[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6FCVXZMPSH02T64EC19DDA8":3,"skill-same:01M6FCVXZMPSH02T64EC19DDA8":76},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":46,"linkOnly":47,"markdownContent":48,"markdownBody":49,"frontMatter":50,"refName":32,"commitSha":56,"skillDirectory":57,"forksCount":58,"repositoryHtmlUrl":59,"repositoryHomepageUrl":6,"ownerHtmlUrl":60,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":61,"install":62,"resources":75},"01M6FCVXZMPSH02T64EC19DDA8","using-n8n-mcp-skills",null,"Route n8n MCP workflow design, editing, validation, testing, deployment, credential, execution, and debugging tasks to specialist guidance.","boisenoise\u002Fskills-collections","boisenoise","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F193180?v=4","01M6CDBDQK6BDN55ZMA6B6PKBM","01M6CDBDVSJ3JPTBYN26FZ7TZK",12,"MIT","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-using-n8n-mcp-skills\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45],"MCP","n8n mcp","using n8n mcp skills","n8n","execution","blob","tree","critical","route","main","community","guidance","editing","testing","https","license","validation","tasks","debugging","deployment","workflow","github","design","2026-11-10 10:12:30",false,"---\nname: using-n8n-mcp-skills\ndescription: Route n8n MCP workflow design, editing, validation, testing, deployment, credential, execution, and debugging tasks to specialist guidance.\nrisk: critical\nsource: https:\u002F\u002Fgithub.com\u002Fczlonkowski\u002Fn8n-skills\u002Ftree\u002Fmain\u002Fskills\u002Fusing-n8n-mcp-skills\nsource_repo: czlonkowski\u002Fn8n-skills\nsource_type: community\ndate_added: \"2026-07-21\"\nauthor: Romuald Czlonkowski\nlicense: MIT\nlicense_source: https:\u002F\u002Fgithub.com\u002Fczlonkowski\u002Fn8n-skills\u002Fblob\u002Fmain\u002FLICENSE\n---\n\n# Using the n8n-mcp Skills\n\n## When to Use\n\nUse this router at the start of any n8n MCP workflow design, inspection, edit, validation, test, deployment, credential, execution, or troubleshooting task so the relevant specialist guidance is loaded first.\n\nBegin with read-only discovery and live schema inspection. Never copy secrets into prompts or workflow fields, never infer the target instance, and obtain approval before tests with side effects, activation, deletion, credential mutation, or other externally visible changes.\n\nThis is a **router**, not a reference. It tells you which skill owns the rules for what\nyou're about to do. The skill bodies hold the actual guidance — invoke them with the\nSkill tool. When in doubt, load more skills rather than fewer.\n\nThe community **n8n-mcp** server and n8n itself move faster than any model's training\ncutoff. Tool names, parameters, node `typeVersion`s, and default behaviors drift between\nreleases. When you spot drift — a tool a skill names doesn't exist, a parameter shape\ndoesn't match what `get_node` returns, behavior differs from what a skill describes —\ntrust the **live tool**, tell the user, and suggest updating the pack and the instance.\n\n## Non-negotiables\n\nThree rules with no exceptions. Each one prevents a class of workflow that looks correct\nbut breaks in production.\n\n1. **Invoke the relevant skill before any n8n action** — not just before MCP calls.\n   Before writing an expression, configuring a node, designing a workflow, wiring a\n   connection, or writing Code, invoke the matching skill. The PreToolUse hooks remind\n   you on the highest-impact tool calls *only when the plugin bundle is installed*; on\n   Claude.ai (plain skill uploads, no hooks) the responsibility is entirely yours.\n2. **Validate AND verify before activating.** Run `validate_workflow` (or\n   `n8n_validate_workflow` by id) before you activate, and call `n8n_get_workflow` after\n   every create or update to inspect the `connections` object. Validation alone misses\n   silently dropped wires, Merge index off-by-one, and error outputs that were never\n   wired. Validation passing means the JSON is well-formed — not that the workflow is\n   correct.\n3. **Secrets never go in text fields.** Tokens, API keys, and passwords always go through\n   the n8n credential system. If no native node exists, use the HTTP Request node with\n   the official credential type. A Set node holding a token referenced via `{{ $json.token }}`\n   is a leak with extra steps. See `n8n-mcp-tools-expert`.\n\n## Lean on skills, not training data\n\nn8n changes constantly. \"Remembered\" parameter names are often silently wrong — they\nvalidate as plain strings and then do nothing at runtime. Trust the skills and the live\ntools (`get_node`, `search_nodes`, `tools_documentation`) over recollection. Treat a skill as versioned guidance; verify consequential behavior against current schemas and owning documentation. If `get_node` contradicts a skill, trust the\ntool and flag the drift.\n\n## Strong defaults\n\nEach skill owns its own exceptions; these are the defaults.\n\n- **The Code node is a last resort.** Expression first, then an arrow function inside Edit\n  Fields, then a Code node only when neither can do the job. See `n8n-code-javascript`.\n- **A Set node feeding 0–1 consumers is almost always wrong.** Inline the expression at\n  the consumer instead. See `n8n-expression-syntax`.\n- **Per-item iteration is automatic.** Don't add a Loop Over Items node to \"make it loop\"\n  when default per-item execution already handles the case.\n- **Configure from the live schema, never from memory.** `get_node` before you set\n  parameters. See `n8n-node-configuration`.\n\n## Red flags: \"about to ___\" → invoke ___\n\nIf you catch yourself thinking any of these, stop and invoke the named skill first.\n\n| Thought | Invoke |\n|---|---|\n| \"This workflow is simple, I'll just build it\" | `n8n-workflow-patterns` — choose the smallest correct graph, not an arbitrary node-count target |\n| \"I'll add a Set node to map these fields\" | `n8n-expression-syntax` — Set feeding ≤1 consumer is the #1 antipattern |\n| \"I'll just use a Code node, it's easier\" | `n8n-code-javascript` — the bar is high; most reaches are expressions or Edit Fields |\n| \"The user mentioned data, I'll write Python\" | `n8n-code-javascript` — default JS; Python (`n8n-code-python`) only on explicit ask |\n| \"I'm writing code an AI agent will call\" | `n8n-code-tool` — a different runtime contract from the Code node |\n| \"Date math — I'll drop in a DateTime node\" | `n8n-expression-syntax` — Luxon inline is almost always right |\n| \"I'll wire a Merge with 3 sources\" | `n8n-node-configuration` — Merge defaults to 2 inputs; the 3rd silently drops |\n| \"Validation passed, I'm ready to activate\" | `n8n-validation-expert` + `n8n-workflow-patterns` — run the antipattern scan |\n| \"Validation threw an error I don't understand\" | `n8n-validation-expert` — what each error and warning means, and which are must-fix vs. best-practice advice |\n| \"I'll reference `$json.x` here\" | `n8n-expression-syntax` — prefer `$('Node').item.json.x` in branchy workflows |\n| \"This webhook\u002Fscheduled flow is happy-path only\" | `n8n-error-handling` — wire an error branch on every fallible node; 4xx caller faults, 5xx yours |\n| \"I'll pass this file\u002Fimage through as JSON\" | `n8n-binary-and-data` — file contents live in `$binary`, and can't cross the agent-tool boundary |\n| \"I'll wire up an AI agent and give the model some tools\" | `n8n-agents` — tool names & descriptions ARE the prompt; memory, structured output, and topology have traps |\n| \"I'll copy this logic into another workflow\" \u002F \"this is getting big\" | `n8n-subworkflows` — extract a reusable sub-workflow; search before building |\n| \"I'll create that credential \u002F open that workflow\" (account has >1 instance) | `n8n-multi-instance` — every call hits the currently-targeted instance; reads misroute silently, and an ambiguous credential write fails closed with `INSTANCE_AMBIGUOUS` |\n\n## Skill index\n\n| Skill | Reach for it when |\n|---|---|\n| `using-n8n-mcp-skills` | This router (auto-loaded). Names the skill that owns your task. |\n| `n8n-mcp-tools-expert` | Choosing or calling any n8n-mcp tool; node discovery; credentials; data tables; security audit; templates |\n| `n8n-workflow-patterns` | Designing or building a workflow; picking an architecture (webhook \u002F HTTP API \u002F database \u002F AI agent \u002F scheduled \u002F batch) |\n| `n8n-node-configuration` | Configuring any node; operation-aware required fields; property dependencies; surgical field edits |\n| `n8n-expression-syntax` | Writing `{{ }}`, `$json`\u002F`$node`\u002F`$now`; mapping data between nodes; the transform gatekeeper; Set-node discipline |\n| `n8n-validation-expert` | Interpreting validation errors\u002Fwarnings; false positives; the validation loop; auto-fix; reviewing an existing workflow |\n| `n8n-code-javascript` | Any Code node in JavaScript; data access; `this.helpers`; DateTime; SplitInBatches loop patterns |\n| `n8n-code-python` | A Code node specifically requested in Python; standard-library limits |\n| `n8n-code-tool` | The AI-agent-callable Custom Code Tool (`toolCode`) — returns a string, no `$fromAI`\u002F`$input` |\n| `n8n-error-handling` | Webhook\u002FAPI or unattended workflows; wiring error outputs; retries; 4xx\u002F5xx response shapes; silent failures |\n| `n8n-binary-and-data` | Files, images, PDFs, attachments, uploads\u002Fdownloads, vision; passing a file to\u002Ffrom an agent tool |\n| `n8n-subworkflows` | Reusable \u002F multi-step builds; Execute Workflow; extracting shared logic; Define-Below inputs; all-vs-each; exposing a workflow as an agent tool |\n| `n8n-agents` | AI Agent \u002F LLM-with-tools \u002F Text Classifier; tool design & `$fromAI`; system prompts; structured output; memory; RAG; human review; chat bots |\n| `n8n-multi-instance` | Accounts with multiple instances (the `n8n_instances` tool is present); switching the target instance; verifying before credential writes; recovering from an unexpected `NOT_FOUND`, wrong\u002Fempty reads, or an `INSTANCE_AMBIGUOUS` credential-write fail-close |\n\n## n8n-mcp tools — working knowledge from turn one\n\nQualified names look like `mcp__\u003Cserver>__\u003Ctool>` (`\u003Cserver>` is usually `n8n-mcp`). This\ncloses the gap where a tool's full description isn't loaded until first use.\n\n**Discovery & docs**\n- `tools_documentation` — meta-docs for every tool; `{topic:\"ai_agents_guide\", depth:\"full\"}` for the agent guide.\n- `search_nodes` — find nodes by keyword.\n- `get_node` — node info. Takes a single **SHORT-form** `nodeType` (`nodes-base.httpRequest`, `nodes-langchain.agent`), plus `detail` (minimal\u002Fstandard\u002Ffull) and `mode` (info\u002Fdocs\u002Fsearch_properties\u002Fversions).\n- `validate_node` — validate one node's config in isolation (profiles: minimal\u002Fruntime\u002Fai-friendly\u002Fstrict).\n- `search_templates` \u002F `get_template` — the template library (by keyword, nodes, task, metadata).\n\n**Build & edit**\n- `n8n_create_workflow` — create from full workflow JSON.\n- `n8n_update_partial_workflow` — incremental diff ops (`{id, operations:[…]}`): addNode, updateNode, patchNodeField, addConnection, activateWorkflow, etc. Preferred for edits.\n- `n8n_update_full_workflow` — full replacement.\n- `n8n_autofix_workflow` — auto-fix common issues.\n- `n8n_deploy_template` — deploy a template to the instance.\n\n**Validate** (necessary, not sufficient — always pair with the antipattern scan)\n- `validate_workflow` — full JSON in, errors\u002Fwarnings\u002Ffixes out. Node types here are **LONG form** (`n8n-nodes-base.set`).\n- `n8n_validate_workflow` — validate a deployed workflow by `{id}` (no node JSON to inspect).\n\n**Inspect & lifecycle**\n- `n8n_get_workflow` — fetch a workflow (full \u002F structure \u002F active \u002F filtered \u002F minimal). Use it to verify `connections` after edits; `mode=\"filtered\"` + `nodeNames` reads one heavy node (e.g. long Code source) without pulling the whole workflow, which can truncate client-side.\n- `n8n_list_workflows` — list\u002Ffilter (search before duplicating logic).\n- `n8n_delete_workflow`, `n8n_workflow_versions` (history\u002Frollback), `n8n_instances` (multi-instance accounts only: list\u002Fswitch the target instance — see `n8n-multi-instance`), `n8n_health_check` (returns the resolved `instanceName`).\n\n**Test & run**\n- `n8n_test_workflow` — runs real nodes (Code, HTTP, DB writes, sends all fire). Ask the user before running when side effects exist.\n- `n8n_executions` — list\u002Finspect executions. **There is no `execute_workflow` tool.**\n- `n8n_evaluations` — read evaluation test runs (n8n ≥ 2.30): list runs, aggregated metrics, per-case results. Read-only — runs are started from the n8n editor, not the API; a 403 indicates denied access: inspect actual version, scopes and policy before proposing any credential replacement.\n\n**Data, credentials, audit**\n- `n8n_manage_datatable` — Data Table CRUD, filtering, dry-run.\n- `n8n_manage_credentials` — credential CRUD + `getSchema` discovery.\n- `n8n_audit_instance` — security audit (hardcoded secrets, unauthenticated webhooks, error-handling gaps).\n\n> **Node-type form trap:** `get_node` \u002F `validate_node` take SHORT form (`nodes-base.set`);\n> workflow JSON inside `validate_workflow` \u002F `n8n_create_workflow` uses LONG form\n> (`n8n-nodes-base.set`). Mixing them is a common, silent mistake — see `n8n-mcp-tools-expert`.\n\n## The protocol, in order\n\n1. Recognize the matching skill from the index and **invoke it before the first MCP call**.\n2. Skim `tools_documentation` once per session to refresh the tool surface if you're unsure.\n3. `get_node` before configuring any node — read the live schema, don't assume.\n4. Build \u002F edit, then **`validate_workflow` before activating** and **`n8n_get_workflow` after** to check `connections`.\n5. Surface any drift you notice (missing tool, changed parameter, diverging behavior).\n\n## When in doubt\n\n- **Can't find a workflow the user built in the UI?** The most common cause is per-workflow\n  MCP access being off. Ask them to open it in n8n, go to Settings, and enable MCP access.\n- **User says it's broken?** Believe them. Re-check parameters against `get_node`, trace\n  data references, inspect the execution. See `n8n-validation-expert`.\n- **No skill fits and the task is non-trivial?** Ask before guessing.\n\nThese are opinionated best practices, not laws. Disagree with a call? It's all markdown —\nedit the skill.\n\n## Example\n\n```yaml\nrequest: Build a webhook that validates input, calls an API, and returns structured errors.\nspecialists: [n8n-workflow-patterns, n8n-node-configuration, n8n-error-handling]\nsequence:\n  - inspect the target instance and live node schemas\n  - build and validate the graph\n  - preview side effects and obtain approval\n  - write changes, fetch the saved workflow with n8n_get_workflow, and revalidate\n  - activate and test only after approval\n```\n\n## Limitations\n\n- The router describes a moving n8n MCP surface; live tool schemas and the target instance override stale examples.\n- Availability of lifecycle, credential, evaluation, and multi-instance tools depends on server version and permissions.\n- Routing to a specialist skill does not authorize mutations, executions, activation, deletion, or credential changes.\n\nA missing companion skill or Skill tool is a disclosed prerequisite gap, not permission to invent one. Upstream hooks are not installed by this catalog source. Do not update the skill pack or instance automatically merely because drift is observed. Per-item execution, item linking and binary\u002Ftool boundaries depend on node mode\u002Fversion; validate the actual data shape with controlled fixtures.\n","# Using the n8n-mcp Skills\n\n## When to Use\n\nUse this router at the start of any n8n MCP workflow design, inspection, edit, validation, test, deployment, credential, execution, or troubleshooting task so the relevant specialist guidance is loaded first.\n\nBegin with read-only discovery and live schema inspection. Never copy secrets into prompts or workflow fields, never infer the target instance, and obtain approval before tests with side effects, activation, deletion, credential mutation, or other externally visible changes.\n\nThis is a **router**, not a reference. It tells you which skill owns the rules for what\nyou're about to do. The skill bodies hold the actual guidance — invoke them with the\nSkill tool. When in doubt, load more skills rather than fewer.\n\nThe community **n8n-mcp** server and n8n itself move faster than any model's training\ncutoff. Tool names, parameters, node `typeVersion`s, and default behaviors drift between\nreleases. When you spot drift — a tool a skill names doesn't exist, a parameter shape\ndoesn't match what `get_node` returns, behavior differs from what a skill describes —\ntrust the **live tool**, tell the user, and suggest updating the pack and the instance.\n\n## Non-negotiables\n\nThree rules with no exceptions. Each one prevents a class of workflow that looks correct\nbut breaks in production.\n\n1. **Invoke the relevant skill before any n8n action** — not just before MCP calls.\n   Before writing an expression, configuring a node, designing a workflow, wiring a\n   connection, or writing Code, invoke the matching skill. The PreToolUse hooks remind\n   you on the highest-impact tool calls *only when the plugin bundle is installed*; on\n   Claude.ai (plain skill uploads, no hooks) the responsibility is entirely yours.\n2. **Validate AND verify before activating.** Run `validate_workflow` (or\n   `n8n_validate_workflow` by id) before you activate, and call `n8n_get_workflow` after\n   every create or update to inspect the `connections` object. Validation alone misses\n   silently dropped wires, Merge index off-by-one, and error outputs that were never\n   wired. Validation passing means the JSON is well-formed — not that the workflow is\n   correct.\n3. **Secrets never go in text fields.** Tokens, API keys, and passwords always go through\n   the n8n credential system. If no native node exists, use the HTTP Request node with\n   the official credential type. A Set node holding a token referenced via `{{ $json.token }}`\n   is a leak with extra steps. See `n8n-mcp-tools-expert`.\n\n## Lean on skills, not training data\n\nn8n changes constantly. \"Remembered\" parameter names are often silently wrong — they\nvalidate as plain strings and then do nothing at runtime. Trust the skills and the live\ntools (`get_node`, `search_nodes`, `tools_documentation`) over recollection. Treat a skill as versioned guidance; verify consequential behavior against current schemas and owning documentation. If `get_node` contradicts a skill, trust the\ntool and flag the drift.\n\n## Strong defaults\n\nEach skill owns its own exceptions; these are the defaults.\n\n- **The Code node is a last resort.** Expression first, then an arrow function inside Edit\n  Fields, then a Code node only when neither can do the job. See `n8n-code-javascript`.\n- **A Set node feeding 0–1 consumers is almost always wrong.** Inline the expression at\n  the consumer instead. See `n8n-expression-syntax`.\n- **Per-item iteration is automatic.** Don't add a Loop Over Items node to \"make it loop\"\n  when default per-item execution already handles the case.\n- **Configure from the live schema, never from memory.** `get_node` before you set\n  parameters. See `n8n-node-configuration`.\n\n## Red flags: \"about to ___\" → invoke ___\n\nIf you catch yourself thinking any of these, stop and invoke the named skill first.\n\n| Thought | Invoke |\n|---|---|\n| \"This workflow is simple, I'll just build it\" | `n8n-workflow-patterns` — choose the smallest correct graph, not an arbitrary node-count target |\n| \"I'll add a Set node to map these fields\" | `n8n-expression-syntax` — Set feeding ≤1 consumer is the #1 antipattern |\n| \"I'll just use a Code node, it's easier\" | `n8n-code-javascript` — the bar is high; most reaches are expressions or Edit Fields |\n| \"The user mentioned data, I'll write Python\" | `n8n-code-javascript` — default JS; Python (`n8n-code-python`) only on explicit ask |\n| \"I'm writing code an AI agent will call\" | `n8n-code-tool` — a different runtime contract from the Code node |\n| \"Date math — I'll drop in a DateTime node\" | `n8n-expression-syntax` — Luxon inline is almost always right |\n| \"I'll wire a Merge with 3 sources\" | `n8n-node-configuration` — Merge defaults to 2 inputs; the 3rd silently drops |\n| \"Validation passed, I'm ready to activate\" | `n8n-validation-expert` + `n8n-workflow-patterns` — run the antipattern scan |\n| \"Validation threw an error I don't understand\" | `n8n-validation-expert` — what each error and warning means, and which are must-fix vs. best-practice advice |\n| \"I'll reference `$json.x` here\" | `n8n-expression-syntax` — prefer `$('Node').item.json.x` in branchy workflows |\n| \"This webhook\u002Fscheduled flow is happy-path only\" | `n8n-error-handling` — wire an error branch on every fallible node; 4xx caller faults, 5xx yours |\n| \"I'll pass this file\u002Fimage through as JSON\" | `n8n-binary-and-data` — file contents live in `$binary`, and can't cross the agent-tool boundary |\n| \"I'll wire up an AI agent and give the model some tools\" | `n8n-agents` — tool names & descriptions ARE the prompt; memory, structured output, and topology have traps |\n| \"I'll copy this logic into another workflow\" \u002F \"this is getting big\" | `n8n-subworkflows` — extract a reusable sub-workflow; search before building |\n| \"I'll create that credential \u002F open that workflow\" (account has >1 instance) | `n8n-multi-instance` — every call hits the currently-targeted instance; reads misroute silently, and an ambiguous credential write fails closed with `INSTANCE_AMBIGUOUS` |\n\n## Skill index\n\n| Skill | Reach for it when |\n|---|---|\n| `using-n8n-mcp-skills` | This router (auto-loaded). Names the skill that owns your task. |\n| `n8n-mcp-tools-expert` | Choosing or calling any n8n-mcp tool; node discovery; credentials; data tables; security audit; templates |\n| `n8n-workflow-patterns` | Designing or building a workflow; picking an architecture (webhook \u002F HTTP API \u002F database \u002F AI agent \u002F scheduled \u002F batch) |\n| `n8n-node-configuration` | Configuring any node; operation-aware required fields; property dependencies; surgical field edits |\n| `n8n-expression-syntax` | Writing `{{ }}`, `$json`\u002F`$node`\u002F`$now`; mapping data between nodes; the transform gatekeeper; Set-node discipline |\n| `n8n-validation-expert` | Interpreting validation errors\u002Fwarnings; false positives; the validation loop; auto-fix; reviewing an existing workflow |\n| `n8n-code-javascript` | Any Code node in JavaScript; data access; `this.helpers`; DateTime; SplitInBatches loop patterns |\n| `n8n-code-python` | A Code node specifically requested in Python; standard-library limits |\n| `n8n-code-tool` | The AI-agent-callable Custom Code Tool (`toolCode`) — returns a string, no `$fromAI`\u002F`$input` |\n| `n8n-error-handling` | Webhook\u002FAPI or unattended workflows; wiring error outputs; retries; 4xx\u002F5xx response shapes; silent failures |\n| `n8n-binary-and-data` | Files, images, PDFs, attachments, uploads\u002Fdownloads, vision; passing a file to\u002Ffrom an agent tool |\n| `n8n-subworkflows` | Reusable \u002F multi-step builds; Execute Workflow; extracting shared logic; Define-Below inputs; all-vs-each; exposing a workflow as an agent tool |\n| `n8n-agents` | AI Agent \u002F LLM-with-tools \u002F Text Classifier; tool design & `$fromAI`; system prompts; structured output; memory; RAG; human review; chat bots |\n| `n8n-multi-instance` | Accounts with multiple instances (the `n8n_instances` tool is present); switching the target instance; verifying before credential writes; recovering from an unexpected `NOT_FOUND`, wrong\u002Fempty reads, or an `INSTANCE_AMBIGUOUS` credential-write fail-close |\n\n## n8n-mcp tools — working knowledge from turn one\n\nQualified names look like `mcp__\u003Cserver>__\u003Ctool>` (`\u003Cserver>` is usually `n8n-mcp`). This\ncloses the gap where a tool's full description isn't loaded until first use.\n\n**Discovery & docs**\n- `tools_documentation` — meta-docs for every tool; `{topic:\"ai_agents_guide\", depth:\"full\"}` for the agent guide.\n- `search_nodes` — find nodes by keyword.\n- `get_node` — node info. Takes a single **SHORT-form** `nodeType` (`nodes-base.httpRequest`, `nodes-langchain.agent`), plus `detail` (minimal\u002Fstandard\u002Ffull) and `mode` (info\u002Fdocs\u002Fsearch_properties\u002Fversions).\n- `validate_node` — validate one node's config in isolation (profiles: minimal\u002Fruntime\u002Fai-friendly\u002Fstrict).\n- `search_templates` \u002F `get_template` — the template library (by keyword, nodes, task, metadata).\n\n**Build & edit**\n- `n8n_create_workflow` — create from full workflow JSON.\n- `n8n_update_partial_workflow` — incremental diff ops (`{id, operations:[…]}`): addNode, updateNode, patchNodeField, addConnection, activateWorkflow, etc. Preferred for edits.\n- `n8n_update_full_workflow` — full replacement.\n- `n8n_autofix_workflow` — auto-fix common issues.\n- `n8n_deploy_template` — deploy a template to the instance.\n\n**Validate** (necessary, not sufficient — always pair with the antipattern scan)\n- `validate_workflow` — full JSON in, errors\u002Fwarnings\u002Ffixes out. Node types here are **LONG form** (`n8n-nodes-base.set`).\n- `n8n_validate_workflow` — validate a deployed workflow by `{id}` (no node JSON to inspect).\n\n**Inspect & lifecycle**\n- `n8n_get_workflow` — fetch a workflow (full \u002F structure \u002F active \u002F filtered \u002F minimal). Use it to verify `connections` after edits; `mode=\"filtered\"` + `nodeNames` reads one heavy node (e.g. long Code source) without pulling the whole workflow, which can truncate client-side.\n- `n8n_list_workflows` — list\u002Ffilter (search before duplicating logic).\n- `n8n_delete_workflow`, `n8n_workflow_versions` (history\u002Frollback), `n8n_instances` (multi-instance accounts only: list\u002Fswitch the target instance — see `n8n-multi-instance`), `n8n_health_check` (returns the resolved `instanceName`).\n\n**Test & run**\n- `n8n_test_workflow` — runs real nodes (Code, HTTP, DB writes, sends all fire). Ask the user before running when side effects exist.\n- `n8n_executions` — list\u002Finspect executions. **There is no `execute_workflow` tool.**\n- `n8n_evaluations` — read evaluation test runs (n8n ≥ 2.30): list runs, aggregated metrics, per-case results. Read-only — runs are started from the n8n editor, not the API; a 403 indicates denied access: inspect actual version, scopes and policy before proposing any credential replacement.\n\n**Data, credentials, audit**\n- `n8n_manage_datatable` — Data Table CRUD, filtering, dry-run.\n- `n8n_manage_credentials` — credential CRUD + `getSchema` discovery.\n- `n8n_audit_instance` — security audit (hardcoded secrets, unauthenticated webhooks, error-handling gaps).\n\n> **Node-type form trap:** `get_node` \u002F `validate_node` take SHORT form (`nodes-base.set`);\n> workflow JSON inside `validate_workflow` \u002F `n8n_create_workflow` uses LONG form\n> (`n8n-nodes-base.set`). Mixing them is a common, silent mistake — see `n8n-mcp-tools-expert`.\n\n## The protocol, in order\n\n1. Recognize the matching skill from the index and **invoke it before the first MCP call**.\n2. Skim `tools_documentation` once per session to refresh the tool surface if you're unsure.\n3. `get_node` before configuring any node — read the live schema, don't assume.\n4. Build \u002F edit, then **`validate_workflow` before activating** and **`n8n_get_workflow` after** to check `connections`.\n5. Surface any drift you notice (missing tool, changed parameter, diverging behavior).\n\n## When in doubt\n\n- **Can't find a workflow the user built in the UI?** The most common cause is per-workflow\n  MCP access being off. Ask them to open it in n8n, go to Settings, and enable MCP access.\n- **User says it's broken?** Believe them. Re-check parameters against `get_node`, trace\n  data references, inspect the execution. See `n8n-validation-expert`.\n- **No skill fits and the task is non-trivial?** Ask before guessing.\n\nThese are opinionated best practices, not laws. Disagree with a call? It's all markdown —\nedit the skill.\n\n## Example\n\n```yaml\nrequest: Build a webhook that validates input, calls an API, and returns structured errors.\nspecialists: [n8n-workflow-patterns, n8n-node-configuration, n8n-error-handling]\nsequence:\n  - inspect the target instance and live node schemas\n  - build and validate the graph\n  - preview side effects and obtain approval\n  - write changes, fetch the saved workflow with n8n_get_workflow, and revalidate\n  - activate and test only after approval\n```\n\n## Limitations\n\n- The router describes a moving n8n MCP surface; live tool schemas and the target instance override stale examples.\n- Availability of lifecycle, credential, evaluation, and multi-instance tools depends on server version and permissions.\n- Routing to a specialist skill does not authorize mutations, executions, activation, deletion, or credential changes.\n\nA missing companion skill or Skill tool is a disclosed prerequisite gap, not permission to invent one. Upstream hooks are not installed by this catalog source. Do not update the skill pack or instance automatically merely because drift is observed. Per-item execution, item linking and binary\u002Ftool boundaries depend on node mode\u002Fversion; validate the actual data shape with controlled fixtures.\n",{"name":5,"risk":30,"author":51,"source":52,"license":14,"date_added":53,"description":7,"source_repo":54,"source_type":33,"license_source":55},"Romuald Czlonkowski","https:\u002F\u002Fgithub.com\u002Fczlonkowski\u002Fn8n-skills\u002Ftree\u002Fmain\u002Fskills\u002Fusing-n8n-mcp-skills","2026-07-21","czlonkowski\u002Fn8n-skills","https:\u002F\u002Fgithub.com\u002Fczlonkowski\u002Fn8n-skills\u002Fblob\u002Fmain\u002FLICENSE","7bf2279c8a65758319526a721d5c4b75683aec9c","skills\u002Fantigravity-using-n8n-mcp-skills",3,"https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections","https:\u002F\u002Fgithub.com\u002Fboisenoise","2026-11-13 14:20:47",{"source":8,"skillName":5,"commands":63,"prompt":73,"zipAvailable":74},[64,67,70],{"tool":65,"command":66},"npx","npx skills add boisenoise\u002Fskills-collections --skill using-n8n-mcp-skills",{"tool":68,"command":69},"bunx","bunx skills add boisenoise\u002Fskills-collections --skill using-n8n-mcp-skills",{"tool":71,"command":72},"pnpm","pnpm dlx skills add boisenoise\u002Fskills-collections --skill using-n8n-mcp-skills","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-using-n8n-mcp-skills\u002FSKILL.md",true,[],[77,106,126,151,170,193],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":81,"licenseFileUrl":82,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":46},"01M6WNH92BHVFXHGPDZCPJ0AG0","web-access","Use Treg for public web or platform data only when existing search, browser and connected tools cannot cover the task, with explicit cost and data boundaries.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-web-access\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-web-access\u002FSKILL.md",[],[86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,30,101,102,103,104,105],"web","access","web access","official","development","browser","search","data","Tools","read","fetch","only","youtube","free tools","platform","free","cover","normal","when","2026",{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":81,"licenseFileUrl":110,"sourceHtmlUrl":111,"categories":112,"keywords":114,"publishedAt":46},"01M6WNF9XAYAB2CZDDJBAKNM93","treg","Use the Treg CLI or MCP catalog to discover, price and call authorized external tools with team-scoped credentials and a user-approved budget.","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-treg\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-treg\u002FSKILL.md",[113],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[108,23,115,44,89,90,38,94,116,117,118,119,120,121,122,30,123,124,125,28,105],"cli","Budget","credentials","team","catalog","use","call","discover","external tools","with","scoped",{"skillNo":127,"name":128,"nameZh":6,"description":129,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":81,"licenseFileUrl":130,"sourceHtmlUrl":131,"categories":132,"keywords":138,"publishedAt":46},"01M6WN93MEAZ4E41DYAHJRPHQT","recruit","Turn a job description into an evidence-linked candidate shortlist through Treg, with job-related ranking and optional authorized business contact enrichment.","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-recruit\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-recruit\u002FSKILL.md",[133],{"categoryNo":134,"categoryName":135,"taxonomyType":136,"taxonomyTypeDesc":137},"01JBSEEDCAT000000000000038","人力资源","PROFESSION","适用职业",[128,44,89,38,37,139,140,141,142,143,30,144,145,146,124,147,148,149,150,28,108,105],"email","enrichment","business","evidence","phone","ranking","post","job description","for","person","candidate","reason",{"skillNo":152,"name":153,"nameZh":6,"description":154,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":81,"licenseFileUrl":155,"sourceHtmlUrl":156,"categories":157,"keywords":158,"publishedAt":46},"01M6WN8R5RXSMHM9B4D9FAFX42","rea-growth","Analyze a company’s public growth and content through Treg, distinguish observations from hypotheses, and produce an evidence-linked playbook within an approved budget.","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-rea-growth\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-rea-growth\u002FSKILL.md",[],[159,160,161,44,89,38,162,163,37,164,116,165,166,167,142,30,168,169,28,108,105],"growth","rea","rea growth","produce","content","playbook","marketing","analyze","public","observations","company",{"skillNo":171,"name":172,"nameZh":6,"description":173,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":81,"licenseFileUrl":174,"sourceHtmlUrl":175,"categories":176,"keywords":177,"publishedAt":46},"01M6WN2EVE3RQRGWAKBT4S7YT2","make-ugc","Create original AI UGC-style product videos through Treg: research hooks, approve a licensed presenter and voice, generate clips, add captions and report costs.","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-make-ugc\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-make-ugc\u002FSKILL.md",[],[178,179,44,180,89,181,38,182,183,184,185,186,30,187,188,189,190,191,192,28],"make","make ugc","research","create","Video","Captions","ads","short","hooks","head","style","niche","trending","talking-head","approve",{"skillNo":194,"name":195,"nameZh":6,"description":196,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":81,"licenseFileUrl":197,"sourceHtmlUrl":198,"categories":199,"keywords":200,"publishedAt":46},"01M6WN10ARAA63Y8K1YNGXJ2RM","lead-signals","Find and qualify public buying signals through Treg, rank fitting business accounts and optionally enrich authorized business contact information.","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-lead-signals\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-lead-signals\u002FSKILL.md",[],[201,202,203,44,89,38,204,205,141,206,207,30,208,209,210,211,212,213,214,28],"signals","lead","lead signals","how","find","ready","as","how to","qualify","people","information","enrich","changes","funding"]