[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-n8n-using-n8n-skills-official":3,"mdc-vevhwk-key":29,"related-repo-n8n-using-n8n-skills-official":2468,"related-org-n8n-using-n8n-skills-official":2568},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":19,"repoUrl":20,"updatedAt":21,"license":22,"forks":23,"topics":24,"repo":25,"sourceUrl":27,"mdContent":28},"using-n8n-skills-official","manage n8n workflows","Use when working with n8n workflows in any capacity. The always-on protocol for the n8n-skills plugin, loaded by the SessionStart hook every session. Routes to the right skill, summarizes every n8n MCP tool (closing the deferred-description gap), and lists the cross-cutting rules.",{"slug":8,"name":8,"logoUrl":9,"githubOrg":10},"n8n","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fn8n.png","n8n-io",[12,16],{"name":13,"slug":14,"type":15},"Productivity","productivity","tag",{"name":17,"slug":18,"type":15},"Workflow Automation","workflow-automation",319,"https:\u002F\u002Fgithub.com\u002Fn8n-io\u002Fskills","2026-07-17T05:32:09.381704",null,30,[],{"repoUrl":20,"stars":19,"forks":23,"topics":26,"description":22},[],"https:\u002F\u002Fgithub.com\u002Fn8n-io\u002Fskills\u002Ftree\u002FHEAD\u002Fskills\u002Fusing-n8n-skills-official","---\nname: using-n8n-skills-official\ndescription: Use when working with n8n workflows in any capacity. The always-on protocol for the n8n-skills plugin, loaded by the SessionStart hook every session. Routes to the right skill, summarizes every n8n MCP tool (closing the deferred-description gap), and lists the cross-cutting rules.\n---\n\n# Using n8n Skills\n\nThe official n8n MCP evolves over time, so tool names, parameters, and default behaviors can drift between versions. When you spot drift (a tool a skill names doesn't exist, a parameter shape doesn't match what `get_node_types` returns, or behavior differs from what the skill describes), suggest updating the skill and n8n instance to the latest stable.\n\n## Non-negotiables\n\nThree rules with no exceptions. Violating any produces workflows that look right but break in production.\n\n1. **Invoke the relevant skill before any n8n action.** Not just MCP tool calls. Before writing SDK code, configuring a node, designing a workflow, wiring a connection, building an agent, or handling errors: invoke the matching skill via the Skill tool. This document is a router. The skill body has the actual rules. The PreToolUse hooks remind you on the highest-impact MCP calls if a plugin is installed. The responsibility is yours on everything else. Err on the side of reading extra documents.\n2. **Validate AND verify before publishing.** `validate_workflow` before `publish_workflow`, and `get_workflow_details` after every create or update to check the `connections` object. Validation alone misses many issues documented in the skills that will silently break workflows.\n3. **Tokens\u002Fsecrets never go in text fields.** Always use the n8n credential system. If no native node exists, configure HTTP Request with the official credential type. See `n8n-credentials-and-security-official`.\n\n## Lean on skills, not training data\n\nn8n evolves faster than any model's training cutoff. Parameter names drift, new MCP tools land, defaults change, patterns get deprecated. Anything you \"remember\" is likely wrong, often silently.\n\nTrust the skills + live MCP tools (`get_node_types`, `get_sdk_reference`, `get_workflow_best_practices`) over recollection. If a skill contradicts what you \"know\", trust the skill. If `get_node_types` contradicts a skill, trust the tool. Without this discipline you will ship workflows that look right and silently fail: parameter names that don't exist, renamed nodes, deprecated patterns.\n\nUnless a user preference overrides it, err on the side of loading too many skills rather than too few. Even a 3-node webhook flow typically needs `n8n-node-configuration-official`, `n8n-expressions-official`, `n8n-error-handling-official`, and `n8n-workflow-lifecycle-official`. Nothing in n8n is too small for skills.\n\n## Strong defaults (each skill owns its exceptions)\n\n- **The Code node is a last resort.** Expression first, then arrow function inside Edit Fields, then Code. Code earns its place for multi-source aggregation, libraries, and stateful work. See `n8n-code-nodes-official`.\n- **Anything reusable becomes a stateless sub-workflow.** Search existing ones via `search_workflows({ tags: ['subworkflow'] })` before building. See `n8n-subworkflows-official`.\n\n## Red flags: thoughts that mean STOP and invoke\n\nThese rationalizations cause skills to be skipped. If you catch yourself thinking any of them, invoke the relevant skill via the Skill tool, **even if you \"already read it\" earlier in the session**.\n\n| Thought | Action |\n|---|---|\n| \"This workflow is simple, I'll just build it\" | Invoke `n8n-workflow-lifecycle-official`. Most \"simple\" workflows are 10+ nodes by the time they ship. |\n| \"I'll add a Set node here to map these fields\" | Invoke `n8n-expressions-official`. Set nodes feeding only 0 or 1 downstream consumer are the most common antipattern in this entire pack. |\n| \"I'll just use a Code node, it's easier\" | Invoke `n8n-code-nodes-official`. The bar is high. Most reaches for Code can be expressions or Edit Fields with arrow functions. |\n| \"Validation passed, I'm ready to publish\" | Invoke `n8n-workflow-lifecycle-official` and walk `VALIDATION_CHECKLIST.md` section 2 (the antipattern scan). Validation passing is necessary, not sufficient. |\n| \"The agent is wired up, the tool descriptions look fine\" | Invoke `n8n-agents-official` `references\u002FTOOLS.md`. Tool names and descriptions ARE part of the prompt, and \"looks fine\" usually means generic. |\n| \"I'll set this sub-workflow trigger to passthrough\" | Invoke `n8n-subworkflows-official`. Passthrough is only correct for binary-receiving sub-workflows that won't be agent tools, or for sub-workflows that genuinely take no inputs (Define Below requires at least one field). |\n| \"I'll use passthrough so binary works, then branch internally on which input shape arrived\" | Invoke `n8n-subworkflows-official` `references\u002FSUBWORKFLOW_PATTERNS.md` \"Splitting by input shape\". This is the signal to SPLIT into two outer sub-workflows (one Define Below, one passthrough) sharing a common downstream sub-workflow. Don't fight passthrough vs Define Below in one trigger. |\n| \"This section's big, I'll pull it into a sub-workflow\" | If it's only to tidy the canvas (not reuse\u002Fisolation\u002Ftesting), a node group is lighter, faster, and simpler: keep it inline and group it via `setNodeGroups`. Extract to a sub-workflow only for reuse, isolation, or an agent tool. See `n8n-workflow-lifecycle-official` Readability. |\n| \"I should ask the user what their credential is named\" | Don't. The string in `newCredential('Label')` is cosmetic. See `n8n-credentials-and-security-official`. |\n| \"The user mentioned data analysis, I'll write Python\" | Invoke `n8n-code-nodes-official`. Default is JavaScript. Python only when explicitly asked. |\n| \"I'll add a Loop Over Items here to process each row\" | Invoke `n8n-loops-official`. Default per-item iteration probably handles it without a Loop Over Items node. |\n| \"Date math, I'll use a DateTime node\" | Invoke `n8n-expressions-official`. DateTime nodes are almost always wrong. |\n| \"I'll wrap this in a Merge with 3 sources\" | Invoke `n8n-node-configuration-official` `references\u002FMERGE_NODE.md`. Merge defaults to 2 inputs, and 3+ sources need `numberOfInputs` set explicitly. |\n| \"I'll fan out these three slow steps to run in parallel\" | Invoke `n8n-workflow-lifecycle-official` and read the Execution model section. n8n executes fan-out branches sequentially (top-to-bottom by Y-position), not concurrently. For real concurrency, see `n8n-loops-official` and `n8n-subworkflows-official` (`mode: 'each'` + `waitForSubWorkflow: false`). |\n| \"User said which project, I'll just build it\" | Invoke `n8n-workflow-lifecycle-official`. Project is not folder. Ask about folder placement BEFORE building. The MCP can't create folders, so if the requested folder doesn't exist, the user must create it in the UI first. |\n| \"I'll just run `test_workflow` to see what happens\" | Invoke `n8n-workflow-lifecycle-official` `references\u002FTESTING.md`. `test_workflow` mocks the trigger only. Slack sends, DB writes, payments all fire for real. Ask the user first when downstreams have side effects. |\n\n**The meta-skill (this document) tells you WHICH skill applies. The Skill tool loads the actual rules.** Reading the meta-skill once at session start is not a substitute for invoking the skill at the moment of decision.\n\n## Skill index\n\nInvoke via the Skill tool. Trigger column = when to invoke.\n\n| Skill | Trigger |\n|---|---|\n| `n8n-workflow-lifecycle-official` | Starting, designing, organizing, or finishing a workflow. Covers sticky-note conventions, descriptions that capture the *why*, naming, validation checklist, folder limitations, MCP-access-per-workflow gotcha |\n| `n8n-subworkflows-official` | Anything reusable, multi-step builds, or the user mentions reuse. Search before building, stateless patterns, tag-based discovery convention |\n| `n8n-extending-mcp-official` | You need capabilities the MCP doesn't natively provide. Wrap n8n APIs as workflow tools, with user permission |\n| `n8n-expressions-official` | Writing `{{}}`, `$json`, `$node`, expression errors. Luxon for dates, indented multi-line, prefer expressions over extra nodes |\n| `n8n-node-configuration-official` | Configuring any node. Operation-aware, property dependencies, never assume parameters |\n| `n8n-code-nodes-official` | User reaches for a Code node, or custom logic is needed. Decision tree, JavaScript patterns when truly required |\n| `n8n-loops-official` | Multi-item data, batching, paginated APIs, \"for each\" or \"loop over\" mentions. Default per-item iteration, `executeOnce`, Loop Over Items, HTTP pagination |\n| `n8n-agents-official` | LangChain Agent node, tool calling, system prompts, structured output, memory, RAG. Tool names\u002Fdescriptions as part of the prompt, sub-workflow as tool, modular prompt design |\n| `n8n-error-handling-official` | Webhook-triggered or production-bound workflows. Error branch on every fallible node, 4xx for caller errors and 5xx for execution errors |\n| `n8n-credentials-and-security-official` | Any auth, API key, or token mention. Credential system, custom credentials, HTTP Request with official creds |\n| `n8n-binary-and-data-official` | Files, images, attachments. Binary handling patterns, agent-tool boundary, CDN requirement for chat surfaces |\n| `n8n-data-tables-official` | Data Tables: schemas, default columns (id\u002FcreatedAt\u002FupdatedAt), no-FK relational design, dedup, the no-JSON-only-primitives rule, the SDK-vs-UI manual-mapping quirk |\n| `n8n-debugging-official` | Errors, unexpected behavior, \"this isn't working\". Believe the user, check parameters, fetch n8n source from GitHub |\n\n## n8n MCP tools (compact reference)\n\nThe MCP defers tool descriptions to save tokens. Below is the short-form list so you have working knowledge of every tool from turn one.\n\nTool names are shown without the MCP prefix. The qualified name is `mcp__\u003Cserver>__\u003Ctool>` where `\u003Cserver>` depends on the user's MCP config.\n\n### Workflow management\n\n| Tool | What it does |\n|---|---|\n| `search_workflows` | Search workflows across the instance by `query` (substring on name\u002Fdescription) and\u002For `tags` (exact tag names, AND semantics: must have all). The primary cross-workflow **discovery** tool. Use it to discover what already exists. |\n| `get_workflow_details` | Fetch a workflow's full JSON by ID. Use after every create\u002Fupdate to verify connections. |\n| `search_folders` | List folders. **You cannot create or move folders.** You can only place workflows into folders that already exist. |\n| `search_projects` | List projects. |\n| `list_tags` | List all workflow tags (with `usageCount` per tag). Check the instance's tag vocabulary before tagging or filtering, so you reuse exact names. Tags are attached\u002Fdetached via `update_workflow` `addTags`\u002F`removeTags`; there's no tag rename\u002Fdelete tool. |\n| `archive_workflow` \u002F `publish_workflow` \u002F `unpublish_workflow` | Soft-delete \u002F activate \u002F deactivate. Validate before publish. `publish_workflow` takes an optional `versionId` to re-publish a specific version. |\n| `search_executions` | Search executions across the instance (filter by status, workflow, time range). Use for \"list recent runs\" \u002F \"failures in the last hour\". Single executions: `get_execution`. |\n\n### Workflow building\n\n| Tool | What it does |\n|---|---|\n| `get_sdk_reference` | Fetch the n8n Workflow SDK reference. **Read this before writing workflow code.** Sections: `patterns`, `patterns_detailed`, `expressions`, `functions`, `rules`, `import`, `guidelines`, `design`, `all`. |\n| `get_workflow_best_practices` | Fetch best-practices for a workflow technique. Call once per technique before searching nodes. `technique: \"list\"` discovers what's available. |\n| `search_nodes` | Discover nodes by capability (e.g. \"gmail\", \"slack\", \"schedule trigger\"). Returns IDs plus discriminators (resource\u002Foperation\u002Fmode). |\n| `get_node_types` | Fetch exact TypeScript parameter definitions for node IDs. **Required before configuring any node.** Don't guess parameter names. |\n| `explore_node_resources` | Resolve the real values behind resource-locator (`@searchListMethod`) and load-options (`@loadOptionsMethod`) params: Slack channels, Sheets tabs\u002Fdocs, DB tables\u002Fcolumns, model lists, labels. Needs a `credentialId` from `list_credentials` (pass `currentNodeParameters` for dependent lookups). Call after `get_node_types` to ground dropdown values instead of inventing IDs. |\n| `create_workflow_from_code` | Save a workflow from SDK code. Always include a 1-2 sentence `description`. Pass `skillsUsed` (below). |\n| `update_workflow` | Apply atomic ops (max 100, all-or-nothing): node\u002Fconnection CRUD, `setNodeCredential`, `setNodeSettings` (per-node onError\u002Fretry\u002FexecuteOnce), `setWorkflowSettings` (errorWorkflow, timezone, callerPolicy, timeouts, save-data policies; n8n 2.29.0+), `setNodeGroups` (canvas grouping), `setWorkflowMetadata`, `addTags`\u002F`removeTags` (auto-create unknown names). Saves a draft; needs `publish_workflow` to go live. Pass `skillsUsed` (below). |\n| `validate_node_config` | Schema-only validation of node configs (1-50 per call). Per-parameter errors, no graph noise. Side-channel for iteration\u002Fdebug; `validate_workflow` still gates publish. For ai_tool subnodes set `isToolNode: true`. |\n| `validate_workflow` | Validate full SDK code before create\u002Fupdate. Necessary but **not sufficient**: doesn't catch all wiring traps (`.to()`, merge index). |\n| `list_credentials` | List accessible credentials (filter by type\u002Fproject\u002Fetc). Returns metadata only, **never secret values**. Discover IDs before binding via `setNodeCredential`. |\n\n### Workflow testing & execution\n\n| Tool | What it does |\n|---|---|\n| `prepare_test_pin_data` | Returns JSON Schemas (not data) for nodes that need pinning: triggers, credentialed nodes, and HTTP Request. You generate sample values. |\n| `test_workflow` | Run with the pin data you supply. **Auto-pins triggers, credentialed nodes, and HTTP Request.** Code, Edit Fields, If, Data Tables, Execute Command, file ops, and sub-workflow calls run for real. Ask before running if any not-auto-pinned node has side effects. Pin data is per-execution only with no visual indicator in the execution viewer, so tell the user which nodes were pinned after the call. See `n8n-workflow-lifecycle-official` `references\u002FTESTING.md`. |\n| `execute_workflow` | Production execution with the real trigger. Wire error handling first. Same side-effect rules as `test_workflow`. **`executionMode` is required** — use `\"manual\"` for testing or validating the current workflow (including tests against live external services), and `\"production\"` only when intentionally running the published workflow as a live execution. Structured `inputs` for chat\u002Fform\u002Fwebhook triggers. Returns an execution ID immediately without waiting; poll `get_execution` for results. |\n| `get_execution` | Fetch an execution by `executionId` + `workflowId` (both required). Metadata only by default; set `includeData: true` (optionally `nodeNames`, `truncateData`) for node inputs\u002Foutputs. |\n\n### Data tables\n\nn8n's built-in tabular storage. **Not** an external service. Prefer over external DBs for workflow-local persistent state. Full surface:\n\n| Tool | What it does |\n|---|---|\n| `create_data_table` | Create a new Data Table. |\n| `search_data_tables` | Find existing Data Tables. |\n| `rename_data_table` \u002F `rename_data_table_column` | Rename. |\n| `add_data_table_column` \u002F `delete_data_table_column` | Schema changes. |\n| `add_data_table_rows` | Append rows. |\n\n### Version history\n\n| Tool | What it does |\n|---|---|\n| `get_workflow_history` | List a workflow's saved versions, newest first (n8n 2.29.0+). |\n| `get_workflow_version` | Fetch a past version's full content by `versionId`. |\n| `restore_workflow_version` | Re-apply a past version as the current draft (records a new history entry). |\n\n## The protocol, in order\n\nFor any n8n task:\n\n1. **Recognize the matching skill** from the index above. If the task spans skills, recognize the primary one first and pick up others as their triggers come up.\n2. **Invoke the skill via the Skill tool** before the first MCP call. Don't call n8n MCP tools blind.\n3. **Read the SDK reference once per session** before writing workflow code (`get_sdk_reference`). The most efficient way to avoid SDK-shape mistakes.\n4. **Get node types before configuring any node** (`get_node_types`). Guessing parameter names creates invalid workflows, sometimes silently.\n5. **Validate before publish, verify after create\u002Fupdate.** Validation catches schema errors. Verification (pulling the workflow back via `get_workflow_details`) catches connection bugs validation misses.\n6. **Surface drift when you spot it.** If a tool or parameter doesn't match what a skill says, tell the user. Updates may be needed.\n\n## Reporting skills used\n\n`create_workflow_from_code` and `update_workflow` take an optional `skillsUsed: string[]`. Pass it every time so the n8n team can measure plugin impact on MCP output.\n\n- **Contents:** report each skill exactly as the Skill tool names it, keeping the `-official` suffix: `plugin:skill-official` when plugin-namespaced, else bare `skill-official`. The suffix marks these as ours (vs other n8n packs); the plugin prefix marks plugin vs raw-skill usage.\n- **Window:** skills invoked since the last successful create\u002Fupdate call. Resets after each.\n- **Limits:** max 50 entries, each max 128 chars.\n\n## Reviewing existing workflows or projects\n\nFor audits, code-review, or any task framed as \"review this workflow\" \u002F \"what's wrong with this\" \u002F \"audit this project,\" walk the **review checklist**: `n8n-workflow-lifecycle-official` `references\u002FREVIEW_CHECKLIST.md`. Severity-tiered (MUST FIX \u002F SHOULD FIX \u002F NICE TO HAVE), with each item linking to the canonical skill ref for the fix. Distinct from `VALIDATION_CHECKLIST.md` (pre-publish gates for in-progress builds): REVIEW_CHECKLIST is for any workflow, including ones built by anyone, any age.\n\nA review agent should call `get_workflow_details` first, walk the checklist top to bottom, and report findings grouped by severity. MUST FIX items shouldn't be auto-fixed without user confirmation.\n\n## When in doubt\n\n- **Can't find a workflow the user is referring to?** If the user built it in the n8n UI, the most common reason is **MCP access isn't enabled on that specific workflow**: UI-created workflows can default to MCP-disabled and stay invisible until the per-workflow toggle is flipped. Ask the user: \"Open the workflow in n8n, Settings, toggle MCP access on.\" (MCP-created workflows default on, so this only applies to UI-built ones.) See the `n8n-workflow-lifecycle-official` skill (`references\u002FMCP_ACCESS_PER_WORKFLOW.md`).\n- The user is right. If they say something's broken, believe them, even if you \"know\" the workflow is correct. Re-check parameters, fetch the n8n source from `github.com\u002Fn8n-io\u002Fn8n` to trace logic, find API docs for missing functions. The `n8n-debugging-official` skill walks through this.\n- If no skill fits and the task is non-trivial, ask before guessing.\n- These skills are opinionated, but considered best practice by the n8n team. The user can override any opinion by editing the SKILL.md. The plugin is just markdown.\n",{"data":30,"body":31},{"name":4,"description":6},{"type":32,"children":33},"root",[34,43,58,65,70,146,152,157,191,225,231,277,283,294,735,745,751,756,1028,1034,1039,1060,1067,1304,1310,1747,1753,1946,1952,1964,2083,2089,2166,2172,2177,2260,2266,2290,2347,2353,2386,2398,2404],{"type":35,"tag":36,"props":37,"children":39},"element","h1",{"id":38},"using-n8n-skills",[40],{"type":41,"value":42},"text","Using n8n Skills",{"type":35,"tag":44,"props":45,"children":46},"p",{},[47,49,56],{"type":41,"value":48},"The official n8n MCP evolves over time, so tool names, parameters, and default behaviors can drift between versions. When you spot drift (a tool a skill names doesn't exist, a parameter shape doesn't match what ",{"type":35,"tag":50,"props":51,"children":53},"code",{"className":52},[],[54],{"type":41,"value":55},"get_node_types",{"type":41,"value":57}," returns, or behavior differs from what the skill describes), suggest updating the skill and n8n instance to the latest stable.",{"type":35,"tag":59,"props":60,"children":62},"h2",{"id":61},"non-negotiables",[63],{"type":41,"value":64},"Non-negotiables",{"type":35,"tag":44,"props":66,"children":67},{},[68],{"type":41,"value":69},"Three rules with no exceptions. Violating any produces workflows that look right but break in production.",{"type":35,"tag":71,"props":72,"children":73},"ol",{},[74,86,128],{"type":35,"tag":75,"props":76,"children":77},"li",{},[78,84],{"type":35,"tag":79,"props":80,"children":81},"strong",{},[82],{"type":41,"value":83},"Invoke the relevant skill before any n8n action.",{"type":41,"value":85}," Not just MCP tool calls. Before writing SDK code, configuring a node, designing a workflow, wiring a connection, building an agent, or handling errors: invoke the matching skill via the Skill tool. This document is a router. The skill body has the actual rules. The PreToolUse hooks remind you on the highest-impact MCP calls if a plugin is installed. The responsibility is yours on everything else. Err on the side of reading extra documents.",{"type":35,"tag":75,"props":87,"children":88},{},[89,94,96,102,104,110,112,118,120,126],{"type":35,"tag":79,"props":90,"children":91},{},[92],{"type":41,"value":93},"Validate AND verify before publishing.",{"type":41,"value":95}," ",{"type":35,"tag":50,"props":97,"children":99},{"className":98},[],[100],{"type":41,"value":101},"validate_workflow",{"type":41,"value":103}," before ",{"type":35,"tag":50,"props":105,"children":107},{"className":106},[],[108],{"type":41,"value":109},"publish_workflow",{"type":41,"value":111},", and ",{"type":35,"tag":50,"props":113,"children":115},{"className":114},[],[116],{"type":41,"value":117},"get_workflow_details",{"type":41,"value":119}," after every create or update to check the ",{"type":35,"tag":50,"props":121,"children":123},{"className":122},[],[124],{"type":41,"value":125},"connections",{"type":41,"value":127}," object. Validation alone misses many issues documented in the skills that will silently break workflows.",{"type":35,"tag":75,"props":129,"children":130},{},[131,136,138,144],{"type":35,"tag":79,"props":132,"children":133},{},[134],{"type":41,"value":135},"Tokens\u002Fsecrets never go in text fields.",{"type":41,"value":137}," Always use the n8n credential system. If no native node exists, configure HTTP Request with the official credential type. See ",{"type":35,"tag":50,"props":139,"children":141},{"className":140},[],[142],{"type":41,"value":143},"n8n-credentials-and-security-official",{"type":41,"value":145},".",{"type":35,"tag":59,"props":147,"children":149},{"id":148},"lean-on-skills-not-training-data",[150],{"type":41,"value":151},"Lean on skills, not training data",{"type":35,"tag":44,"props":153,"children":154},{},[155],{"type":41,"value":156},"n8n evolves faster than any model's training cutoff. Parameter names drift, new MCP tools land, defaults change, patterns get deprecated. Anything you \"remember\" is likely wrong, often silently.",{"type":35,"tag":44,"props":158,"children":159},{},[160,162,167,169,175,176,182,184,189],{"type":41,"value":161},"Trust the skills + live MCP tools (",{"type":35,"tag":50,"props":163,"children":165},{"className":164},[],[166],{"type":41,"value":55},{"type":41,"value":168},", ",{"type":35,"tag":50,"props":170,"children":172},{"className":171},[],[173],{"type":41,"value":174},"get_sdk_reference",{"type":41,"value":168},{"type":35,"tag":50,"props":177,"children":179},{"className":178},[],[180],{"type":41,"value":181},"get_workflow_best_practices",{"type":41,"value":183},") over recollection. If a skill contradicts what you \"know\", trust the skill. If ",{"type":35,"tag":50,"props":185,"children":187},{"className":186},[],[188],{"type":41,"value":55},{"type":41,"value":190}," contradicts a skill, trust the tool. Without this discipline you will ship workflows that look right and silently fail: parameter names that don't exist, renamed nodes, deprecated patterns.",{"type":35,"tag":44,"props":192,"children":193},{},[194,196,202,203,209,210,216,217,223],{"type":41,"value":195},"Unless a user preference overrides it, err on the side of loading too many skills rather than too few. Even a 3-node webhook flow typically needs ",{"type":35,"tag":50,"props":197,"children":199},{"className":198},[],[200],{"type":41,"value":201},"n8n-node-configuration-official",{"type":41,"value":168},{"type":35,"tag":50,"props":204,"children":206},{"className":205},[],[207],{"type":41,"value":208},"n8n-expressions-official",{"type":41,"value":168},{"type":35,"tag":50,"props":211,"children":213},{"className":212},[],[214],{"type":41,"value":215},"n8n-error-handling-official",{"type":41,"value":111},{"type":35,"tag":50,"props":218,"children":220},{"className":219},[],[221],{"type":41,"value":222},"n8n-workflow-lifecycle-official",{"type":41,"value":224},". Nothing in n8n is too small for skills.",{"type":35,"tag":59,"props":226,"children":228},{"id":227},"strong-defaults-each-skill-owns-its-exceptions",[229],{"type":41,"value":230},"Strong defaults (each skill owns its exceptions)",{"type":35,"tag":232,"props":233,"children":234},"ul",{},[235,252],{"type":35,"tag":75,"props":236,"children":237},{},[238,243,245,251],{"type":35,"tag":79,"props":239,"children":240},{},[241],{"type":41,"value":242},"The Code node is a last resort.",{"type":41,"value":244}," Expression first, then arrow function inside Edit Fields, then Code. Code earns its place for multi-source aggregation, libraries, and stateful work. See ",{"type":35,"tag":50,"props":246,"children":248},{"className":247},[],[249],{"type":41,"value":250},"n8n-code-nodes-official",{"type":41,"value":145},{"type":35,"tag":75,"props":253,"children":254},{},[255,260,262,268,270,276],{"type":35,"tag":79,"props":256,"children":257},{},[258],{"type":41,"value":259},"Anything reusable becomes a stateless sub-workflow.",{"type":41,"value":261}," Search existing ones via ",{"type":35,"tag":50,"props":263,"children":265},{"className":264},[],[266],{"type":41,"value":267},"search_workflows({ tags: ['subworkflow'] })",{"type":41,"value":269}," before building. See ",{"type":35,"tag":50,"props":271,"children":273},{"className":272},[],[274],{"type":41,"value":275},"n8n-subworkflows-official",{"type":41,"value":145},{"type":35,"tag":59,"props":278,"children":280},{"id":279},"red-flags-thoughts-that-mean-stop-and-invoke",[281],{"type":41,"value":282},"Red flags: thoughts that mean STOP and invoke",{"type":35,"tag":44,"props":284,"children":285},{},[286,288,293],{"type":41,"value":287},"These rationalizations cause skills to be skipped. If you catch yourself thinking any of them, invoke the relevant skill via the Skill tool, ",{"type":35,"tag":79,"props":289,"children":290},{},[291],{"type":41,"value":292},"even if you \"already read it\" earlier in the session",{"type":41,"value":145},{"type":35,"tag":295,"props":296,"children":297},"table",{},[298,317],{"type":35,"tag":299,"props":300,"children":301},"thead",{},[302],{"type":35,"tag":303,"props":304,"children":305},"tr",{},[306,312],{"type":35,"tag":307,"props":308,"children":309},"th",{},[310],{"type":41,"value":311},"Thought",{"type":35,"tag":307,"props":313,"children":314},{},[315],{"type":41,"value":316},"Action",{"type":35,"tag":318,"props":319,"children":320},"tbody",{},[321,342,361,380,407,434,453,479,507,534,553,573,592,626,675,694],{"type":35,"tag":303,"props":322,"children":323},{},[324,330],{"type":35,"tag":325,"props":326,"children":327},"td",{},[328],{"type":41,"value":329},"\"This workflow is simple, I'll just build it\"",{"type":35,"tag":325,"props":331,"children":332},{},[333,335,340],{"type":41,"value":334},"Invoke ",{"type":35,"tag":50,"props":336,"children":338},{"className":337},[],[339],{"type":41,"value":222},{"type":41,"value":341},". Most \"simple\" workflows are 10+ nodes by the time they ship.",{"type":35,"tag":303,"props":343,"children":344},{},[345,350],{"type":35,"tag":325,"props":346,"children":347},{},[348],{"type":41,"value":349},"\"I'll add a Set node here to map these fields\"",{"type":35,"tag":325,"props":351,"children":352},{},[353,354,359],{"type":41,"value":334},{"type":35,"tag":50,"props":355,"children":357},{"className":356},[],[358],{"type":41,"value":208},{"type":41,"value":360},". Set nodes feeding only 0 or 1 downstream consumer are the most common antipattern in this entire pack.",{"type":35,"tag":303,"props":362,"children":363},{},[364,369],{"type":35,"tag":325,"props":365,"children":366},{},[367],{"type":41,"value":368},"\"I'll just use a Code node, it's easier\"",{"type":35,"tag":325,"props":370,"children":371},{},[372,373,378],{"type":41,"value":334},{"type":35,"tag":50,"props":374,"children":376},{"className":375},[],[377],{"type":41,"value":250},{"type":41,"value":379},". The bar is high. Most reaches for Code can be expressions or Edit Fields with arrow functions.",{"type":35,"tag":303,"props":381,"children":382},{},[383,388],{"type":35,"tag":325,"props":384,"children":385},{},[386],{"type":41,"value":387},"\"Validation passed, I'm ready to publish\"",{"type":35,"tag":325,"props":389,"children":390},{},[391,392,397,399,405],{"type":41,"value":334},{"type":35,"tag":50,"props":393,"children":395},{"className":394},[],[396],{"type":41,"value":222},{"type":41,"value":398}," and walk ",{"type":35,"tag":50,"props":400,"children":402},{"className":401},[],[403],{"type":41,"value":404},"VALIDATION_CHECKLIST.md",{"type":41,"value":406}," section 2 (the antipattern scan). Validation passing is necessary, not sufficient.",{"type":35,"tag":303,"props":408,"children":409},{},[410,415],{"type":35,"tag":325,"props":411,"children":412},{},[413],{"type":41,"value":414},"\"The agent is wired up, the tool descriptions look fine\"",{"type":35,"tag":325,"props":416,"children":417},{},[418,419,425,426,432],{"type":41,"value":334},{"type":35,"tag":50,"props":420,"children":422},{"className":421},[],[423],{"type":41,"value":424},"n8n-agents-official",{"type":41,"value":95},{"type":35,"tag":50,"props":427,"children":429},{"className":428},[],[430],{"type":41,"value":431},"references\u002FTOOLS.md",{"type":41,"value":433},". Tool names and descriptions ARE part of the prompt, and \"looks fine\" usually means generic.",{"type":35,"tag":303,"props":435,"children":436},{},[437,442],{"type":35,"tag":325,"props":438,"children":439},{},[440],{"type":41,"value":441},"\"I'll set this sub-workflow trigger to passthrough\"",{"type":35,"tag":325,"props":443,"children":444},{},[445,446,451],{"type":41,"value":334},{"type":35,"tag":50,"props":447,"children":449},{"className":448},[],[450],{"type":41,"value":275},{"type":41,"value":452},". Passthrough is only correct for binary-receiving sub-workflows that won't be agent tools, or for sub-workflows that genuinely take no inputs (Define Below requires at least one field).",{"type":35,"tag":303,"props":454,"children":455},{},[456,461],{"type":35,"tag":325,"props":457,"children":458},{},[459],{"type":41,"value":460},"\"I'll use passthrough so binary works, then branch internally on which input shape arrived\"",{"type":35,"tag":325,"props":462,"children":463},{},[464,465,470,471,477],{"type":41,"value":334},{"type":35,"tag":50,"props":466,"children":468},{"className":467},[],[469],{"type":41,"value":275},{"type":41,"value":95},{"type":35,"tag":50,"props":472,"children":474},{"className":473},[],[475],{"type":41,"value":476},"references\u002FSUBWORKFLOW_PATTERNS.md",{"type":41,"value":478}," \"Splitting by input shape\". This is the signal to SPLIT into two outer sub-workflows (one Define Below, one passthrough) sharing a common downstream sub-workflow. Don't fight passthrough vs Define Below in one trigger.",{"type":35,"tag":303,"props":480,"children":481},{},[482,487],{"type":35,"tag":325,"props":483,"children":484},{},[485],{"type":41,"value":486},"\"This section's big, I'll pull it into a sub-workflow\"",{"type":35,"tag":325,"props":488,"children":489},{},[490,492,498,500,505],{"type":41,"value":491},"If it's only to tidy the canvas (not reuse\u002Fisolation\u002Ftesting), a node group is lighter, faster, and simpler: keep it inline and group it via ",{"type":35,"tag":50,"props":493,"children":495},{"className":494},[],[496],{"type":41,"value":497},"setNodeGroups",{"type":41,"value":499},". Extract to a sub-workflow only for reuse, isolation, or an agent tool. See ",{"type":35,"tag":50,"props":501,"children":503},{"className":502},[],[504],{"type":41,"value":222},{"type":41,"value":506}," Readability.",{"type":35,"tag":303,"props":508,"children":509},{},[510,515],{"type":35,"tag":325,"props":511,"children":512},{},[513],{"type":41,"value":514},"\"I should ask the user what their credential is named\"",{"type":35,"tag":325,"props":516,"children":517},{},[518,520,526,528,533],{"type":41,"value":519},"Don't. The string in ",{"type":35,"tag":50,"props":521,"children":523},{"className":522},[],[524],{"type":41,"value":525},"newCredential('Label')",{"type":41,"value":527}," is cosmetic. See ",{"type":35,"tag":50,"props":529,"children":531},{"className":530},[],[532],{"type":41,"value":143},{"type":41,"value":145},{"type":35,"tag":303,"props":535,"children":536},{},[537,542],{"type":35,"tag":325,"props":538,"children":539},{},[540],{"type":41,"value":541},"\"The user mentioned data analysis, I'll write Python\"",{"type":35,"tag":325,"props":543,"children":544},{},[545,546,551],{"type":41,"value":334},{"type":35,"tag":50,"props":547,"children":549},{"className":548},[],[550],{"type":41,"value":250},{"type":41,"value":552},". Default is JavaScript. Python only when explicitly asked.",{"type":35,"tag":303,"props":554,"children":555},{},[556,561],{"type":35,"tag":325,"props":557,"children":558},{},[559],{"type":41,"value":560},"\"I'll add a Loop Over Items here to process each row\"",{"type":35,"tag":325,"props":562,"children":563},{},[564,565,571],{"type":41,"value":334},{"type":35,"tag":50,"props":566,"children":568},{"className":567},[],[569],{"type":41,"value":570},"n8n-loops-official",{"type":41,"value":572},". Default per-item iteration probably handles it without a Loop Over Items node.",{"type":35,"tag":303,"props":574,"children":575},{},[576,581],{"type":35,"tag":325,"props":577,"children":578},{},[579],{"type":41,"value":580},"\"Date math, I'll use a DateTime node\"",{"type":35,"tag":325,"props":582,"children":583},{},[584,585,590],{"type":41,"value":334},{"type":35,"tag":50,"props":586,"children":588},{"className":587},[],[589],{"type":41,"value":208},{"type":41,"value":591},". DateTime nodes are almost always wrong.",{"type":35,"tag":303,"props":593,"children":594},{},[595,600],{"type":35,"tag":325,"props":596,"children":597},{},[598],{"type":41,"value":599},"\"I'll wrap this in a Merge with 3 sources\"",{"type":35,"tag":325,"props":601,"children":602},{},[603,604,609,610,616,618,624],{"type":41,"value":334},{"type":35,"tag":50,"props":605,"children":607},{"className":606},[],[608],{"type":41,"value":201},{"type":41,"value":95},{"type":35,"tag":50,"props":611,"children":613},{"className":612},[],[614],{"type":41,"value":615},"references\u002FMERGE_NODE.md",{"type":41,"value":617},". Merge defaults to 2 inputs, and 3+ sources need ",{"type":35,"tag":50,"props":619,"children":621},{"className":620},[],[622],{"type":41,"value":623},"numberOfInputs",{"type":41,"value":625}," set explicitly.",{"type":35,"tag":303,"props":627,"children":628},{},[629,634],{"type":35,"tag":325,"props":630,"children":631},{},[632],{"type":41,"value":633},"\"I'll fan out these three slow steps to run in parallel\"",{"type":35,"tag":325,"props":635,"children":636},{},[637,638,643,645,650,652,657,659,665,667,673],{"type":41,"value":334},{"type":35,"tag":50,"props":639,"children":641},{"className":640},[],[642],{"type":41,"value":222},{"type":41,"value":644}," and read the Execution model section. n8n executes fan-out branches sequentially (top-to-bottom by Y-position), not concurrently. For real concurrency, see ",{"type":35,"tag":50,"props":646,"children":648},{"className":647},[],[649],{"type":41,"value":570},{"type":41,"value":651}," and ",{"type":35,"tag":50,"props":653,"children":655},{"className":654},[],[656],{"type":41,"value":275},{"type":41,"value":658}," (",{"type":35,"tag":50,"props":660,"children":662},{"className":661},[],[663],{"type":41,"value":664},"mode: 'each'",{"type":41,"value":666}," + ",{"type":35,"tag":50,"props":668,"children":670},{"className":669},[],[671],{"type":41,"value":672},"waitForSubWorkflow: false",{"type":41,"value":674},").",{"type":35,"tag":303,"props":676,"children":677},{},[678,683],{"type":35,"tag":325,"props":679,"children":680},{},[681],{"type":41,"value":682},"\"User said which project, I'll just build it\"",{"type":35,"tag":325,"props":684,"children":685},{},[686,687,692],{"type":41,"value":334},{"type":35,"tag":50,"props":688,"children":690},{"className":689},[],[691],{"type":41,"value":222},{"type":41,"value":693},". Project is not folder. Ask about folder placement BEFORE building. The MCP can't create folders, so if the requested folder doesn't exist, the user must create it in the UI first.",{"type":35,"tag":303,"props":695,"children":696},{},[697,710],{"type":35,"tag":325,"props":698,"children":699},{},[700,702,708],{"type":41,"value":701},"\"I'll just run ",{"type":35,"tag":50,"props":703,"children":705},{"className":704},[],[706],{"type":41,"value":707},"test_workflow",{"type":41,"value":709}," to see what happens\"",{"type":35,"tag":325,"props":711,"children":712},{},[713,714,719,720,726,728,733],{"type":41,"value":334},{"type":35,"tag":50,"props":715,"children":717},{"className":716},[],[718],{"type":41,"value":222},{"type":41,"value":95},{"type":35,"tag":50,"props":721,"children":723},{"className":722},[],[724],{"type":41,"value":725},"references\u002FTESTING.md",{"type":41,"value":727},". ",{"type":35,"tag":50,"props":729,"children":731},{"className":730},[],[732],{"type":41,"value":707},{"type":41,"value":734}," mocks the trigger only. Slack sends, DB writes, payments all fire for real. Ask the user first when downstreams have side effects.",{"type":35,"tag":44,"props":736,"children":737},{},[738,743],{"type":35,"tag":79,"props":739,"children":740},{},[741],{"type":41,"value":742},"The meta-skill (this document) tells you WHICH skill applies. The Skill tool loads the actual rules.",{"type":41,"value":744}," Reading the meta-skill once at session start is not a substitute for invoking the skill at the moment of decision.",{"type":35,"tag":59,"props":746,"children":748},{"id":747},"skill-index",[749],{"type":41,"value":750},"Skill index",{"type":35,"tag":44,"props":752,"children":753},{},[754],{"type":41,"value":755},"Invoke via the Skill tool. Trigger column = when to invoke.",{"type":35,"tag":295,"props":757,"children":758},{},[759,775],{"type":35,"tag":299,"props":760,"children":761},{},[762],{"type":35,"tag":303,"props":763,"children":764},{},[765,770],{"type":35,"tag":307,"props":766,"children":767},{},[768],{"type":41,"value":769},"Skill",{"type":35,"tag":307,"props":771,"children":772},{},[773],{"type":41,"value":774},"Trigger",{"type":35,"tag":318,"props":776,"children":777},{},[778,802,818,835,873,889,905,929,945,961,977,994,1011],{"type":35,"tag":303,"props":779,"children":780},{},[781,789],{"type":35,"tag":325,"props":782,"children":783},{},[784],{"type":35,"tag":50,"props":785,"children":787},{"className":786},[],[788],{"type":41,"value":222},{"type":35,"tag":325,"props":790,"children":791},{},[792,794,800],{"type":41,"value":793},"Starting, designing, organizing, or finishing a workflow. Covers sticky-note conventions, descriptions that capture the ",{"type":35,"tag":795,"props":796,"children":797},"em",{},[798],{"type":41,"value":799},"why",{"type":41,"value":801},", naming, validation checklist, folder limitations, MCP-access-per-workflow gotcha",{"type":35,"tag":303,"props":803,"children":804},{},[805,813],{"type":35,"tag":325,"props":806,"children":807},{},[808],{"type":35,"tag":50,"props":809,"children":811},{"className":810},[],[812],{"type":41,"value":275},{"type":35,"tag":325,"props":814,"children":815},{},[816],{"type":41,"value":817},"Anything reusable, multi-step builds, or the user mentions reuse. Search before building, stateless patterns, tag-based discovery convention",{"type":35,"tag":303,"props":819,"children":820},{},[821,830],{"type":35,"tag":325,"props":822,"children":823},{},[824],{"type":35,"tag":50,"props":825,"children":827},{"className":826},[],[828],{"type":41,"value":829},"n8n-extending-mcp-official",{"type":35,"tag":325,"props":831,"children":832},{},[833],{"type":41,"value":834},"You need capabilities the MCP doesn't natively provide. Wrap n8n APIs as workflow tools, with user permission",{"type":35,"tag":303,"props":836,"children":837},{},[838,846],{"type":35,"tag":325,"props":839,"children":840},{},[841],{"type":35,"tag":50,"props":842,"children":844},{"className":843},[],[845],{"type":41,"value":208},{"type":35,"tag":325,"props":847,"children":848},{},[849,851,857,858,864,865,871],{"type":41,"value":850},"Writing ",{"type":35,"tag":50,"props":852,"children":854},{"className":853},[],[855],{"type":41,"value":856},"{{}}",{"type":41,"value":168},{"type":35,"tag":50,"props":859,"children":861},{"className":860},[],[862],{"type":41,"value":863},"$json",{"type":41,"value":168},{"type":35,"tag":50,"props":866,"children":868},{"className":867},[],[869],{"type":41,"value":870},"$node",{"type":41,"value":872},", expression errors. Luxon for dates, indented multi-line, prefer expressions over extra nodes",{"type":35,"tag":303,"props":874,"children":875},{},[876,884],{"type":35,"tag":325,"props":877,"children":878},{},[879],{"type":35,"tag":50,"props":880,"children":882},{"className":881},[],[883],{"type":41,"value":201},{"type":35,"tag":325,"props":885,"children":886},{},[887],{"type":41,"value":888},"Configuring any node. Operation-aware, property dependencies, never assume parameters",{"type":35,"tag":303,"props":890,"children":891},{},[892,900],{"type":35,"tag":325,"props":893,"children":894},{},[895],{"type":35,"tag":50,"props":896,"children":898},{"className":897},[],[899],{"type":41,"value":250},{"type":35,"tag":325,"props":901,"children":902},{},[903],{"type":41,"value":904},"User reaches for a Code node, or custom logic is needed. Decision tree, JavaScript patterns when truly required",{"type":35,"tag":303,"props":906,"children":907},{},[908,916],{"type":35,"tag":325,"props":909,"children":910},{},[911],{"type":35,"tag":50,"props":912,"children":914},{"className":913},[],[915],{"type":41,"value":570},{"type":35,"tag":325,"props":917,"children":918},{},[919,921,927],{"type":41,"value":920},"Multi-item data, batching, paginated APIs, \"for each\" or \"loop over\" mentions. Default per-item iteration, ",{"type":35,"tag":50,"props":922,"children":924},{"className":923},[],[925],{"type":41,"value":926},"executeOnce",{"type":41,"value":928},", Loop Over Items, HTTP pagination",{"type":35,"tag":303,"props":930,"children":931},{},[932,940],{"type":35,"tag":325,"props":933,"children":934},{},[935],{"type":35,"tag":50,"props":936,"children":938},{"className":937},[],[939],{"type":41,"value":424},{"type":35,"tag":325,"props":941,"children":942},{},[943],{"type":41,"value":944},"LangChain Agent node, tool calling, system prompts, structured output, memory, RAG. Tool names\u002Fdescriptions as part of the prompt, sub-workflow as tool, modular prompt design",{"type":35,"tag":303,"props":946,"children":947},{},[948,956],{"type":35,"tag":325,"props":949,"children":950},{},[951],{"type":35,"tag":50,"props":952,"children":954},{"className":953},[],[955],{"type":41,"value":215},{"type":35,"tag":325,"props":957,"children":958},{},[959],{"type":41,"value":960},"Webhook-triggered or production-bound workflows. Error branch on every fallible node, 4xx for caller errors and 5xx for execution errors",{"type":35,"tag":303,"props":962,"children":963},{},[964,972],{"type":35,"tag":325,"props":965,"children":966},{},[967],{"type":35,"tag":50,"props":968,"children":970},{"className":969},[],[971],{"type":41,"value":143},{"type":35,"tag":325,"props":973,"children":974},{},[975],{"type":41,"value":976},"Any auth, API key, or token mention. Credential system, custom credentials, HTTP Request with official creds",{"type":35,"tag":303,"props":978,"children":979},{},[980,989],{"type":35,"tag":325,"props":981,"children":982},{},[983],{"type":35,"tag":50,"props":984,"children":986},{"className":985},[],[987],{"type":41,"value":988},"n8n-binary-and-data-official",{"type":35,"tag":325,"props":990,"children":991},{},[992],{"type":41,"value":993},"Files, images, attachments. Binary handling patterns, agent-tool boundary, CDN requirement for chat surfaces",{"type":35,"tag":303,"props":995,"children":996},{},[997,1006],{"type":35,"tag":325,"props":998,"children":999},{},[1000],{"type":35,"tag":50,"props":1001,"children":1003},{"className":1002},[],[1004],{"type":41,"value":1005},"n8n-data-tables-official",{"type":35,"tag":325,"props":1007,"children":1008},{},[1009],{"type":41,"value":1010},"Data Tables: schemas, default columns (id\u002FcreatedAt\u002FupdatedAt), no-FK relational design, dedup, the no-JSON-only-primitives rule, the SDK-vs-UI manual-mapping quirk",{"type":35,"tag":303,"props":1012,"children":1013},{},[1014,1023],{"type":35,"tag":325,"props":1015,"children":1016},{},[1017],{"type":35,"tag":50,"props":1018,"children":1020},{"className":1019},[],[1021],{"type":41,"value":1022},"n8n-debugging-official",{"type":35,"tag":325,"props":1024,"children":1025},{},[1026],{"type":41,"value":1027},"Errors, unexpected behavior, \"this isn't working\". Believe the user, check parameters, fetch n8n source from GitHub",{"type":35,"tag":59,"props":1029,"children":1031},{"id":1030},"n8n-mcp-tools-compact-reference",[1032],{"type":41,"value":1033},"n8n MCP tools (compact reference)",{"type":35,"tag":44,"props":1035,"children":1036},{},[1037],{"type":41,"value":1038},"The MCP defers tool descriptions to save tokens. Below is the short-form list so you have working knowledge of every tool from turn one.",{"type":35,"tag":44,"props":1040,"children":1041},{},[1042,1044,1050,1052,1058],{"type":41,"value":1043},"Tool names are shown without the MCP prefix. The qualified name is ",{"type":35,"tag":50,"props":1045,"children":1047},{"className":1046},[],[1048],{"type":41,"value":1049},"mcp__\u003Cserver>__\u003Ctool>",{"type":41,"value":1051}," where ",{"type":35,"tag":50,"props":1053,"children":1055},{"className":1054},[],[1056],{"type":41,"value":1057},"\u003Cserver>",{"type":41,"value":1059}," depends on the user's MCP config.",{"type":35,"tag":1061,"props":1062,"children":1064},"h3",{"id":1063},"workflow-management",[1065],{"type":41,"value":1066},"Workflow management",{"type":35,"tag":295,"props":1068,"children":1069},{},[1070,1086],{"type":35,"tag":299,"props":1071,"children":1072},{},[1073],{"type":35,"tag":303,"props":1074,"children":1075},{},[1076,1081],{"type":35,"tag":307,"props":1077,"children":1078},{},[1079],{"type":41,"value":1080},"Tool",{"type":35,"tag":307,"props":1082,"children":1083},{},[1084],{"type":41,"value":1085},"What it does",{"type":35,"tag":318,"props":1087,"children":1088},{},[1089,1129,1145,1169,1186,1234,1280],{"type":35,"tag":303,"props":1090,"children":1091},{},[1092,1101],{"type":35,"tag":325,"props":1093,"children":1094},{},[1095],{"type":35,"tag":50,"props":1096,"children":1098},{"className":1097},[],[1099],{"type":41,"value":1100},"search_workflows",{"type":35,"tag":325,"props":1102,"children":1103},{},[1104,1106,1112,1114,1120,1122,1127],{"type":41,"value":1105},"Search workflows across the instance by ",{"type":35,"tag":50,"props":1107,"children":1109},{"className":1108},[],[1110],{"type":41,"value":1111},"query",{"type":41,"value":1113}," (substring on name\u002Fdescription) and\u002For ",{"type":35,"tag":50,"props":1115,"children":1117},{"className":1116},[],[1118],{"type":41,"value":1119},"tags",{"type":41,"value":1121}," (exact tag names, AND semantics: must have all). The primary cross-workflow ",{"type":35,"tag":79,"props":1123,"children":1124},{},[1125],{"type":41,"value":1126},"discovery",{"type":41,"value":1128}," tool. Use it to discover what already exists.",{"type":35,"tag":303,"props":1130,"children":1131},{},[1132,1140],{"type":35,"tag":325,"props":1133,"children":1134},{},[1135],{"type":35,"tag":50,"props":1136,"children":1138},{"className":1137},[],[1139],{"type":41,"value":117},{"type":35,"tag":325,"props":1141,"children":1142},{},[1143],{"type":41,"value":1144},"Fetch a workflow's full JSON by ID. Use after every create\u002Fupdate to verify connections.",{"type":35,"tag":303,"props":1146,"children":1147},{},[1148,1157],{"type":35,"tag":325,"props":1149,"children":1150},{},[1151],{"type":35,"tag":50,"props":1152,"children":1154},{"className":1153},[],[1155],{"type":41,"value":1156},"search_folders",{"type":35,"tag":325,"props":1158,"children":1159},{},[1160,1162,1167],{"type":41,"value":1161},"List folders. ",{"type":35,"tag":79,"props":1163,"children":1164},{},[1165],{"type":41,"value":1166},"You cannot create or move folders.",{"type":41,"value":1168}," You can only place workflows into folders that already exist.",{"type":35,"tag":303,"props":1170,"children":1171},{},[1172,1181],{"type":35,"tag":325,"props":1173,"children":1174},{},[1175],{"type":35,"tag":50,"props":1176,"children":1178},{"className":1177},[],[1179],{"type":41,"value":1180},"search_projects",{"type":35,"tag":325,"props":1182,"children":1183},{},[1184],{"type":41,"value":1185},"List projects.",{"type":35,"tag":303,"props":1187,"children":1188},{},[1189,1198],{"type":35,"tag":325,"props":1190,"children":1191},{},[1192],{"type":35,"tag":50,"props":1193,"children":1195},{"className":1194},[],[1196],{"type":41,"value":1197},"list_tags",{"type":35,"tag":325,"props":1199,"children":1200},{},[1201,1203,1209,1211,1217,1218,1224,1226,1232],{"type":41,"value":1202},"List all workflow tags (with ",{"type":35,"tag":50,"props":1204,"children":1206},{"className":1205},[],[1207],{"type":41,"value":1208},"usageCount",{"type":41,"value":1210}," per tag). Check the instance's tag vocabulary before tagging or filtering, so you reuse exact names. Tags are attached\u002Fdetached via ",{"type":35,"tag":50,"props":1212,"children":1214},{"className":1213},[],[1215],{"type":41,"value":1216},"update_workflow",{"type":41,"value":95},{"type":35,"tag":50,"props":1219,"children":1221},{"className":1220},[],[1222],{"type":41,"value":1223},"addTags",{"type":41,"value":1225},"\u002F",{"type":35,"tag":50,"props":1227,"children":1229},{"className":1228},[],[1230],{"type":41,"value":1231},"removeTags",{"type":41,"value":1233},"; there's no tag rename\u002Fdelete tool.",{"type":35,"tag":303,"props":1235,"children":1236},{},[1237,1260],{"type":35,"tag":325,"props":1238,"children":1239},{},[1240,1246,1248,1253,1254],{"type":35,"tag":50,"props":1241,"children":1243},{"className":1242},[],[1244],{"type":41,"value":1245},"archive_workflow",{"type":41,"value":1247}," \u002F ",{"type":35,"tag":50,"props":1249,"children":1251},{"className":1250},[],[1252],{"type":41,"value":109},{"type":41,"value":1247},{"type":35,"tag":50,"props":1255,"children":1257},{"className":1256},[],[1258],{"type":41,"value":1259},"unpublish_workflow",{"type":35,"tag":325,"props":1261,"children":1262},{},[1263,1265,1270,1272,1278],{"type":41,"value":1264},"Soft-delete \u002F activate \u002F deactivate. Validate before publish. ",{"type":35,"tag":50,"props":1266,"children":1268},{"className":1267},[],[1269],{"type":41,"value":109},{"type":41,"value":1271}," takes an optional ",{"type":35,"tag":50,"props":1273,"children":1275},{"className":1274},[],[1276],{"type":41,"value":1277},"versionId",{"type":41,"value":1279}," to re-publish a specific version.",{"type":35,"tag":303,"props":1281,"children":1282},{},[1283,1292],{"type":35,"tag":325,"props":1284,"children":1285},{},[1286],{"type":35,"tag":50,"props":1287,"children":1289},{"className":1288},[],[1290],{"type":41,"value":1291},"search_executions",{"type":35,"tag":325,"props":1293,"children":1294},{},[1295,1297,1303],{"type":41,"value":1296},"Search executions across the instance (filter by status, workflow, time range). Use for \"list recent runs\" \u002F \"failures in the last hour\". Single executions: ",{"type":35,"tag":50,"props":1298,"children":1300},{"className":1299},[],[1301],{"type":41,"value":1302},"get_execution",{"type":41,"value":145},{"type":35,"tag":1061,"props":1305,"children":1307},{"id":1306},"workflow-building",[1308],{"type":41,"value":1309},"Workflow building",{"type":35,"tag":295,"props":1311,"children":1312},{},[1313,1327],{"type":35,"tag":299,"props":1314,"children":1315},{},[1316],{"type":35,"tag":303,"props":1317,"children":1318},{},[1319,1323],{"type":35,"tag":307,"props":1320,"children":1321},{},[1322],{"type":41,"value":1080},{"type":35,"tag":307,"props":1324,"children":1325},{},[1326],{"type":41,"value":1085},{"type":35,"tag":318,"props":1328,"children":1329},{},[1330,1416,1440,1457,1480,1544,1577,1656,1687,1718],{"type":35,"tag":303,"props":1331,"children":1332},{},[1333,1341],{"type":35,"tag":325,"props":1334,"children":1335},{},[1336],{"type":35,"tag":50,"props":1337,"children":1339},{"className":1338},[],[1340],{"type":41,"value":174},{"type":35,"tag":325,"props":1342,"children":1343},{},[1344,1346,1351,1353,1359,1360,1366,1367,1373,1374,1380,1381,1387,1388,1394,1395,1401,1402,1408,1409,1415],{"type":41,"value":1345},"Fetch the n8n Workflow SDK reference. ",{"type":35,"tag":79,"props":1347,"children":1348},{},[1349],{"type":41,"value":1350},"Read this before writing workflow code.",{"type":41,"value":1352}," Sections: ",{"type":35,"tag":50,"props":1354,"children":1356},{"className":1355},[],[1357],{"type":41,"value":1358},"patterns",{"type":41,"value":168},{"type":35,"tag":50,"props":1361,"children":1363},{"className":1362},[],[1364],{"type":41,"value":1365},"patterns_detailed",{"type":41,"value":168},{"type":35,"tag":50,"props":1368,"children":1370},{"className":1369},[],[1371],{"type":41,"value":1372},"expressions",{"type":41,"value":168},{"type":35,"tag":50,"props":1375,"children":1377},{"className":1376},[],[1378],{"type":41,"value":1379},"functions",{"type":41,"value":168},{"type":35,"tag":50,"props":1382,"children":1384},{"className":1383},[],[1385],{"type":41,"value":1386},"rules",{"type":41,"value":168},{"type":35,"tag":50,"props":1389,"children":1391},{"className":1390},[],[1392],{"type":41,"value":1393},"import",{"type":41,"value":168},{"type":35,"tag":50,"props":1396,"children":1398},{"className":1397},[],[1399],{"type":41,"value":1400},"guidelines",{"type":41,"value":168},{"type":35,"tag":50,"props":1403,"children":1405},{"className":1404},[],[1406],{"type":41,"value":1407},"design",{"type":41,"value":168},{"type":35,"tag":50,"props":1410,"children":1412},{"className":1411},[],[1413],{"type":41,"value":1414},"all",{"type":41,"value":145},{"type":35,"tag":303,"props":1417,"children":1418},{},[1419,1427],{"type":35,"tag":325,"props":1420,"children":1421},{},[1422],{"type":35,"tag":50,"props":1423,"children":1425},{"className":1424},[],[1426],{"type":41,"value":181},{"type":35,"tag":325,"props":1428,"children":1429},{},[1430,1432,1438],{"type":41,"value":1431},"Fetch best-practices for a workflow technique. Call once per technique before searching nodes. ",{"type":35,"tag":50,"props":1433,"children":1435},{"className":1434},[],[1436],{"type":41,"value":1437},"technique: \"list\"",{"type":41,"value":1439}," discovers what's available.",{"type":35,"tag":303,"props":1441,"children":1442},{},[1443,1452],{"type":35,"tag":325,"props":1444,"children":1445},{},[1446],{"type":35,"tag":50,"props":1447,"children":1449},{"className":1448},[],[1450],{"type":41,"value":1451},"search_nodes",{"type":35,"tag":325,"props":1453,"children":1454},{},[1455],{"type":41,"value":1456},"Discover nodes by capability (e.g. \"gmail\", \"slack\", \"schedule trigger\"). Returns IDs plus discriminators (resource\u002Foperation\u002Fmode).",{"type":35,"tag":303,"props":1458,"children":1459},{},[1460,1468],{"type":35,"tag":325,"props":1461,"children":1462},{},[1463],{"type":35,"tag":50,"props":1464,"children":1466},{"className":1465},[],[1467],{"type":41,"value":55},{"type":35,"tag":325,"props":1469,"children":1470},{},[1471,1473,1478],{"type":41,"value":1472},"Fetch exact TypeScript parameter definitions for node IDs. ",{"type":35,"tag":79,"props":1474,"children":1475},{},[1476],{"type":41,"value":1477},"Required before configuring any node.",{"type":41,"value":1479}," Don't guess parameter names.",{"type":35,"tag":303,"props":1481,"children":1482},{},[1483,1492],{"type":35,"tag":325,"props":1484,"children":1485},{},[1486],{"type":35,"tag":50,"props":1487,"children":1489},{"className":1488},[],[1490],{"type":41,"value":1491},"explore_node_resources",{"type":35,"tag":325,"props":1493,"children":1494},{},[1495,1497,1503,1505,1511,1513,1519,1521,1527,1529,1535,1537,1542],{"type":41,"value":1496},"Resolve the real values behind resource-locator (",{"type":35,"tag":50,"props":1498,"children":1500},{"className":1499},[],[1501],{"type":41,"value":1502},"@searchListMethod",{"type":41,"value":1504},") and load-options (",{"type":35,"tag":50,"props":1506,"children":1508},{"className":1507},[],[1509],{"type":41,"value":1510},"@loadOptionsMethod",{"type":41,"value":1512},") params: Slack channels, Sheets tabs\u002Fdocs, DB tables\u002Fcolumns, model lists, labels. Needs a ",{"type":35,"tag":50,"props":1514,"children":1516},{"className":1515},[],[1517],{"type":41,"value":1518},"credentialId",{"type":41,"value":1520}," from ",{"type":35,"tag":50,"props":1522,"children":1524},{"className":1523},[],[1525],{"type":41,"value":1526},"list_credentials",{"type":41,"value":1528}," (pass ",{"type":35,"tag":50,"props":1530,"children":1532},{"className":1531},[],[1533],{"type":41,"value":1534},"currentNodeParameters",{"type":41,"value":1536}," for dependent lookups). Call after ",{"type":35,"tag":50,"props":1538,"children":1540},{"className":1539},[],[1541],{"type":41,"value":55},{"type":41,"value":1543}," to ground dropdown values instead of inventing IDs.",{"type":35,"tag":303,"props":1545,"children":1546},{},[1547,1556],{"type":35,"tag":325,"props":1548,"children":1549},{},[1550],{"type":35,"tag":50,"props":1551,"children":1553},{"className":1552},[],[1554],{"type":41,"value":1555},"create_workflow_from_code",{"type":35,"tag":325,"props":1557,"children":1558},{},[1559,1561,1567,1569,1575],{"type":41,"value":1560},"Save a workflow from SDK code. Always include a 1-2 sentence ",{"type":35,"tag":50,"props":1562,"children":1564},{"className":1563},[],[1565],{"type":41,"value":1566},"description",{"type":41,"value":1568},". Pass ",{"type":35,"tag":50,"props":1570,"children":1572},{"className":1571},[],[1573],{"type":41,"value":1574},"skillsUsed",{"type":41,"value":1576}," (below).",{"type":35,"tag":303,"props":1578,"children":1579},{},[1580,1588],{"type":35,"tag":325,"props":1581,"children":1582},{},[1583],{"type":35,"tag":50,"props":1584,"children":1586},{"className":1585},[],[1587],{"type":41,"value":1216},{"type":35,"tag":325,"props":1589,"children":1590},{},[1591,1593,1599,1600,1606,1608,1614,1616,1621,1623,1629,1630,1635,1636,1641,1643,1648,1650,1655],{"type":41,"value":1592},"Apply atomic ops (max 100, all-or-nothing): node\u002Fconnection CRUD, ",{"type":35,"tag":50,"props":1594,"children":1596},{"className":1595},[],[1597],{"type":41,"value":1598},"setNodeCredential",{"type":41,"value":168},{"type":35,"tag":50,"props":1601,"children":1603},{"className":1602},[],[1604],{"type":41,"value":1605},"setNodeSettings",{"type":41,"value":1607}," (per-node onError\u002Fretry\u002FexecuteOnce), ",{"type":35,"tag":50,"props":1609,"children":1611},{"className":1610},[],[1612],{"type":41,"value":1613},"setWorkflowSettings",{"type":41,"value":1615}," (errorWorkflow, timezone, callerPolicy, timeouts, save-data policies; n8n 2.29.0+), ",{"type":35,"tag":50,"props":1617,"children":1619},{"className":1618},[],[1620],{"type":41,"value":497},{"type":41,"value":1622}," (canvas grouping), ",{"type":35,"tag":50,"props":1624,"children":1626},{"className":1625},[],[1627],{"type":41,"value":1628},"setWorkflowMetadata",{"type":41,"value":168},{"type":35,"tag":50,"props":1631,"children":1633},{"className":1632},[],[1634],{"type":41,"value":1223},{"type":41,"value":1225},{"type":35,"tag":50,"props":1637,"children":1639},{"className":1638},[],[1640],{"type":41,"value":1231},{"type":41,"value":1642}," (auto-create unknown names). Saves a draft; needs ",{"type":35,"tag":50,"props":1644,"children":1646},{"className":1645},[],[1647],{"type":41,"value":109},{"type":41,"value":1649}," to go live. Pass ",{"type":35,"tag":50,"props":1651,"children":1653},{"className":1652},[],[1654],{"type":41,"value":1574},{"type":41,"value":1576},{"type":35,"tag":303,"props":1657,"children":1658},{},[1659,1668],{"type":35,"tag":325,"props":1660,"children":1661},{},[1662],{"type":35,"tag":50,"props":1663,"children":1665},{"className":1664},[],[1666],{"type":41,"value":1667},"validate_node_config",{"type":35,"tag":325,"props":1669,"children":1670},{},[1671,1673,1678,1680,1686],{"type":41,"value":1672},"Schema-only validation of node configs (1-50 per call). Per-parameter errors, no graph noise. Side-channel for iteration\u002Fdebug; ",{"type":35,"tag":50,"props":1674,"children":1676},{"className":1675},[],[1677],{"type":41,"value":101},{"type":41,"value":1679}," still gates publish. For ai_tool subnodes set ",{"type":35,"tag":50,"props":1681,"children":1683},{"className":1682},[],[1684],{"type":41,"value":1685},"isToolNode: true",{"type":41,"value":145},{"type":35,"tag":303,"props":1688,"children":1689},{},[1690,1698],{"type":35,"tag":325,"props":1691,"children":1692},{},[1693],{"type":35,"tag":50,"props":1694,"children":1696},{"className":1695},[],[1697],{"type":41,"value":101},{"type":35,"tag":325,"props":1699,"children":1700},{},[1701,1703,1708,1710,1716],{"type":41,"value":1702},"Validate full SDK code before create\u002Fupdate. Necessary but ",{"type":35,"tag":79,"props":1704,"children":1705},{},[1706],{"type":41,"value":1707},"not sufficient",{"type":41,"value":1709},": doesn't catch all wiring traps (",{"type":35,"tag":50,"props":1711,"children":1713},{"className":1712},[],[1714],{"type":41,"value":1715},".to()",{"type":41,"value":1717},", merge index).",{"type":35,"tag":303,"props":1719,"children":1720},{},[1721,1729],{"type":35,"tag":325,"props":1722,"children":1723},{},[1724],{"type":35,"tag":50,"props":1725,"children":1727},{"className":1726},[],[1728],{"type":41,"value":1526},{"type":35,"tag":325,"props":1730,"children":1731},{},[1732,1734,1739,1741,1746],{"type":41,"value":1733},"List accessible credentials (filter by type\u002Fproject\u002Fetc). Returns metadata only, ",{"type":35,"tag":79,"props":1735,"children":1736},{},[1737],{"type":41,"value":1738},"never secret values",{"type":41,"value":1740},". Discover IDs before binding via ",{"type":35,"tag":50,"props":1742,"children":1744},{"className":1743},[],[1745],{"type":41,"value":1598},{"type":41,"value":145},{"type":35,"tag":1061,"props":1748,"children":1750},{"id":1749},"workflow-testing-execution",[1751],{"type":41,"value":1752},"Workflow testing & execution",{"type":35,"tag":295,"props":1754,"children":1755},{},[1756,1770],{"type":35,"tag":299,"props":1757,"children":1758},{},[1759],{"type":35,"tag":303,"props":1760,"children":1761},{},[1762,1766],{"type":35,"tag":307,"props":1763,"children":1764},{},[1765],{"type":41,"value":1080},{"type":35,"tag":307,"props":1767,"children":1768},{},[1769],{"type":41,"value":1085},{"type":35,"tag":318,"props":1771,"children":1772},{},[1773,1790,1825,1892],{"type":35,"tag":303,"props":1774,"children":1775},{},[1776,1785],{"type":35,"tag":325,"props":1777,"children":1778},{},[1779],{"type":35,"tag":50,"props":1780,"children":1782},{"className":1781},[],[1783],{"type":41,"value":1784},"prepare_test_pin_data",{"type":35,"tag":325,"props":1786,"children":1787},{},[1788],{"type":41,"value":1789},"Returns JSON Schemas (not data) for nodes that need pinning: triggers, credentialed nodes, and HTTP Request. You generate sample values.",{"type":35,"tag":303,"props":1791,"children":1792},{},[1793,1801],{"type":35,"tag":325,"props":1794,"children":1795},{},[1796],{"type":35,"tag":50,"props":1797,"children":1799},{"className":1798},[],[1800],{"type":41,"value":707},{"type":35,"tag":325,"props":1802,"children":1803},{},[1804,1806,1811,1813,1818,1819,1824],{"type":41,"value":1805},"Run with the pin data you supply. ",{"type":35,"tag":79,"props":1807,"children":1808},{},[1809],{"type":41,"value":1810},"Auto-pins triggers, credentialed nodes, and HTTP Request.",{"type":41,"value":1812}," Code, Edit Fields, If, Data Tables, Execute Command, file ops, and sub-workflow calls run for real. Ask before running if any not-auto-pinned node has side effects. Pin data is per-execution only with no visual indicator in the execution viewer, so tell the user which nodes were pinned after the call. See ",{"type":35,"tag":50,"props":1814,"children":1816},{"className":1815},[],[1817],{"type":41,"value":222},{"type":41,"value":95},{"type":35,"tag":50,"props":1820,"children":1822},{"className":1821},[],[1823],{"type":41,"value":725},{"type":41,"value":145},{"type":35,"tag":303,"props":1826,"children":1827},{},[1828,1837],{"type":35,"tag":325,"props":1829,"children":1830},{},[1831],{"type":35,"tag":50,"props":1832,"children":1834},{"className":1833},[],[1835],{"type":41,"value":1836},"execute_workflow",{"type":35,"tag":325,"props":1838,"children":1839},{},[1840,1842,1847,1848,1859,1861,1867,1869,1875,1877,1883,1885,1890],{"type":41,"value":1841},"Production execution with the real trigger. Wire error handling first. Same side-effect rules as ",{"type":35,"tag":50,"props":1843,"children":1845},{"className":1844},[],[1846],{"type":41,"value":707},{"type":41,"value":727},{"type":35,"tag":79,"props":1849,"children":1850},{},[1851,1857],{"type":35,"tag":50,"props":1852,"children":1854},{"className":1853},[],[1855],{"type":41,"value":1856},"executionMode",{"type":41,"value":1858}," is required",{"type":41,"value":1860}," — use ",{"type":35,"tag":50,"props":1862,"children":1864},{"className":1863},[],[1865],{"type":41,"value":1866},"\"manual\"",{"type":41,"value":1868}," for testing or validating the current workflow (including tests against live external services), and ",{"type":35,"tag":50,"props":1870,"children":1872},{"className":1871},[],[1873],{"type":41,"value":1874},"\"production\"",{"type":41,"value":1876}," only when intentionally running the published workflow as a live execution. Structured ",{"type":35,"tag":50,"props":1878,"children":1880},{"className":1879},[],[1881],{"type":41,"value":1882},"inputs",{"type":41,"value":1884}," for chat\u002Fform\u002Fwebhook triggers. Returns an execution ID immediately without waiting; poll ",{"type":35,"tag":50,"props":1886,"children":1888},{"className":1887},[],[1889],{"type":41,"value":1302},{"type":41,"value":1891}," for results.",{"type":35,"tag":303,"props":1893,"children":1894},{},[1895,1903],{"type":35,"tag":325,"props":1896,"children":1897},{},[1898],{"type":35,"tag":50,"props":1899,"children":1901},{"className":1900},[],[1902],{"type":41,"value":1302},{"type":35,"tag":325,"props":1904,"children":1905},{},[1906,1908,1914,1915,1921,1923,1929,1931,1937,1938,1944],{"type":41,"value":1907},"Fetch an execution by ",{"type":35,"tag":50,"props":1909,"children":1911},{"className":1910},[],[1912],{"type":41,"value":1913},"executionId",{"type":41,"value":666},{"type":35,"tag":50,"props":1916,"children":1918},{"className":1917},[],[1919],{"type":41,"value":1920},"workflowId",{"type":41,"value":1922}," (both required). Metadata only by default; set ",{"type":35,"tag":50,"props":1924,"children":1926},{"className":1925},[],[1927],{"type":41,"value":1928},"includeData: true",{"type":41,"value":1930}," (optionally ",{"type":35,"tag":50,"props":1932,"children":1934},{"className":1933},[],[1935],{"type":41,"value":1936},"nodeNames",{"type":41,"value":168},{"type":35,"tag":50,"props":1939,"children":1941},{"className":1940},[],[1942],{"type":41,"value":1943},"truncateData",{"type":41,"value":1945},") for node inputs\u002Foutputs.",{"type":35,"tag":1061,"props":1947,"children":1949},{"id":1948},"data-tables",[1950],{"type":41,"value":1951},"Data tables",{"type":35,"tag":44,"props":1953,"children":1954},{},[1955,1957,1962],{"type":41,"value":1956},"n8n's built-in tabular storage. ",{"type":35,"tag":79,"props":1958,"children":1959},{},[1960],{"type":41,"value":1961},"Not",{"type":41,"value":1963}," an external service. Prefer over external DBs for workflow-local persistent state. Full surface:",{"type":35,"tag":295,"props":1965,"children":1966},{},[1967,1981],{"type":35,"tag":299,"props":1968,"children":1969},{},[1970],{"type":35,"tag":303,"props":1971,"children":1972},{},[1973,1977],{"type":35,"tag":307,"props":1974,"children":1975},{},[1976],{"type":41,"value":1080},{"type":35,"tag":307,"props":1978,"children":1979},{},[1980],{"type":41,"value":1085},{"type":35,"tag":318,"props":1982,"children":1983},{},[1984,2001,2018,2042,2066],{"type":35,"tag":303,"props":1985,"children":1986},{},[1987,1996],{"type":35,"tag":325,"props":1988,"children":1989},{},[1990],{"type":35,"tag":50,"props":1991,"children":1993},{"className":1992},[],[1994],{"type":41,"value":1995},"create_data_table",{"type":35,"tag":325,"props":1997,"children":1998},{},[1999],{"type":41,"value":2000},"Create a new Data Table.",{"type":35,"tag":303,"props":2002,"children":2003},{},[2004,2013],{"type":35,"tag":325,"props":2005,"children":2006},{},[2007],{"type":35,"tag":50,"props":2008,"children":2010},{"className":2009},[],[2011],{"type":41,"value":2012},"search_data_tables",{"type":35,"tag":325,"props":2014,"children":2015},{},[2016],{"type":41,"value":2017},"Find existing Data Tables.",{"type":35,"tag":303,"props":2019,"children":2020},{},[2021,2037],{"type":35,"tag":325,"props":2022,"children":2023},{},[2024,2030,2031],{"type":35,"tag":50,"props":2025,"children":2027},{"className":2026},[],[2028],{"type":41,"value":2029},"rename_data_table",{"type":41,"value":1247},{"type":35,"tag":50,"props":2032,"children":2034},{"className":2033},[],[2035],{"type":41,"value":2036},"rename_data_table_column",{"type":35,"tag":325,"props":2038,"children":2039},{},[2040],{"type":41,"value":2041},"Rename.",{"type":35,"tag":303,"props":2043,"children":2044},{},[2045,2061],{"type":35,"tag":325,"props":2046,"children":2047},{},[2048,2054,2055],{"type":35,"tag":50,"props":2049,"children":2051},{"className":2050},[],[2052],{"type":41,"value":2053},"add_data_table_column",{"type":41,"value":1247},{"type":35,"tag":50,"props":2056,"children":2058},{"className":2057},[],[2059],{"type":41,"value":2060},"delete_data_table_column",{"type":35,"tag":325,"props":2062,"children":2063},{},[2064],{"type":41,"value":2065},"Schema changes.",{"type":35,"tag":303,"props":2067,"children":2068},{},[2069,2078],{"type":35,"tag":325,"props":2070,"children":2071},{},[2072],{"type":35,"tag":50,"props":2073,"children":2075},{"className":2074},[],[2076],{"type":41,"value":2077},"add_data_table_rows",{"type":35,"tag":325,"props":2079,"children":2080},{},[2081],{"type":41,"value":2082},"Append rows.",{"type":35,"tag":1061,"props":2084,"children":2086},{"id":2085},"version-history",[2087],{"type":41,"value":2088},"Version history",{"type":35,"tag":295,"props":2090,"children":2091},{},[2092,2106],{"type":35,"tag":299,"props":2093,"children":2094},{},[2095],{"type":35,"tag":303,"props":2096,"children":2097},{},[2098,2102],{"type":35,"tag":307,"props":2099,"children":2100},{},[2101],{"type":41,"value":1080},{"type":35,"tag":307,"props":2103,"children":2104},{},[2105],{"type":41,"value":1085},{"type":35,"tag":318,"props":2107,"children":2108},{},[2109,2126,2149],{"type":35,"tag":303,"props":2110,"children":2111},{},[2112,2121],{"type":35,"tag":325,"props":2113,"children":2114},{},[2115],{"type":35,"tag":50,"props":2116,"children":2118},{"className":2117},[],[2119],{"type":41,"value":2120},"get_workflow_history",{"type":35,"tag":325,"props":2122,"children":2123},{},[2124],{"type":41,"value":2125},"List a workflow's saved versions, newest first (n8n 2.29.0+).",{"type":35,"tag":303,"props":2127,"children":2128},{},[2129,2138],{"type":35,"tag":325,"props":2130,"children":2131},{},[2132],{"type":35,"tag":50,"props":2133,"children":2135},{"className":2134},[],[2136],{"type":41,"value":2137},"get_workflow_version",{"type":35,"tag":325,"props":2139,"children":2140},{},[2141,2143,2148],{"type":41,"value":2142},"Fetch a past version's full content by ",{"type":35,"tag":50,"props":2144,"children":2146},{"className":2145},[],[2147],{"type":41,"value":1277},{"type":41,"value":145},{"type":35,"tag":303,"props":2150,"children":2151},{},[2152,2161],{"type":35,"tag":325,"props":2153,"children":2154},{},[2155],{"type":35,"tag":50,"props":2156,"children":2158},{"className":2157},[],[2159],{"type":41,"value":2160},"restore_workflow_version",{"type":35,"tag":325,"props":2162,"children":2163},{},[2164],{"type":41,"value":2165},"Re-apply a past version as the current draft (records a new history entry).",{"type":35,"tag":59,"props":2167,"children":2169},{"id":2168},"the-protocol-in-order",[2170],{"type":41,"value":2171},"The protocol, in order",{"type":35,"tag":44,"props":2173,"children":2174},{},[2175],{"type":41,"value":2176},"For any n8n task:",{"type":35,"tag":71,"props":2178,"children":2179},{},[2180,2190,2200,2217,2233,2250],{"type":35,"tag":75,"props":2181,"children":2182},{},[2183,2188],{"type":35,"tag":79,"props":2184,"children":2185},{},[2186],{"type":41,"value":2187},"Recognize the matching skill",{"type":41,"value":2189}," from the index above. If the task spans skills, recognize the primary one first and pick up others as their triggers come up.",{"type":35,"tag":75,"props":2191,"children":2192},{},[2193,2198],{"type":35,"tag":79,"props":2194,"children":2195},{},[2196],{"type":41,"value":2197},"Invoke the skill via the Skill tool",{"type":41,"value":2199}," before the first MCP call. Don't call n8n MCP tools blind.",{"type":35,"tag":75,"props":2201,"children":2202},{},[2203,2208,2210,2215],{"type":35,"tag":79,"props":2204,"children":2205},{},[2206],{"type":41,"value":2207},"Read the SDK reference once per session",{"type":41,"value":2209}," before writing workflow code (",{"type":35,"tag":50,"props":2211,"children":2213},{"className":2212},[],[2214],{"type":41,"value":174},{"type":41,"value":2216},"). The most efficient way to avoid SDK-shape mistakes.",{"type":35,"tag":75,"props":2218,"children":2219},{},[2220,2225,2226,2231],{"type":35,"tag":79,"props":2221,"children":2222},{},[2223],{"type":41,"value":2224},"Get node types before configuring any node",{"type":41,"value":658},{"type":35,"tag":50,"props":2227,"children":2229},{"className":2228},[],[2230],{"type":41,"value":55},{"type":41,"value":2232},"). Guessing parameter names creates invalid workflows, sometimes silently.",{"type":35,"tag":75,"props":2234,"children":2235},{},[2236,2241,2243,2248],{"type":35,"tag":79,"props":2237,"children":2238},{},[2239],{"type":41,"value":2240},"Validate before publish, verify after create\u002Fupdate.",{"type":41,"value":2242}," Validation catches schema errors. Verification (pulling the workflow back via ",{"type":35,"tag":50,"props":2244,"children":2246},{"className":2245},[],[2247],{"type":41,"value":117},{"type":41,"value":2249},") catches connection bugs validation misses.",{"type":35,"tag":75,"props":2251,"children":2252},{},[2253,2258],{"type":35,"tag":79,"props":2254,"children":2255},{},[2256],{"type":41,"value":2257},"Surface drift when you spot it.",{"type":41,"value":2259}," If a tool or parameter doesn't match what a skill says, tell the user. Updates may be needed.",{"type":35,"tag":59,"props":2261,"children":2263},{"id":2262},"reporting-skills-used",[2264],{"type":41,"value":2265},"Reporting skills used",{"type":35,"tag":44,"props":2267,"children":2268},{},[2269,2274,2275,2280,2282,2288],{"type":35,"tag":50,"props":2270,"children":2272},{"className":2271},[],[2273],{"type":41,"value":1555},{"type":41,"value":651},{"type":35,"tag":50,"props":2276,"children":2278},{"className":2277},[],[2279],{"type":41,"value":1216},{"type":41,"value":2281}," take an optional ",{"type":35,"tag":50,"props":2283,"children":2285},{"className":2284},[],[2286],{"type":41,"value":2287},"skillsUsed: string[]",{"type":41,"value":2289},". Pass it every time so the n8n team can measure plugin impact on MCP output.",{"type":35,"tag":232,"props":2291,"children":2292},{},[2293,2327,2337],{"type":35,"tag":75,"props":2294,"children":2295},{},[2296,2301,2303,2309,2311,2317,2319,2325],{"type":35,"tag":79,"props":2297,"children":2298},{},[2299],{"type":41,"value":2300},"Contents:",{"type":41,"value":2302}," report each skill exactly as the Skill tool names it, keeping the ",{"type":35,"tag":50,"props":2304,"children":2306},{"className":2305},[],[2307],{"type":41,"value":2308},"-official",{"type":41,"value":2310}," suffix: ",{"type":35,"tag":50,"props":2312,"children":2314},{"className":2313},[],[2315],{"type":41,"value":2316},"plugin:skill-official",{"type":41,"value":2318}," when plugin-namespaced, else bare ",{"type":35,"tag":50,"props":2320,"children":2322},{"className":2321},[],[2323],{"type":41,"value":2324},"skill-official",{"type":41,"value":2326},". The suffix marks these as ours (vs other n8n packs); the plugin prefix marks plugin vs raw-skill usage.",{"type":35,"tag":75,"props":2328,"children":2329},{},[2330,2335],{"type":35,"tag":79,"props":2331,"children":2332},{},[2333],{"type":41,"value":2334},"Window:",{"type":41,"value":2336}," skills invoked since the last successful create\u002Fupdate call. Resets after each.",{"type":35,"tag":75,"props":2338,"children":2339},{},[2340,2345],{"type":35,"tag":79,"props":2341,"children":2342},{},[2343],{"type":41,"value":2344},"Limits:",{"type":41,"value":2346}," max 50 entries, each max 128 chars.",{"type":35,"tag":59,"props":2348,"children":2350},{"id":2349},"reviewing-existing-workflows-or-projects",[2351],{"type":41,"value":2352},"Reviewing existing workflows or projects",{"type":35,"tag":44,"props":2354,"children":2355},{},[2356,2358,2363,2365,2370,2371,2377,2379,2384],{"type":41,"value":2357},"For audits, code-review, or any task framed as \"review this workflow\" \u002F \"what's wrong with this\" \u002F \"audit this project,\" walk the ",{"type":35,"tag":79,"props":2359,"children":2360},{},[2361],{"type":41,"value":2362},"review checklist",{"type":41,"value":2364},": ",{"type":35,"tag":50,"props":2366,"children":2368},{"className":2367},[],[2369],{"type":41,"value":222},{"type":41,"value":95},{"type":35,"tag":50,"props":2372,"children":2374},{"className":2373},[],[2375],{"type":41,"value":2376},"references\u002FREVIEW_CHECKLIST.md",{"type":41,"value":2378},". Severity-tiered (MUST FIX \u002F SHOULD FIX \u002F NICE TO HAVE), with each item linking to the canonical skill ref for the fix. Distinct from ",{"type":35,"tag":50,"props":2380,"children":2382},{"className":2381},[],[2383],{"type":41,"value":404},{"type":41,"value":2385}," (pre-publish gates for in-progress builds): REVIEW_CHECKLIST is for any workflow, including ones built by anyone, any age.",{"type":35,"tag":44,"props":2387,"children":2388},{},[2389,2391,2396],{"type":41,"value":2390},"A review agent should call ",{"type":35,"tag":50,"props":2392,"children":2394},{"className":2393},[],[2395],{"type":41,"value":117},{"type":41,"value":2397}," first, walk the checklist top to bottom, and report findings grouped by severity. MUST FIX items shouldn't be auto-fixed without user confirmation.",{"type":35,"tag":59,"props":2399,"children":2401},{"id":2400},"when-in-doubt",[2402],{"type":41,"value":2403},"When in doubt",{"type":35,"tag":232,"props":2405,"children":2406},{},[2407,2438,2458,2463],{"type":35,"tag":75,"props":2408,"children":2409},{},[2410,2415,2417,2422,2424,2429,2431,2437],{"type":35,"tag":79,"props":2411,"children":2412},{},[2413],{"type":41,"value":2414},"Can't find a workflow the user is referring to?",{"type":41,"value":2416}," If the user built it in the n8n UI, the most common reason is ",{"type":35,"tag":79,"props":2418,"children":2419},{},[2420],{"type":41,"value":2421},"MCP access isn't enabled on that specific workflow",{"type":41,"value":2423},": UI-created workflows can default to MCP-disabled and stay invisible until the per-workflow toggle is flipped. Ask the user: \"Open the workflow in n8n, Settings, toggle MCP access on.\" (MCP-created workflows default on, so this only applies to UI-built ones.) See the ",{"type":35,"tag":50,"props":2425,"children":2427},{"className":2426},[],[2428],{"type":41,"value":222},{"type":41,"value":2430}," skill (",{"type":35,"tag":50,"props":2432,"children":2434},{"className":2433},[],[2435],{"type":41,"value":2436},"references\u002FMCP_ACCESS_PER_WORKFLOW.md",{"type":41,"value":674},{"type":35,"tag":75,"props":2439,"children":2440},{},[2441,2443,2449,2451,2456],{"type":41,"value":2442},"The user is right. If they say something's broken, believe them, even if you \"know\" the workflow is correct. Re-check parameters, fetch the n8n source from ",{"type":35,"tag":50,"props":2444,"children":2446},{"className":2445},[],[2447],{"type":41,"value":2448},"github.com\u002Fn8n-io\u002Fn8n",{"type":41,"value":2450}," to trace logic, find API docs for missing functions. The ",{"type":35,"tag":50,"props":2452,"children":2454},{"className":2453},[],[2455],{"type":41,"value":1022},{"type":41,"value":2457}," skill walks through this.",{"type":35,"tag":75,"props":2459,"children":2460},{},[2461],{"type":41,"value":2462},"If no skill fits and the task is non-trivial, ask before guessing.",{"type":35,"tag":75,"props":2464,"children":2465},{},[2466],{"type":41,"value":2467},"These skills are opinionated, but considered best practice by the n8n team. The user can override any opinion by editing the SKILL.md. The plugin is just markdown.",{"items":2469,"total":2567},[2470,2483,2497,2512,2529,2543,2555],{"slug":424,"name":424,"fn":2471,"description":2472,"org":2473,"tags":2474,"stars":19,"repoUrl":20,"updatedAt":2482},"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},[2475,2478,2481],{"name":2476,"slug":2477,"type":15},"Agents","agents",{"name":2479,"slug":2480,"type":15},"LLM","llm",{"name":17,"slug":18,"type":15},"2026-07-08T05:44:47.938896",{"slug":988,"name":988,"fn":2484,"description":2485,"org":2486,"tags":2487,"stars":19,"repoUrl":20,"updatedAt":2496},"handle binary data and files in n8n","Use when handling files, images, attachments, or binary data in n8n, OR when an AI agent needs to take a user-uploaded file as tool input or return a generated file. For Data Tables (schemas, dedup, persistent state), see the separate n8n-data-tables-official skill. Triggers on \"file\", \"image\", \"PDF\", \"attachment\", \"binary\", \"upload\", \"download\", chat trigger with files, agent tool that needs a file, vision\u002Fmultimodal, or any handling of non-JSON file data.",{"slug":8,"name":8,"logoUrl":9,"githubOrg":10},[2488,2491,2494,2495],{"name":2489,"slug":2490,"type":15},"Automation","automation",{"name":2492,"slug":2493,"type":15},"File Uploads","file-uploads",{"name":8,"slug":8,"type":15},{"name":17,"slug":18,"type":15},"2026-07-08T05:45:01.884342",{"slug":250,"name":250,"fn":2498,"description":2499,"org":2500,"tags":2501,"stars":19,"repoUrl":20,"updatedAt":2511},"write custom logic in n8n","Use when the user reaches for a Code node, mentions writing JavaScript or Python in n8n, or any custom logic comes up in workflow design. Triggers on \"Code node\", \"Code\", \"JavaScript\", \"Python\", \"custom logic\", \"transform data\", \"$input\", \"$json transformation\", \"loop in code\", \"write a function\", or any time the obvious answer seems to be \"just put it in code.\"",{"slug":8,"name":8,"logoUrl":9,"githubOrg":10},[2502,2505,2508],{"name":2503,"slug":2504,"type":15},"Engineering","engineering",{"name":2506,"slug":2507,"type":15},"JavaScript","javascript",{"name":2509,"slug":2510,"type":15},"Python","python","2026-07-08T05:44:49.656127",{"slug":143,"name":143,"fn":2513,"description":2514,"org":2515,"tags":2516,"stars":19,"repoUrl":20,"updatedAt":2528},"manage credentials and security in n8n","Use when handling any auth, API keys, tokens, OAuth, bearer tokens, basic auth, or secret values in n8n workflows. Triggers on \"API key\", \"token\", \"bearer\", \"OAuth\", \"secret\", \"auth\", \"credentials\", \"Authorization header\", \"x-api-key\", or any node configuration that mentions a third-party service.",{"slug":8,"name":8,"logoUrl":9,"githubOrg":10},[2517,2520,2521,2522,2525],{"name":2518,"slug":2519,"type":15},"Authentication","authentication",{"name":2489,"slug":2490,"type":15},{"name":8,"slug":8,"type":15},{"name":2523,"slug":2524,"type":15},"OAuth","oauth",{"name":2526,"slug":2527,"type":15},"Security","security","2026-07-08T05:45:07.766252",{"slug":1005,"name":1005,"fn":2530,"description":2531,"org":2532,"tags":2533,"stars":19,"repoUrl":20,"updatedAt":2542},"manage n8n Data Tables","Use when working with n8n's built-in Data Tables, designing schemas, inserting\u002Fupdating\u002Fupserting rows, deduping, or querying. Triggers on \"Data Table\", \"data table\", `n8n-nodes-base.dataTable`, \"dedup\", \"idempotency\", \"lookup\", \"persistent state\", \"store across executions\", or any schema design discussion inside n8n.",{"slug":8,"name":8,"logoUrl":9,"githubOrg":10},[2534,2537,2540,2541],{"name":2535,"slug":2536,"type":15},"Data Modeling","data-modeling",{"name":2538,"slug":2539,"type":15},"Database","database",{"name":8,"slug":8,"type":15},{"name":17,"slug":18,"type":15},"2026-07-08T05:44:52.048039",{"slug":1022,"name":1022,"fn":2544,"description":2545,"org":2546,"tags":2547,"stars":19,"repoUrl":20,"updatedAt":2554},"debug and fix n8n workflow errors","Use when an n8n workflow isn't working, errors appear, results don't match what was expected, or the user says \"this isn't working.\" Triggers on errors, unexpected output, \"it's not working\", \"why is this happening\", \"the workflow stopped\", failure investigation, or any debugging context.",{"slug":8,"name":8,"logoUrl":9,"githubOrg":10},[2548,2549,2552,2553],{"name":2489,"slug":2490,"type":15},{"name":2550,"slug":2551,"type":15},"Debugging","debugging",{"name":8,"slug":8,"type":15},{"name":17,"slug":18,"type":15},"2026-07-08T05:45:05.897341",{"slug":215,"name":215,"fn":2556,"description":2557,"org":2558,"tags":2559,"stars":19,"repoUrl":20,"updatedAt":2566},"implement error handling in n8n","Use when building any webhook-triggered workflow, scheduled\u002Fproduction-bound workflow, wiring a per-node error output, or any workflow where silent failure would drop user-visible work. Triggers on \"webhook\", \"respond to webhook\", \"API\", \"production\", \"error\", \"failure\", \"5xx\", \"try\u002Fcatch\", \"error workflow\", \"onError\", \"continueErrorOutput\", \"error branch\", \"node error output\", \"output(1)\", \"main[1]\", \"scheduled\", or any workflow that runs unattended.",{"slug":8,"name":8,"logoUrl":9,"githubOrg":10},[2560,2561,2562,2565],{"name":2550,"slug":2551,"type":15},{"name":8,"slug":8,"type":15},{"name":2563,"slug":2564,"type":15},"Operations","operations",{"name":17,"slug":18,"type":15},"2026-07-08T05:44:59.710099",14,{"items":2569,"total":2709},[2570,2587,2600,2611,2621,2632,2645,2662,2671,2683,2693,2703],{"slug":2571,"name":2571,"fn":2572,"description":2573,"org":2574,"tags":2575,"stars":2584,"repoUrl":2585,"updatedAt":2586},"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},[2576,2579,2580,2583],{"name":2577,"slug":2578,"type":15},"Evals","evals",{"name":8,"slug":8,"type":15},{"name":2581,"slug":2582,"type":15},"Testing","testing",{"name":17,"slug":18,"type":15},198156,"https:\u002F\u002Fgithub.com\u002Fn8n-io\u002Fn8n","2026-07-24T05:37:07.398695",{"slug":2588,"name":2588,"fn":2589,"description":2590,"org":2591,"tags":2592,"stars":2584,"repoUrl":2585,"updatedAt":2599},"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},[2593,2594,2597,2598],{"name":2489,"slug":2490,"type":15},{"name":2595,"slug":2596,"type":15},"Configuration","configuration",{"name":8,"slug":8,"type":15},{"name":2523,"slug":2524,"type":15},"2026-06-30T07:40:45.54",{"slug":2601,"name":2601,"fn":2530,"description":2602,"org":2603,"tags":2604,"stars":2584,"repoUrl":2585,"updatedAt":2610},"data-table-manager","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},[2605,2608,2609],{"name":2606,"slug":2607,"type":15},"Data Engineering","data-engineering",{"name":2538,"slug":2539,"type":15},{"name":8,"slug":8,"type":15},"2026-07-27T06:07:14.648144",{"slug":2612,"name":2612,"fn":2613,"description":2614,"org":2615,"tags":2616,"stars":2584,"repoUrl":2585,"updatedAt":2599},"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},[2617,2618,2619,2620],{"name":2489,"slug":2490,"type":15},{"name":2550,"slug":2551,"type":15},{"name":8,"slug":8,"type":15},{"name":17,"slug":18,"type":15},{"slug":2622,"name":2622,"fn":2623,"description":2624,"org":2625,"tags":2626,"stars":2584,"repoUrl":2585,"updatedAt":2631},"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},[2627,2628,2629,2630],{"name":2476,"slug":2477,"type":15},{"name":2489,"slug":2490,"type":15},{"name":8,"slug":8,"type":15},{"name":17,"slug":18,"type":15},"2026-07-30T05:30:06.772347",{"slug":2633,"name":2633,"fn":2634,"description":2635,"org":2636,"tags":2637,"stars":2584,"repoUrl":2585,"updatedAt":2644},"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},[2638,2639,2642,2643],{"name":2489,"slug":2490,"type":15},{"name":2640,"slug":2641,"type":15},"CLI","cli",{"name":8,"slug":8,"type":15},{"name":17,"slug":18,"type":15},"2026-04-06T18:38:40.360123",{"slug":2646,"name":2646,"fn":2647,"description":2648,"org":2649,"tags":2650,"stars":2584,"repoUrl":2585,"updatedAt":2661},"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},[2651,2654,2655,2658],{"name":2652,"slug":2653,"type":15},"Documentation","documentation",{"name":8,"slug":8,"type":15},{"name":2656,"slug":2657,"type":15},"Reference","reference",{"name":2659,"slug":2660,"type":15},"Search","search","2026-07-27T06:07:15.692906",{"slug":2663,"name":2663,"fn":2664,"description":2665,"org":2666,"tags":2667,"stars":2584,"repoUrl":2585,"updatedAt":2599},"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},[2668,2669,2670],{"name":2489,"slug":2490,"type":15},{"name":8,"slug":8,"type":15},{"name":17,"slug":18,"type":15},{"slug":2672,"name":2672,"fn":2673,"description":2674,"org":2675,"tags":2676,"stars":2584,"repoUrl":2585,"updatedAt":2682},"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},[2677,2678,2679,2681],{"name":2489,"slug":2490,"type":15},{"name":8,"slug":8,"type":15},{"name":2680,"slug":2672,"type":15},"Planning",{"name":17,"slug":18,"type":15},"2026-07-27T06:07:16.673218",{"slug":2684,"name":2684,"fn":2685,"description":2686,"org":2687,"tags":2688,"stars":2584,"repoUrl":2585,"updatedAt":2692},"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},[2689,2690,2691],{"name":2489,"slug":2490,"type":15},{"name":8,"slug":8,"type":15},{"name":17,"slug":18,"type":15},"2026-07-24T05:37:08.421329",{"slug":2694,"name":2694,"fn":2695,"description":2696,"org":2697,"tags":2698,"stars":2584,"repoUrl":2585,"updatedAt":2702},"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},[2699,2700,2701],{"name":2489,"slug":2490,"type":15},{"name":8,"slug":8,"type":15},{"name":17,"slug":18,"type":15},"2026-07-30T05:30:07.798011",{"slug":424,"name":424,"fn":2471,"description":2472,"org":2704,"tags":2705,"stars":19,"repoUrl":20,"updatedAt":2482},{"slug":8,"name":8,"logoUrl":9,"githubOrg":10},[2706,2707,2708],{"name":2476,"slug":2477,"type":15},{"name":2479,"slug":2480,"type":15},{"name":17,"slug":18,"type":15},25]