Communityn8ngithub.com

n8n-agent-builder

Build, deploy and manage AI agents on n8n. Use when the user wants an AI agent, chatbot or assistant on n8n - with its own chat page or website widget, on WhatsApp, Telegram, Slack or as an API - connected to any LLM (OpenAI, Claude, Gemini, Groq, Mistral, Ollama, OpenRouter or any OpenAI-compatible API), optionally answering from their documents (RAG), using tools (Google Sheets, Calendar, Gmail, web search, Shopify, WooCommerce, HubSpot, databases, MCP), or routing to specialist sub-agents. Also for updating, testing, listing or deleting such agents.

¿Qué es n8n-agent-builder?

n8n-agent-builder is a Claude Code agent skill that build, deploy and manage AI agents on n8n. Use when the user wants an AI agent, chatbot or assistant on n8n - with its own chat page or website widget, on WhatsApp, Telegram, Slack or as an API - connected to any LLM (OpenAI, Claude, Gemini, Groq, Mistral, Ollama, OpenRouter or any OpenAI-compatible API), optionally answering from their documents (RAG), using tools (Google Sheets, Calendar, Gmail, web search, Shopify, WooCommerce, HubSpot, databases, MCP), or routing to specialist sub-agents. Also for updating, testing, listing or deleting such agents.

Compatible con✓Claude Code✓Codex CLI~Cursor✓Gemini CLI
npx skills add https://github.com/jrnoorbaloch/n8n-agent-builder/tree/HEAD/skills/n8n-agent-builder

Installed? Explore more n8n skills: ashtonfeliciano/n8n-workflow-engineer, ashtonfeliciano/n8n-evaluations-runner, caiqueDeOliveira-dev/homelab · View all 6 →

Preguntar en tu IA favorita

Abre un nuevo chat con esta habilidad de agente ya precargada.

Documentación

n8n Agent Builder

Turns a plain-language request ("make a WhatsApp bot for my clinic that books appointments, using Claude") into working n8n workflows, deploys them through the n8n public API, and hands the user the links.

Everything runs through one script (Python 3.10+, standard library only):

python3 <skill-dir>/scripts/n8n_agent.py <command> ...

Run it from the user's project folder so it finds their .env. Spec files and the <spec>.deployed.json state files live there too.

fileread when
references/spec.mdwriting a spec - every field, tool and channel option
references/channels.mdsetting up WhatsApp, Telegram, Slack, webhook or website chat
references/providers.mdchoosing an LLM / embeddings provider, OpenAI-compatible URLs
references/troubleshooting.mdany error
templates/*.jsonready-made agents - start from one whenever it fits

Workflow

1. Connection

python3 scripts/n8n_agent.py check

If it fails, the user needs a .env (copy of .env.example) with N8N_BASE_URL (root URL, e.g. https://me.app.n8n.cloud) and N8N_API_KEY (n8n → Settings → n8n API). Ask them to create it themselves. Never ask for secrets in chat and never print them. If n8n is unreachable from here, still build the spec and use build to hand over importable JSON files.

2. Pick a starting point

Run templates and pick the closest one; copy it with new <template> -o <file>.json --name "..." [--provider ...]. Templates exist for: restaurant orders, clinic appointments, real estate leads, e-commerce support, tutor, HR FAQ, website lead capture, chat-with-documents, research, multi-agent front desk. If nothing fits, write a spec from scratch (see references/spec.md).

3. Ask only what's missing

Keep it to one short round of questions. Typical gaps:

  • business details for the {PLACEHOLDERS} in the template (name, hours, prices...)
  • which LLM provider [default openai / gpt-4o-mini]
  • where it should live: website chat (default), WhatsApp, Telegram, Slack, API
  • IDs the tools need (Google Sheet ID, calendar ID) - or leave the placeholder and tell them to set it in the editor
  • existing n8n credential IDs (shown in the credential's URL in n8n). Put them in credential_id or, for tools/channels, in the top-level credentials map ({"googleSheetsOAuth2Api": "12"}) so one ID covers every node of that type.

Write a strong system_prompt: role, business facts, what to collect, when to use each tool (by node name), what never to do, reply language, tone, escalation path.

4. Validate, then deploy

python3 scripts/n8n_agent.py validate agent.json     # offline check + warnings
python3 scripts/n8n_agent.py deploy agent.json --activate

validate/deploy list unfilled placeholders and every node still missing a credential. Fix placeholders before deploying. Missing credentials are fine: the workflow is created inactive and the user selects credentials in the editor, then activates (or re-runs update --activate).

deploy saves IDs and links to agent.deployed.json. Deploy order is handled (sub-agents first). A spec with knowledge on a persistent store also creates a separate "knowledge upload" workflow.

5. Test

python3 scripts/n8n_agent.py test agent.json                 # runs spec "tests"
python3 scripts/n8n_agent.py test agent.json -m "Hi" -m "Menu?"

Works for chat and webhook channels once active. For WhatsApp/Telegram/Slack ask the user to message the bot.

6. Hand over

Tell the user, briefly: what the agent does, its model, channels, tools; the links from the deploy output (editor, chat, upload form, API); what they still must do (credentials, Meta/Telegram/Slack setup from references/channels.md, upload documents); and that the chat is public unless chat_auth is set.

For their own website: set "chat_mode": "embedded", update, then ui agent.json -o chat-site [--mode bubble] [--color ...] [--files] makes a branded chat site/widget (right-to-left support, voice input, file upload). It can be dragged onto Netlify Drop or embedded with two script tags.

Studio (visual alternative)

If the user prefers a visual tool, or wants to let non-technical teammates build agents, point them to the Studio: python3 <skill-dir>/studio/server.py (or python studio.py in the repo) opens a local web app with chat-to-agent, a form builder, a live workflow diagram, deploy/update/delete and a test chat. It reads the same .env. Online version (design and download only): https://jrnoorbaloch.github.io/n8n-agent-builder/studio/

Changing and managing agents

taskcommand
change prompt/model/tools/channelsedit spec, then update agent.json [--activate] (keeps chat URLs)
list agentslist (--all for every workflow)
backup a workflowexport <id> -o file.json
pause / resumedeactivate <id> / activate <id>
token use and costusage <id> --price-in 0.15 --price-out 0.6 ($ per 1M tokens)
removedelete agent.json (everything deployed from it) or delete <id> - always confirm with the user first; pass -y only after they agree
add a credential via APIuser sets LLM_API_KEY env var, then create-credential --provider anthropic --name "Claude" (also telegram)

Rules

  • Secrets only in .env or n8n credentials - never in specs, chat, or git. .deployed.json holds webhook URLs: keep it out of git (already in .gitignore).
  • Public chats spend the user's LLM credits: suggest chat_auth for internal bots.
  • postgres_query tool: insist on a read-only database user.
  • Prefer a persistent knowledge store (supabase/pinecone/qdrant/pgvector) for anything beyond a demo; memory store is wiped on n8n restart.
  • Don't claim something works until test passes or the user confirms.

Skills relacionados

ashtonfeliciano/n8n-workflow-engineer

Build, debug, and harden n8n workflows. Use when the user is editing n8n workflow JSON, debugging silent failures, working with Code nodes, Telegram / Gmail / HTTP Request nodes, scheduled triggers, paired-item tracking, dedup with static data, or doing bulk operations via the n8n REST API. Covers v2.x UI specifics. Not for non-n8n automation.

community

ashtonfeliciano/n8n-evaluations-runner

Build and run zero-API-cost logic test suites for n8n workflows. Use when adding test coverage to filter logic, scoring functions, validators, keyword lists, resume maps, or any pure-JS code-node logic. Outputs grouped pass/fail/pending report via Telegram. Run before AND after any logic change to catch regressions without burning API credits.

community

caiqueDeOliveira-dev/homelab

HomeLab Agent — Gerencia Home Assistant, ESP32 satellites, dispositivos Zigbee/Matter/Thread, automações físicas, cameras, sensores. Camada de decisão e execução no hardware (não orquestração de software = Automação/n8n).

community

hubgunter4-ops/experto-en-n8n-mcp

Guía a los desarrolladores a seleccionar y configurar herramientas y formatos de nodo del Protocolo de Contexto de Modelo MCP dentro de los flujos de trabajo de n8n. Proporciona orientación estructurada para integrar herramientas MCP.

community

hubgunter4-ops/configurador-de-nodos-n8n

Ayuda a configurar nodos de n8n con reglas de dependencia complejas y conexiones de IA. Agiliza la creación de flujos de trabajo automatizados gestionando dependencias de nodos intrincadas e integraciones de IA.

community

hubgunter4-ops/experto-en-validacion-de-n8n

Corrige errores de validación de n8n consultando un catálogo de errores integrado. Optimiza el proceso de depuración, permitiendo identificar rápidamente problemas y resolver problemas de configuración del flujo de trabajo.

community