,"value":89},"Before calling ",{"type":65,"tag":78,"props":91,"children":93},{"className":92},[],[94],{"type":70,"value":53},{"type":70,"value":96},", load it via ",{"type":65,"tag":78,"props":98,"children":100},{"className":99},[],[101],{"type":70,"value":102},"load_tool",{"type":70,"value":104}," (search \"create tasks\" if\nit is not visible).",{"type":65,"tag":106,"props":107,"children":109},"h2",{"id":108},"when-not-to-use-this-skill",[110],{"type":70,"value":111},"When NOT to use this skill",{"type":65,"tag":72,"props":113,"children":114},{},[115,117,123,125,131],{"type":70,"value":116},"Stop and use ",{"type":65,"tag":78,"props":118,"children":120},{"className":119},[],[121],{"type":70,"value":122},"workflow-builder",{"type":70,"value":124}," + ",{"type":65,"tag":78,"props":126,"children":128},{"className":127},[],[129],{"type":70,"value":130},"build-workflow",{"type":70,"value":132}," instead when the request is:",{"type":65,"tag":134,"props":135,"children":136},"ul",{},[137,143,148,153,158],{"type":65,"tag":138,"props":139,"children":140},"li",{},[141],{"type":70,"value":142},"A new or one-off single workflow, even if it sounds large or unfamiliar",{"type":65,"tag":138,"props":144,"children":145},{},[146],{"type":70,"value":147},"An edit to one existing workflow (nodes, expressions, credentials, schedule, Code)",{"type":65,"tag":138,"props":149,"children":150},{},[151],{"type":70,"value":152},"Verification, setup, or credential collection for a workflow you just built",{"type":65,"tag":138,"props":154,"children":155},{},[156],{"type":70,"value":157},"A workflow-local data table whose schema ships with that same workflow",{"type":65,"tag":138,"props":159,"children":160},{},[161],{"type":70,"value":162},"Standalone data-table list\u002Fschema\u002Fquery\u002Fcreate\u002Fmutation work",{"type":65,"tag":72,"props":164,"children":165},{},[166,168,173,175,180],{"type":70,"value":167},"Do not call ",{"type":65,"tag":78,"props":169,"children":171},{"className":170},[],[172],{"type":70,"value":53},{"type":70,"value":174}," just to get approval, verification, or a checklist for\na single workflow. Workflow verification is automatic from structured build\noutcomes after ",{"type":65,"tag":78,"props":176,"children":178},{"className":177},[],[179],{"type":70,"value":130},{"type":70,"value":181},".",{"type":65,"tag":106,"props":183,"children":185},{"id":184},"when-to-use-this-skill",[186],{"type":70,"value":187},"When to use this skill",{"type":65,"tag":72,"props":189,"children":190},{},[191,193,198],{"type":70,"value":192},"Planning is only for work that needs coordination: multiple workflows,\ndependencies between workflows, shared data-table schema or migration work across\ntasks, multiple durable artifacts, broad best-practice research across many\nsources, genuinely ambiguous business-process architecture that cannot be\nresolved with one ",{"type":65,"tag":78,"props":194,"children":196},{"className":195},[],[197],{"type":70,"value":130},{"type":70,"value":199}," call, or an explicit user request to review a\nplan first.",{"type":65,"tag":72,"props":201,"children":202},{},[203,205,211,213,218,220,225,227,232,234,239,241,246],{"type":70,"value":204},"If shared data tables are involved, load ",{"type":65,"tag":78,"props":206,"children":208},{"className":207},[],[209],{"type":70,"value":210},"data-table-manager",{"type":70,"value":212}," before this skill\nand carry the relevant table guidance into workflow task specs. Clear\nsingle-workflow builds and existing-workflow edits use ",{"type":65,"tag":78,"props":214,"children":216},{"className":215},[],[217],{"type":70,"value":122},{"type":70,"value":219}," with\n",{"type":65,"tag":78,"props":221,"children":223},{"className":222},[],[224],{"type":70,"value":130},{"type":70,"value":226}," directly. Standalone data-table work uses ",{"type":65,"tag":78,"props":228,"children":230},{"className":229},[],[231],{"type":70,"value":210},{"type":70,"value":233},"\nwith direct ",{"type":65,"tag":78,"props":235,"children":237},{"className":236},[],[238],{"type":70,"value":57},{"type":70,"value":240}," and ",{"type":65,"tag":78,"props":242,"children":244},{"className":243},[],[245],{"type":70,"value":58},{"type":70,"value":247}," calls.",{"type":65,"tag":106,"props":249,"children":251},{"id":250},"knowledge-base",[252],{"type":70,"value":253},"Knowledge Base",{"type":65,"tag":72,"props":255,"children":256},{},[257,263,265,271,273,279,281,287,289,295,297,303,305,311,313,319,321,327],{"type":65,"tag":258,"props":259,"children":260},"strong",{},[261],{"type":70,"value":262},"Consult the knowledge base before planning.",{"type":70,"value":264}," Read the relevant ",{"type":65,"tag":78,"props":266,"children":268},{"className":267},[],[269],{"type":70,"value":270},".md",{"type":70,"value":272}," guides\nand templates for each technique the request involves (",{"type":65,"tag":78,"props":274,"children":276},{"className":275},[],[277],{"type":70,"value":278},"knowledge-base\u002Findex.json",{"type":70,"value":280},",\n",{"type":65,"tag":78,"props":282,"children":284},{"className":283},[],[285],{"type":70,"value":286},"knowledge-base\u002Fbest-practices\u002Findex.json",{"type":70,"value":288},", and linked files). Use\n",{"type":65,"tag":78,"props":290,"children":292},{"className":291},[],[293],{"type":70,"value":294},"workspace_execute_command",{"type":70,"value":296}," with ",{"type":65,"tag":78,"props":298,"children":300},{"className":299},[],[301],{"type":70,"value":302},"rg",{"type":70,"value":304}," or ",{"type":65,"tag":78,"props":306,"children":308},{"className":307},[],[309],{"type":70,"value":310},"find",{"type":70,"value":312}," under ",{"type":65,"tag":78,"props":314,"children":316},{"className":315},[],[317],{"type":70,"value":318},"knowledge-base\u002Ftemplates\u002F",{"type":70,"value":320},"\nto locate matching SDK examples — never load ",{"type":65,"tag":78,"props":322,"children":324},{"className":323},[],[325],{"type":70,"value":326},"templates\u002Findex.json",{"type":70,"value":328}," wholesale.\nSkip only for trivial mechanical edits you have already reviewed in this thread.",{"type":65,"tag":106,"props":330,"children":332},{"id":331},"method",[333],{"type":70,"value":334},"Method",{"type":65,"tag":336,"props":337,"children":338},"ol",{},[339,344,391,396,401,406,411,467],{"type":65,"tag":138,"props":340,"children":341},{},[342],{"type":70,"value":343},"Decide whether the request is plan-worthy by coordination need, not by\nwhether a workflow is new.",{"type":65,"tag":138,"props":345,"children":346},{},[347,349,355,357,363,364,370,371,376,377,382,384,389],{"type":70,"value":348},"Discover what materially affects the plan with normal tools:\n",{"type":65,"tag":78,"props":350,"children":352},{"className":351},[],[353],{"type":70,"value":354},"nodes(action=\"suggested\")",{"type":70,"value":356},", ",{"type":65,"tag":78,"props":358,"children":360},{"className":359},[],[361],{"type":70,"value":362},"credentials(action=\"list\")",{"type":70,"value":280},{"type":65,"tag":78,"props":365,"children":367},{"className":366},[],[368],{"type":70,"value":369},"data-tables(action=\"list\")",{"type":70,"value":356},{"type":65,"tag":78,"props":372,"children":374},{"className":373},[],[375],{"type":70,"value":58},{"type":70,"value":356},{"type":65,"tag":78,"props":378,"children":380},{"className":379},[],[381],{"type":70,"value":54},{"type":70,"value":383},", and ",{"type":65,"tag":78,"props":385,"children":387},{"className":386},[],[388],{"type":70,"value":59},{"type":70,"value":390},"\nwhen relevant.",{"type":65,"tag":138,"props":392,"children":393},{},[394],{"type":70,"value":395},"Prefer reasonable assumptions over questions. Ask the user only when the\nanswer would materially change the plan and cannot be discovered.",{"type":65,"tag":138,"props":397,"children":398},{},[399],{"type":70,"value":400},"Build a dependency-aware graph. Producers must come before consumers.\nIndependent tasks should not depend on each other.",{"type":65,"tag":138,"props":402,"children":403},{},[404],{"type":70,"value":405},"Put single workflow-local table requirements inside that workflow task spec.\nDo not create separate data-table tasks unless the table work is a durable\nartifact shared across tasks.",{"type":65,"tag":138,"props":407,"children":408},{},[409],{"type":70,"value":410},"Add checkpoint tasks only for exceptional semantic checks that normal\nworkflow verification cannot cover.",{"type":65,"tag":138,"props":412,"children":413},{},[414,416,421,423,428,430,435,436,442,444,450,452,458,459,465],{"type":70,"value":415},"Load ",{"type":65,"tag":78,"props":417,"children":419},{"className":418},[],[420],{"type":70,"value":53},{"type":70,"value":422}," via ",{"type":65,"tag":78,"props":424,"children":426},{"className":425},[],[427],{"type":70,"value":102},{"type":70,"value":429}," if needed, then call ",{"type":65,"tag":78,"props":431,"children":433},{"className":432},[],[434],{"type":70,"value":53},{"type":70,"value":219},{"type":65,"tag":78,"props":437,"children":439},{"className":438},[],[440],{"type":70,"value":441},"planningContext.source: \"planning-skill\"",{"type":70,"value":443},",\na concise ",{"type":65,"tag":78,"props":445,"children":447},{"className":446},[],[448],{"type":70,"value":449},"summary",{"type":70,"value":451},", optional ",{"type":65,"tag":78,"props":453,"children":455},{"className":454},[],[456],{"type":70,"value":457},"assumptions",{"type":70,"value":356},{"type":65,"tag":78,"props":460,"children":462},{"className":461},[],[463],{"type":70,"value":464},"postBuildRunRequested: true",{"type":70,"value":466},"\nonly when the user explicitly asked to run, execute, or test a workflow\nafter building it, and the final task graph.",{"type":65,"tag":138,"props":468,"children":469},{},[470,472,477],{"type":70,"value":471},"After calling ",{"type":65,"tag":78,"props":473,"children":475},{"className":474},[],[476],{"type":70,"value":53},{"type":70,"value":478},", do not write visible text. The approval card is\nthe user-visible surface.",{"type":65,"tag":106,"props":480,"children":482},{"id":481},"task-graph-rules",[483],{"type":70,"value":484},"Task Graph Rules",{"type":65,"tag":134,"props":486,"children":487},{},[488,506,519,532,544,627,639,650,661,672,683,694,714],{"type":65,"tag":138,"props":489,"children":490},{},[491,493,498,499,505],{"type":70,"value":492},"Use task kinds exactly as supported: ",{"type":65,"tag":78,"props":494,"children":496},{"className":495},[],[497],{"type":70,"value":130},{"type":70,"value":240},{"type":65,"tag":78,"props":500,"children":502},{"className":501},[],[503],{"type":70,"value":504},"checkpoint",{"type":70,"value":181},{"type":65,"tag":138,"props":507,"children":508},{},[509,511,517],{"type":70,"value":510},"Each task ",{"type":65,"tag":78,"props":512,"children":514},{"className":513},[],[515],{"type":70,"value":516},"id",{"type":70,"value":518}," must be stable and referenced by dependency edges.",{"type":65,"tag":138,"props":520,"children":521},{},[522,524,530],{"type":70,"value":523},"Each ",{"type":65,"tag":78,"props":525,"children":527},{"className":526},[],[528],{"type":70,"value":529},"title",{"type":70,"value":531}," should be short and user-facing.",{"type":65,"tag":138,"props":533,"children":534},{},[535,536,542],{"type":70,"value":523},{"type":65,"tag":78,"props":537,"children":539},{"className":538},[],[540],{"type":70,"value":541},"spec",{"type":70,"value":543}," must be the complete executor briefing for that task. The task\nexecutor may not see your broader planning notes.",{"type":65,"tag":138,"props":545,"children":546},{},[547,549,554,556,561,563,569,570,576,577,583,584,590,591,597,598,604,605,611,612,618,620,626],{"type":70,"value":548},"For ",{"type":65,"tag":78,"props":550,"children":552},{"className":551},[],[553],{"type":70,"value":130},{"type":70,"value":555}," tasks, make ",{"type":65,"tag":78,"props":557,"children":559},{"className":558},[],[560],{"type":70,"value":541},{"type":70,"value":562}," a structured executor briefing, not\nfreeform prose. Include these labels in this order: ",{"type":65,"tag":78,"props":564,"children":566},{"className":565},[],[567],{"type":70,"value":568},"Outcome",{"type":70,"value":280},{"type":65,"tag":78,"props":571,"children":573},{"className":572},[],[574],{"type":70,"value":575},"Trigger mode",{"type":70,"value":356},{"type":65,"tag":78,"props":578,"children":580},{"className":579},[],[581],{"type":70,"value":582},"External systems",{"type":70,"value":356},{"type":65,"tag":78,"props":585,"children":587},{"className":586},[],[588],{"type":70,"value":589},"Required effects",{"type":70,"value":356},{"type":65,"tag":78,"props":592,"children":594},{"className":593},[],[595],{"type":70,"value":596},"Required branches",{"type":70,"value":280},{"type":65,"tag":78,"props":599,"children":601},{"className":600},[],[602],{"type":70,"value":603},"Required data",{"type":70,"value":356},{"type":65,"tag":78,"props":606,"children":608},{"className":607},[],[609],{"type":70,"value":610},"Explicit constraints",{"type":70,"value":356},{"type":65,"tag":78,"props":613,"children":615},{"className":614},[],[616],{"type":70,"value":617},"Empty\u002Finvalid behavior",{"type":70,"value":619},", and\n",{"type":65,"tag":78,"props":621,"children":623},{"className":622},[],[624],{"type":70,"value":625},"Done when",{"type":70,"value":181},{"type":65,"tag":138,"props":628,"children":629},{},[630,632,637],{"type":70,"value":631},"In ",{"type":65,"tag":78,"props":633,"children":635},{"className":634},[],[636],{"type":70,"value":589},{"type":70,"value":638},", list every observable action the user asked for, such\nas send email, send Telegram, write Google Sheets, create Notion pages, upsert\nData Table rows, or post one Slack summary.",{"type":65,"tag":138,"props":640,"children":641},{},[642,643,648],{"type":70,"value":631},{"type":65,"tag":78,"props":644,"children":646},{"className":645},[],[647],{"type":70,"value":596},{"type":70,"value":649},", state partial-failure behavior when multiple effects\nstart from the same trigger, and state whether no-results or invalid-input\npaths need an explicit notification, fallback, log, or no-op.",{"type":65,"tag":138,"props":651,"children":652},{},[653,654,659],{"type":70,"value":631},{"type":65,"tag":78,"props":655,"children":657},{"className":656},[],[658],{"type":70,"value":603},{"type":70,"value":660},", name fields needed by later conditions, filters, ranking,\nresponse messages, or downstream effects, and note when those fields must\nremain available after side-effect nodes that replace item JSON.",{"type":65,"tag":138,"props":662,"children":663},{},[664,665,670],{"type":70,"value":631},{"type":65,"tag":78,"props":666,"children":668},{"className":667},[],[669],{"type":70,"value":610},{"type":70,"value":671},", preserve concrete user-provided resource names,\nchannels, tables, labels, URLs, and required node families or mechanisms. If\nthe user explicitly says to use a node family or mechanism such as HTTP\nRequest, webhook, form, MCP, or a service-native node, treat that as a hard\nrequirement unless it is impossible or contradicts another stated requirement.\nDo not move those values to assumptions, replace them with placeholders, or\nsilently swap them for a more convenient alternative.",{"type":65,"tag":138,"props":673,"children":674},{},[675,676,681],{"type":70,"value":631},{"type":65,"tag":78,"props":677,"children":679},{"className":678},[],[680],{"type":70,"value":617},{"type":70,"value":682},", distinguish data that invalidates the whole item\nfrom data that only affects one requested effect. For multi-effect intake\nworkflows, do not turn a field into a workflow-wide rejection requirement\nmerely because one message or side effect uses it.",{"type":65,"tag":138,"props":684,"children":685},{},[686,687,692],{"type":70,"value":631},{"type":65,"tag":78,"props":688,"children":690},{"className":689},[],[691],{"type":70,"value":625},{"type":70,"value":693},", write observable acceptance checks, including final actions\nand branch behavior. Do not write node-by-node wiring or fake user data.",{"type":65,"tag":138,"props":695,"children":696},{},[697,699,704,706,712],{"type":70,"value":698},"If a ",{"type":65,"tag":78,"props":700,"children":702},{"className":701},[],[703],{"type":70,"value":130},{"type":70,"value":705}," task's final deliverable is a supporting sub-workflow,\nset ",{"type":65,"tag":78,"props":707,"children":709},{"className":708},[],[710],{"type":70,"value":711},"isSupportingWorkflow: true",{"type":70,"value":713}," on that task. Do not set it for helper\nsub-workflows that are only intermediate artifacts inside a larger main\nworkflow task.",{"type":65,"tag":138,"props":715,"children":716},{},[717,718,723,725,731,732,738,739,745,746,752,753,759,760,766,767,773,774,780],{"type":70,"value":548},{"type":65,"tag":78,"props":719,"children":721},{"className":720},[],[722],{"type":70,"value":504},{"type":70,"value":724}," tasks, write structured semantic verification instructions:\n",{"type":65,"tag":78,"props":726,"children":728},{"className":727},[],[729],{"type":70,"value":730},"Verify trigger mode",{"type":70,"value":356},{"type":65,"tag":78,"props":733,"children":735},{"className":734},[],[736],{"type":70,"value":737},"Verify external systems",{"type":70,"value":356},{"type":65,"tag":78,"props":740,"children":742},{"className":741},[],[743],{"type":70,"value":744},"Verify required effects",{"type":70,"value":280},{"type":65,"tag":78,"props":747,"children":749},{"className":748},[],[750],{"type":70,"value":751},"Verify required branches",{"type":70,"value":356},{"type":65,"tag":78,"props":754,"children":756},{"className":755},[],[757],{"type":70,"value":758},"Verify required data",{"type":70,"value":280},{"type":65,"tag":78,"props":761,"children":763},{"className":762},[],[764],{"type":70,"value":765},"Verify explicit constraints",{"type":70,"value":356},{"type":65,"tag":78,"props":768,"children":770},{"className":769},[],[771],{"type":70,"value":772},"Verify empty\u002Finvalid behavior",{"type":70,"value":619},{"type":65,"tag":78,"props":775,"children":777},{"className":776},[],[778],{"type":70,"value":779},"Pass condition",{"type":70,"value":781},". Checkpoints are exceptional; use this structure only when a\ncheckpoint is actually warranted.",{"type":65,"tag":106,"props":783,"children":785},{"id":784},"assumptions-and-questions",[786],{"type":70,"value":787},"Assumptions And Questions",{"type":65,"tag":134,"props":789,"children":790},{},[791,796,801,806,811,816,829,840,845,857],{"type":65,"tag":138,"props":792,"children":793},{},[794],{"type":70,"value":795},"Never ask about things tools can discover, such as available credentials,\nexisting data tables, workflow names, node availability, or attached-file\nstructure.",{"type":65,"tag":138,"props":797,"children":798},{},[799],{"type":70,"value":800},"Never ask for implementation details such as node choices, column names, or\ntrigger mechanics when a sensible default exists.",{"type":65,"tag":138,"props":802,"children":803},{},[804],{"type":70,"value":805},"Never ask for the user's timezone when the current date\u002Ftime section includes\nit. Use that timezone for schedule times, cron assumptions, and digest windows.",{"type":65,"tag":138,"props":807,"children":808},{},[809],{"type":70,"value":810},"Never default resource identifiers the user did not mention, such as Slack\nchannels, calendars, spreadsheets, folders, databases, or recipient lists.\nLeave them for the builder to resolve or collect through setup.",{"type":65,"tag":138,"props":812,"children":813},{},[814],{"type":70,"value":815},"Trust already-collected briefing context. If the conversation or task briefing\nincludes already-collected answers or already-discovered resources, treat them\nas authoritative and do not ask again for purpose, trigger, integrations,\nschedule, model, resource, or credential choices already listed there.",{"type":65,"tag":138,"props":817,"children":818},{},[819,821,827],{"type":70,"value":820},"A question is asked at most once. Once the user has answered, deferred\n(\"later\"), or skipped it, never re-present it. On a skip or deferral, record a\nsensible assumption in ",{"type":65,"tag":78,"props":822,"children":824},{"className":823},[],[825],{"type":70,"value":826},"planningContext.assumptions",{"type":70,"value":828}," where a default exists\n(for example a default morning time for a digest), otherwise leave the detail\nfor the builder or setup — do not block on it and do not ask again.",{"type":65,"tag":138,"props":830,"children":831},{},[832,834,839],{"type":70,"value":833},"If exactly one matching credential exists, assume it and mention the\ncredential name in ",{"type":65,"tag":78,"props":835,"children":837},{"className":836},[],[838],{"type":70,"value":826},{"type":70,"value":181},{"type":65,"tag":138,"props":841,"children":842},{},[843],{"type":70,"value":844},"If no matching credential exists, plan normally. The builder will mock or\nleave it unresolved and route setup after verification.",{"type":65,"tag":138,"props":846,"children":847},{},[848,850,855],{"type":70,"value":849},"If multiple matching credentials exist and the user did not name one, ask once\nwith ",{"type":65,"tag":78,"props":851,"children":853},{"className":852},[],[854],{"type":70,"value":60},{"type":70,"value":856}," because the choice cannot be discovered.",{"type":65,"tag":138,"props":858,"children":859},{},[860],{"type":70,"value":861},"Use credential-backed resource investigation only when it changes the plan,\nfor example validating a named Slack channel that affects the architecture. Do\nnot turn resource lookup into a credential-choice question unless the\nmultiple-credentials rule applies.",{"type":65,"tag":106,"props":863,"children":865},{"id":864},"checkpoints",[866],{"type":70,"value":867},"Checkpoints",{"type":65,"tag":72,"props":869,"children":870},{},[871],{"type":70,"value":872},"Workflow verification is automatic from structured build outcomes. Do not add\nroutine \"verify this workflow\" checkpoint tasks for every workflow.",{"type":65,"tag":72,"props":874,"children":875},{},[876],{"type":70,"value":877},"Checkpoint tasks are exceptional semantic checks. Use them for cross-workflow\ncontracts, confirming a report combines upstream data correctly, validating a\nbusiness invariant across deliverables, or checking a condition that cannot be\ncovered by normal runtime verification.",{"type":65,"tag":72,"props":879,"children":880},{},[881],{"type":70,"value":882},"Do not add checkpoints for routine verification-only work.",{"type":65,"tag":106,"props":884,"children":886},{"id":885},"revisions",[887],{"type":70,"value":888},"Revisions",{"type":65,"tag":72,"props":890,"children":891},{},[892,894,899,900,905,907,912,914,919],{"type":70,"value":893},"If the user rejects the plan with requested changes, revise surgically, load\n",{"type":65,"tag":78,"props":895,"children":897},{"className":896},[],[898],{"type":70,"value":53},{"type":70,"value":422},{"type":65,"tag":78,"props":901,"children":903},{"className":902},[],[904],{"type":70,"value":102},{"type":70,"value":906}," if needed, and call ",{"type":65,"tag":78,"props":908,"children":910},{"className":909},[],[911],{"type":70,"value":53},{"type":70,"value":913}," again in the\nsame orchestrator run with\n",{"type":65,"tag":78,"props":915,"children":917},{"className":916},[],[918],{"type":70,"value":441},{"type":70,"value":181},{"type":65,"tag":72,"props":921,"children":922},{},[923,925,930],{"type":70,"value":924},"If the user denies the plan outright, stop. Do not call ",{"type":65,"tag":78,"props":926,"children":928},{"className":927},[],[929],{"type":70,"value":53},{"type":70,"value":931}," again in\nthe same message group.",{"items":933,"total":1080},[934,949,964,977,989,1002,1014,1031,1040,1047,1057,1066],{"slug":935,"name":935,"fn":936,"description":937,"org":938,"tags":939,"stars":22,"repoUrl":23,"updatedAt":948},"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},[940,943,944,947],{"name":941,"slug":942,"type":13},"Evals","evals",{"name":8,"slug":8,"type":13},{"name":945,"slug":946,"type":13},"Testing","testing",{"name":20,"slug":21,"type":13},"2026-07-24T05:37:07.398695",{"slug":950,"name":950,"fn":951,"description":952,"org":953,"tags":954,"stars":22,"repoUrl":23,"updatedAt":963},"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},[955,956,959,960],{"name":15,"slug":16,"type":13},{"name":957,"slug":958,"type":13},"Configuration","configuration",{"name":8,"slug":8,"type":13},{"name":961,"slug":962,"type":13},"OAuth","oauth","2026-06-30T07:40:45.54",{"slug":210,"name":210,"fn":965,"description":966,"org":967,"tags":968,"stars":22,"repoUrl":23,"updatedAt":976},"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},[969,972,975],{"name":970,"slug":971,"type":13},"Data Engineering","data-engineering",{"name":973,"slug":974,"type":13},"Database","database",{"name":8,"slug":8,"type":13},"2026-07-27T06:07:14.648144",{"slug":978,"name":978,"fn":979,"description":980,"org":981,"tags":982,"stars":22,"repoUrl":23,"updatedAt":963},"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},[983,984,987,988],{"name":15,"slug":16,"type":13},{"name":985,"slug":986,"type":13},"Debugging","debugging",{"name":8,"slug":8,"type":13},{"name":20,"slug":21,"type":13},{"slug":990,"name":990,"fn":991,"description":992,"org":993,"tags":994,"stars":22,"repoUrl":23,"updatedAt":1001},"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},[995,998,999,1000],{"name":996,"slug":997,"type":13},"Agents","agents",{"name":15,"slug":16,"type":13},{"name":8,"slug":8,"type":13},{"name":20,"slug":21,"type":13},"2026-07-30T05:30:06.772347",{"slug":1003,"name":1003,"fn":1004,"description":1005,"org":1006,"tags":1007,"stars":22,"repoUrl":23,"updatedAt":1013},"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},[1008,1009,1011,1012],{"name":15,"slug":16,"type":13},{"name":1010,"slug":30,"type":13},"CLI",{"name":8,"slug":8,"type":13},{"name":20,"slug":21,"type":13},"2026-04-06T18:38:40.360123",{"slug":1015,"name":1015,"fn":1016,"description":1017,"org":1018,"tags":1019,"stars":22,"repoUrl":23,"updatedAt":1030},"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},[1020,1023,1024,1027],{"name":1021,"slug":1022,"type":13},"Documentation","documentation",{"name":8,"slug":8,"type":13},{"name":1025,"slug":1026,"type":13},"Reference","reference",{"name":1028,"slug":1029,"type":13},"Search","search","2026-07-27T06:07:15.692906",{"slug":1032,"name":1032,"fn":1033,"description":1034,"org":1035,"tags":1036,"stars":22,"repoUrl":23,"updatedAt":963},"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},[1037,1038,1039],{"name":15,"slug":16,"type":13},{"name":8,"slug":8,"type":13},{"name":20,"slug":21,"type":13},{"slug":4,"name":4,"fn":5,"description":6,"org":1041,"tags":1042,"stars":22,"repoUrl":23,"updatedAt":24},{"slug":8,"name":8,"logoUrl":9,"githubOrg":10},[1043,1044,1045,1046],{"name":15,"slug":16,"type":13},{"name":8,"slug":8,"type":13},{"name":18,"slug":4,"type":13},{"name":20,"slug":21,"type":13},{"slug":1048,"name":1048,"fn":1049,"description":1050,"org":1051,"tags":1052,"stars":22,"repoUrl":23,"updatedAt":1056},"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},[1053,1054,1055],{"name":15,"slug":16,"type":13},{"name":8,"slug":8,"type":13},{"name":20,"slug":21,"type":13},"2026-07-24T05:37:08.421329",{"slug":122,"name":122,"fn":1058,"description":1059,"org":1060,"tags":1061,"stars":22,"repoUrl":23,"updatedAt":1065},"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},[1062,1063,1064],{"name":15,"slug":16,"type":13},{"name":8,"slug":8,"type":13},{"name":20,"slug":21,"type":13},"2026-07-30T05:30:07.798011",{"slug":1067,"name":1067,"fn":1068,"description":1069,"org":1070,"tags":1071,"stars":1077,"repoUrl":1078,"updatedAt":1079},"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},[1072,1073,1076],{"name":996,"slug":997,"type":13},{"name":1074,"slug":1075,"type":13},"LLM","llm",{"name":20,"slug":21,"type":13},319,"https:\u002F\u002Fgithub.com\u002Fn8n-io\u002Fskills","2026-07-08T05:44:47.938896",25,{"items":1082,"total":1131},[1083,1090,1097,1103,1110,1117,1124],{"slug":935,"name":935,"fn":936,"description":937,"org":1084,"tags":1085,"stars":22,"repoUrl":23,"updatedAt":948},{"slug":8,"name":8,"logoUrl":9,"githubOrg":10},[1086,1087,1088,1089],{"name":941,"slug":942,"type":13},{"name":8,"slug":8,"type":13},{"name":945,"slug":946,"type":13},{"name":20,"slug":21,"type":13},{"slug":950,"name":950,"fn":951,"description":952,"org":1091,"tags":1092,"stars":22,"repoUrl":23,"updatedAt":963},{"slug":8,"name":8,"logoUrl":9,"githubOrg":10},[1093,1094,1095,1096],{"name":15,"slug":16,"type":13},{"name":957,"slug":958,"type":13},{"name":8,"slug":8,"type":13},{"name":961,"slug":962,"type":13},{"slug":210,"name":210,"fn":965,"description":966,"org":1098,"tags":1099,"stars":22,"repoUrl":23,"updatedAt":976},{"slug":8,"name":8,"logoUrl":9,"githubOrg":10},[1100,1101,1102],{"name":970,"slug":971,"type":13},{"name":973,"slug":974,"type":13},{"name":8,"slug":8,"type":13},{"slug":978,"name":978,"fn":979,"description":980,"org":1104,"tags":1105,"stars":22,"repoUrl":23,"updatedAt":963},{"slug":8,"name":8,"logoUrl":9,"githubOrg":10},[1106,1107,1108,1109],{"name":15,"slug":16,"type":13},{"name":985,"slug":986,"type":13},{"name":8,"slug":8,"type":13},{"name":20,"slug":21,"type":13},{"slug":990,"name":990,"fn":991,"description":992,"org":1111,"tags":1112,"stars":22,"repoUrl":23,"updatedAt":1001},{"slug":8,"name":8,"logoUrl":9,"githubOrg":10},[1113,1114,1115,1116],{"name":996,"slug":997,"type":13},{"name":15,"slug":16,"type":13},{"name":8,"slug":8,"type":13},{"name":20,"slug":21,"type":13},{"slug":1003,"name":1003,"fn":1004,"description":1005,"org":1118,"tags":1119,"stars":22,"repoUrl":23,"updatedAt":1013},{"slug":8,"name":8,"logoUrl":9,"githubOrg":10},[1120,1121,1122,1123],{"name":15,"slug":16,"type":13},{"name":1010,"slug":30,"type":13},{"name":8,"slug":8,"type":13},{"name":20,"slug":21,"type":13},{"slug":1015,"name":1015,"fn":1016,"description":1017,"org":1125,"tags":1126,"stars":22,"repoUrl":23,"updatedAt":1030},{"slug":8,"name":8,"logoUrl":9,"githubOrg":10},[1127,1128,1129,1130],{"name":1021,"slug":1022,"type":13},{"name":8,"slug":8,"type":13},{"name":1025,"slug":1026,"type":13},{"name":1028,"slug":1029,"type":13},11]