By n8n-io
Design, build, and debug production-grade n8n workflows with Claude — from AI agents and file handling to error management, credential security, and exposing workflows as MCP tools for coding agents.
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 / audio / video) via the native LangChain provider nodes. Triggers on any `@n8n/n8n-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 / video / audio generation, or any multi-turn or one-shot LLM behavior.
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 skill. Triggers on "file", "image", "PDF", "attachment", "binary", "upload", "download", chat trigger with files, agent tool that needs a file, vision/multimodal, or any handling of non-JSON file data.
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."
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.
Use when working with n8n's built-in Data Tables, designing schemas, inserting/updating/upserting 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.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
n8n's MCP makes the connection. n8n Skills set the standard.
Built by the n8n team to pair with n8n's instance-level MCP server. Your coding agent can now build and edit workflows through the MCP, and the skills enable it to get it right the first time.
What's inside:
An n8n instance (any plan, Cloud or self-hosted) with the instance-level MCP server enabled. See n8n's MCP setup guide.
Pick your platform:
Inside Claude Code, run these one at a time:
/plugin marketplace add n8n-io/skills
/plugin install n8n-skills@n8n-io
Restart Claude Code. Skills load automatically.
Run these one at a time:
codex plugin marketplace add n8n-io/skills
codex plugin add n8n-skills@n8n-io
Restart Codex. On first run, Codex prompts to review and trust the plugin's hooks, approve them so the SessionStart, PreToolUse, and PostToolUse reminders fire. Skills load automatically.
Each coding agent has its own skill format. Follow your platform's docs for installing skills
skills.sh handles a few popular platforms via npx. From your project folder:
npx skills add n8n-io/skills
Compatibility varies by agent. Check skills.sh for support on your specific platform.
AGENTS.mdThis project uses n8n. When working with workflows, nodes, expressions, or
the n8n MCP tools, always start by loading the `using-n8n-skills` meta-skill
and follow its routing into the matching capability skill before acting.
The plugins ship a SessionStart hook that loads the entry-point skill for you. Plain skill installs don't have that hook, so the snippet is what cues your agent to start every n8n task by loading
using-n8n-skills.
| Skill | When it activates |
|---|---|
n8n-workflow-lifecycle | Starting, designing, organizing, or finishing a workflow |
n8n-subworkflows | Anything reusable, multi-step builds |
n8n-extending-mcp | Need capabilities the MCP doesn't have |
n8n-expressions | Writing {{}}, $json, $node |
n8n-node-configuration | Configuring any node |
n8n-code-nodes | Custom logic, Code node consideration |
n8n-loops | Loops, batching, paginated APIs |
n8n-agents | LangChain Agent node, tools, system prompts, structured output |
n8n-error-handling | Webhook APIs, production workflows |
n8n-credentials-and-security | Auth, API keys, tokens |
n8n-binary-and-data | Files, images, attachments, vision |
n8n-data-tables | Data Tables: schemas, dedup, persistent state |
n8n-debugging | Things break |
A 14th meta-skill, using-n8n-skills, is loaded by the SessionStart hook in plugins and routes your agent to the right capability skill on every n8n task.
Each skill is a markdown file. Frontmatter tells the agent when to load it. The SessionStart hook routes to the right one on every n8n task; PreToolUse hooks pull the matching skill back into context before high-impact MCP calls. It's all just markdown. Disagree with a call? Fork it.
See CLAUDE.md, the contributing guide for humans and AI agents alike. Open an issue first. We don't accept PRs that haven't been discussed in an issue.
Looking for contributors: feature parity plugins for other coding agents (Cursor, OpenCode, etc.). The skills are just markdown, the work is wrapping them so they activate in those harnesses the way they do in Claude Code.
Apache 2.0. See LICENSE.
npx claudepluginhub n8n-io/skills --plugin n8n-skillsA growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Superpowers Plus core skills library for Claude Code: planning, execution routing, TDD, debugging, and collaboration workflows
Memory compression system for Claude Code - persist context across sessions