N8n
Use when the user wants to build, debug, or extend an n8n workflow - generating workflow JSON from a description, scaffolding a custom TypeScript node, building an AI agent (LangChain cluster), iterating over items, writing Code-node JS, linting an existing workflow, diagnosing a failed execution, or driving a live n8n instance via REST.
Install
npx skills add AutomateLab-tech/n8n-mcp --skill n8ngit clone --depth 1 https://github.com/AutomateLab-tech/n8n-mcp.git /tmp/n8n-mcp
mkdir -p ~/.claude/skills
cp -r /tmp/n8n-mcp/. ~/.claude/skills/n8nPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# n8n
Pairs with the `@automatelab/n8n-mcp` server. The server exposes 9 MCP tools; this skill tells you when to use which and where to load deeper context.
## Tool routing
Tool names use dot-notation: `node.*`, `workflow.*`, `execution.*` (renamed in v0.4.0 from `n8n_*`).
**Stateless tools** (work without any n8n instance):
- `workflow_generate` - plain-English description → workflow JSON. Detects AI-agent intent and emits a LangChain cluster.
- `node_scaffold` - description → single `INodeType` TypeScript file for a custom n8n package.
- `workflow_lint` - workflow JSON → list of issues (deprecated types, missing `typeVersion`, broken connections, AI Agent without `ai_languageModel`, IF v1 schema, etc.).
- `execution_explain` - failed/surprising execution JSON → diagnosis. Catches the #1 n8n pain point: items "silently disappearing" between nodes. Also flags unresolved `={{ ... }}` expressions and surfaces LLM token usage.
**Live-instance tools** (require `N8N_API_URL` + `N8N_API_KEY` env vars):
- `workflow_list` - paginate workflows; filter by active/tags/name.
- `workflow_get` - fetch a workflow by id. Pair with `workflow_lint` to audit deployed workflows.
- `workflow_create` - POST a generated workflow. Strips read-only fields. Workflow is created inactive.
- `workflow_activate` - flip active on/off.
- `execution_list` - browse executions; pass `includeData: true` for the full body. Pair with `execution_explain`.
Default chains:Details
- Skill name
n8n- Repository
- AutomateLab-tech/n8n-mcp
- License
- MIT
- Repo updated
- 22 October 2026
FAQ
What does the N8n skill do?
Use when the user wants to build, debug, or extend an n8n workflow - generating workflow JSON from a description, scaffolding a custom TypeScript node, building an AI agent (LangChain cluster), iterating over items, writing Code-node JS, linting an existing workflow, diagnosing a failed execution, or driving a live n8n instance via REST.
How do I install the N8n skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add AutomateLab-tech/n8n-mcp --skill n8n. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is N8n popular?
It lives in AutomateLab-tech/n8n-mcp, which has 15 GitHub stars and 0 forks.
Related skills
Tradegit
12rollingSirius/TradeGit
基于 GitHub 私有仓库的交易日志(trading journal)。用于记录每一笔交易及其理由、 导入券商流水、复盘历史盈亏。触发场景:用户说「记一笔交易 / 记录一下我买了 XXX / log this trade」、「导入 IBKR / 盈透 / 嘉信 / Schwab 的对账单」、「看看我过去 三个月的盈亏 / 哪笔亏得最多 / 复盘一下我的交易」、「我的持仓」、 或首次配置时说「安装/连接交易日志」。也在用户提到 trade journal、交易记录、 round trip、win rate、盈亏分析、R 倍数时触发。 仅负责记录、同步与盈亏计算;不下单、不提供投资建议、不生成图表或面板。
Desktop Controller
1224kchengYe/desktop-controller-skill
Universal desktop application controller for Windows. Automate any desktop app — send messages, click buttons, type text, take screenshots, and interact with native Windows applications. Use this skill when the user asks to: "control my computer", "automate desktop", "send a message on [any chat app]", "click on [something]", "type into [app]", "take a screenshot", "操控电脑", "自动化桌面", "给某某发消息", "打开某某软件", "截个屏", or any task involving interacting with Windows desktop applications. WeChat triggers: "send a WeChat message", "message someone on WeChat", "打开微信发消息", "给某某发微信", "微信发送", "微信发消息", "用微信发", "帮
Arcgram
13jovesun-lab/arcgram
Generate an interactive node-and-edge diagram as a single standalone HTML file (Arcgram v2). Triggers on: arcgram, interactive/architectural diagram, topology, node graph, flow diagram, system map, dependency graph, workflow diagram, knowledge map, 'show me how X connects to Y', 'visualize this workflow', 'make this a topology', 'build a diagram of this'. Prefer for any system map, dependency graph, topology, or workflow picture even if interactivity wasn't asked for; on a follow-up 'make it inline' / 'show me' / 'render in chat', stay within Arcgram (Mode 1/2), don't switch tools.
Scholarship Finder Planner
14OmarZen/scholarship-navigator
Main entry point for finding and planning scholarships. Use whenever someone asks which scholarships they can get, whether they are eligible, how well they match (score), which papers they are missing, what to prepare and by when, or wants a tracker, plan, calendar or report. Covers 103 awards from Diploma to PhD (Chevening, Erasmus Mundus, DAAD, Stipendium Hungaricum, Fulbright, MEXT, GKS, CSC, Türkiye Burslari, KAUST, Commonwealth...), scholarships to study in your own country without travelling (Egypt, Turkey, Indonesia, Mexico, Nigeria, Africa in-country...), awards for women, and individu
Fable Harness
13AAO-SH/fable-harness
Use when installing or updating a project-local Fable Harness for Codex, Claude Code, or compatible agent workflows; when a workspace needs AGENTS.md or CLAUDE.md boot instructions, .codex/.claude/.agents templates, decision traces, semantic notes, native loop governance, loop state, event logs, checklist evidence, subagent briefs, memory closure checks, or protected TDD audit rails.
Orca Orchestration Dev
12nergury74/orca-orchestration-dev
Orca ADE의 오케스트레이션(멀티 에이전트 감독)으로 웹앱·앱 기능을 개발하는 워크플로우 스킬. 환경 조사 → 계약 확정 → Task DAG 설계 → 병렬 구현 → 통합 → 점검 순서로 진행하며, 파일 소유권 배정·결정 게이트·독립 검증 절차를 강제한다. "오케스트레이션으로 개발", "오케스트레이션으로 만들어줘", "Orca로 병렬 개발", "멀티 에이전트로 구현", "여러 에이전트에 나눠서 개발", "워커 나눠서 구현", "PRD로 Task 쪼개서 개발" 같은 요청이 있으면 반드시 이 스킬을 사용한다. 사용자가 PRD·기획서를 주면서 구현을 맡기거나, 여러 작업을 동시에 진행하며 감독·완료 추적을 원한다고 말할 때도 이 스킬을 쓴다. Orca 오케스트레이션 명령을 실행하기 전에는 항상 이 스킬을 먼저 읽을 것.
Browse the most popular Claude skills, all productivity & notes skills, or write your own with the skills generator.