The Ultimate n8n TemplatesLibrary & Marketplace

Discover 7000+ premium n8n templates with AI-powered generation. The largest n8n templates marketplace enabling anyone to have a running workflow in 5 minutes

Start AI Generation Browse Templates

Or browse our extensive n8n templates collection. Try the AI generator to create custom n8n templates instantly.

12320+

Templates

50+

Integrations

50k+

Downloads

Latest n8n Templates

Freshly updated automation workflows to keep your n8n stack current

View All

Summarize Google Reviews into monthly owner digests with Claude and Supabase

Quick overview Pulls Google Business Profile reviews, classifies each one with Claude, stores them in Supabase, and emails the owner a monthly plain-English digest via Outlook. Every count, disagreement and trend is computed in code, never by the model, so the report cannot invent findings. How it works Runs manually (test set, live reviews, or location lookup) or on a monthly schedule to start a reporting cycle. Fetches Google Business Profile reviews for the configured location (or loads built-in test reviews) and normalizes them into a consistent structure. Reads previously stored classifications from Supabase and keeps only reviews that have not been classified before. Sends each new review to Anthropic Claude for theme and sentiment classification, validates the JSON and quotes against the original text, and upserts the classifications into Supabase. Combines stored and newly classified reviews, then computes theme counts, severity, “real split” disagreements, staleness, and a 24‑month rating trend entirely in code. Pulls the last saved report from Supabase to determine whether this run is a full, delta, or quiet report and builds a digest prompt (or generates a quiet-month digest without AI). Produces a final digest, renders it into branded HTML, sends it via Microsoft Outlook, and saves the report snapshot back to Supabase for next month’s comparison. Setup Create the Supabase tables (review_classifications and review_reports) and add a Supabase API credential, then replace YOUR_PROJECT_REF in the Supabase REST URLs. Add Google Business Profile OAuth2 credentials and set YOUR_GBP_ACCOUNT_ID and YOUR_GBP_LOCATION_ID in the Google Business Profile requests. Add an Anthropic credential for the Claude model used to classify reviews and write the digest. Add Microsoft Outlook credentials and update the To/CC/BCC recipients used for the digest email. Update the business_name and location_id in the run configuration to match the location you want to report on, then enable the Monthly Run trigger when you are ready. Additional info Why the AI never counts Most AI review summarizers hand the whole pile of reviews to a language model and ask it to summarize. That is how you get invented findings, softened complaints, and quotes no customer ever wrote. This template works the other way around. The model classifies one review at a time and writes the final prose, but every count, every disagreement and every trend is calculated in code from stored rows. The model turns finished facts into sentences. It is never the source of a fact. Three decisions worth knowing before you adapt it: Each review is classified once and stored. Language models are not reproducible even at temperature 0, so re-asking gives you slightly different counts each run. Classify once, save, then count rows forever after. Re-runs are deterministic and cost almost nothing. Every quote is checked against the source in code. A model will reorder the clauses of a real review and hand it back as a verbatim quote. Quotes that do not match the original text are dropped; the theme and sentiment they carried are kept. A disagreement needs proportional balance, not just counts. Thirty-two positive mentions against four negative is a consensus with outliers, not a split. Publishing that under "where customers disagree" misleads the owner. Full guide, including why most months should stay silent: https://docs.google.com/document/d/1o3DhkJV9yXyKwop6O7GZJyn6u7b4nvY1cjuDokPJo_4/edit Questions or help getting it running: support@priscgroup.com Built by PRISC Group. Automate. Relentlessly. Ruthlessly.

BeginnerManual Trigger

by Pedro Olavarria

Verify billing-ready completion documents with OpenRouter and Google Sheets

Quick overview This workflow ingests proof-of-delivery and completion documents from Gmail or a webhook, extracts key fields with an OpenRouter vision model, reconciles them against Google Sheets dispatch data, archives evidence to Google Drive, and routes items to an automatic Billing Ready queue or a human Review Queue. How it works Triggers when a new unread Gmail message with attachments arrives or when a document is posted to a webhook endpoint. Splits incoming attachments into individual PDF/image items, generates a traceable document key, and sends each file to OpenRouter (e.g., Gemini) to extract structured POD fields as strict JSON. Normalizes the AI response and reconciles the extracted dispatch reference against the Dispatches, POD Register, and Billing Ready tabs in Google Sheets to detect matches and duplicates. Scores the evidence (readability, confidence, signature presence, and dispatch match), assigns a status of Billing ready, Needs review, or Duplicate, and uploads the original document to Google Drive for archiving. Appends a full audit record to the POD Register in Google Sheets, then either adds billing-ready items to the Billing Ready tab or logs exceptions to the Review Queue and emails the reviewer via Gmail. Runs every 15 minutes to read Review Queue decisions in Google Sheets, appends approved items to Billing Ready once, and updates the Review Queue row with the final review status. Runs every weekday morning to compare Dispatches to Billing Ready and emails each owner (or the reviewer) a cash-risk digest of late jobs that still lack billable evidence. Setup Add credentials for Google Sheets, Google Drive, and Gmail, and configure an HTTP Header Auth credential for the OpenRouter API request. Update the configuration values in the workflow (Google Sheet ID, Drive folder ID, reviewer email, thresholds, and the review queue URL) to match your environment. Create the required Google Sheets tabs named Dispatches, POD Register, Review Queue, and Billing Ready with the expected headers (including Dispatch Reference, Scheduled Delivery Date, and Invoice Amount). In Gmail, create and apply a dedicated label/filter for POD intake and ensure the trigger monitors only that label and downloads attachments. If using the webhook intake, copy the webhook URL from n8n and configure your source app to POST PDF or image files to it.

Publish weekly AI social videos with Airtable, Claude, Sora, Cloudinary, and Buffer

Quick overview This workflow runs weekly to pick a fresh video topic from Airtable, generate a short caption with Anthropic Claude and a vertical Sora video via OpenAI, upload the clip to Cloudinary for a public URL, and schedule the post to LinkedIn and Instagram through Buffer. How it works Runs every week on a schedule (Monday at 17:00 in the workflow timezone). Reads all active topics from an Airtable Topics table and fetches the 14 most recent entries from an Airtable Reels history table. Compares available topics with recently used ones, randomly selects a topic that has not appeared in the last 14 reels, and stops if none are available. Sends the selected topic to the Anthropic Messages API (Claude) to generate a short Dutch caption and extracts the plain text for reuse. Uses OpenAI Sora to generate a 720×1280 vertical video clip based on the same topic. Uploads the generated video to Cloudinary to obtain a public video URL. Creates a video post in Buffer for LinkedIn and Instagram using the caption and Cloudinary URL, then logs the topic and caption back to Airtable to maintain the anti-repeat history. Setup Create Airtable credentials (personal access token) and replace the base ID and table IDs for the Topics and Reels tables. Ensure Airtable has a Topics table with fields Topic (text) and Active (checkbox) and a Reels table with a Created time Date field plus Topic and Post fields. Add an Anthropic API credential and customize the Claude prompt in the request body to match your brand voice and rules. Add an OpenAI API credential with access to Sora and adjust the video prompt and model selection if needed. Add Cloudinary credentials for video uploads. Add Buffer credentials and set your Buffer organization ID plus the LinkedIn and Instagram channel IDs used for publishing.

BeginnerManual Trigger

Serve a notes web app via webhooks and n8n Data Tables

Quick overview This workflow hosts a simple notes web app in n8n, serving a static HTML UI via a webhook and providing CRUD API endpoints backed by an n8n Data Table. No separate website, database, or hosting. Everything — the UI, logic and data — runs in the same workflow. How it works A manual run creates the "n8n-notes" Data Table (if it does not already exist) with columns for note title, body, color, and position. A GET request to the /notes webhook returns a static HTML page that acts as the notes UI. The UI calls the GET /notes-list webhook to fetch all notes from the n8n Data Table and display them in the browser. When a note is added from the UI, the POST /notes-create webhook inserts a new row into the Data Table and returns the result. When a note is edited or reordered, the PUT /notes-update webhook updates the matching Data Table row by id and returns the updated record. When a note is deleted, the DELETE /notes-delete webhook removes the matching Data Table row by id and returns the deletion result. Setup Run the manual trigger once to create the "n8n-notes" Data Table with the required columns. Activate the workflow and copy the production URL for the GET /notes webhook, then open it in a browser to load the UI. If you serve the UI from a different origin, ensure your environment allows cross-origin requests (the API webhooks enable CORS with allowedOrigins set to *).

BeginnerManual Trigger

Create weekly social visuals from OpenAI ideas with Canvora and Slack

Quick overview This workflow runs every Monday and uses OpenAI to generate a social post concept, then sends it to the Canvora API to create on-brand visuals in selected formats and posts the finished image links to a Slack channel for review. How it works Runs every Monday at 9am on a scheduled trigger. Sets campaign parameters like topic, desired output formats, optional language, and optional Canvora brand kit ID. Uses OpenAI to write a single, specific social post concept based on the configured topic. Sends the concept to Canvora to generate visuals in the requested formats (and applies language/brand settings when provided). Polls Canvora for generation status until it completes or a timeout threshold is reached. If generation succeeds, sorts the outputs and posts a Slack message with the file URLs and a Canvora review link; otherwise, it posts a failure/timeout notice to Slack. Setup Add an OpenAI API credential and select the model you want to use for generating the post concept. Create a Canvora account, generate an API key, and configure an HTTP Header Auth credential named X-API-Key with your Canvora key for the Canvora HTTP requests. Add a Slack credential and set the target channel (for example, #content) where the review or failure messages should be posted. Update the campaign settings (topic, comma-separated formats, and optional language/brandId) and adjust the schedule time if needed. Requirements - An OpenAI API key (or swap the node for Anthropic/Gemini — any text model works) A free Canvora account – canvora.ai, free credits included, no card required; API keys on all plans (Integrations → API Keys) A Slack workspace for the review channel Customization Change the topic, formats (100+ available via the Canvora formats API), language (150+ generated natively), or brand kit in one Set node Swap Slack for LinkedIn/Buffer nodes to go fully automatic Additional info Example output Real visuals produced by this exact workflow during testing – the AI wrote the concept, Canvora designed both:

Beginner

Bridge two-way SMS conversations between Android and Slack with Relayion

Quick overview This workflow uses Relayion and Slack to mirror inbound SMS messages into a Slack channel and let teammates reply in a Slack thread to send an SMS back to the original sender, adding a ✅ or ❌ reaction to confirm whether the outgoing text was sent. How it works Triggers when Relayion receives an inbound SMS message. Formats the SMS content and sender phone number into a Slack message and posts it to a configured Slack channel. Triggers when a new message is posted in the configured Slack channel. Verifies the Slack message is a threaded reply from a human (not a new top-level post and not a bot message). Fetches the thread root message from Slack, extracts the original sender phone number, and uses the threaded reply text as the outbound SMS body. Sends the SMS reply via Relayion and reacts to the Slack reply with a ✅ on success or ❌ if the send returns an error. Setup Create and connect a Relayion account with a paired Android device, and enable "Include Body" on the Relayion inbound webhook so SMS text is included. Create a Slack app/bot, add Slack OAuth credentials in n8n including the Signing Secret (Slack app → Basic Information → App Credentials), and grant the bot permissions to read the target channel and write messages and reactions. Invite the bot to your target Slack channel (/invite @YourAppName), or Slack API calls will fail with channel_not_found. Replace REPLACE_WITH_SLACK_CHANNEL_ID in both the Set Slack Channel ID step (used for posting inbound SMS) and the Slack trigger's Channel field (used for capturing replies). Activate the workflow, then copy the Slack trigger's Production webhook URL (not the Test URL) and paste it into your Slack app's Event Subscriptions Request URL field. Requirements A Relayion account with at least one paired Android device. A Slack workspace where you can create and install an app. Customization Edit the message format in Prepare Slack Message Text, or swap the reactions used in Post Success Reaction / Post Failure Reaction. Additional info This workflow uses Relayion (relayion.com) to connect an Android device as the SMS gateway. You'll need a Relayion account with at least one paired device before setting this up. Relayion ships natively in n8n's two most recent releases; on older versions, install the community node n8n-nodes-relayion from the Community Hub instead (self-hosted n8n only, not available on n8n Cloud).

Detect Stripe payment anomalies with Groq, Supabase, Slack, and Google Sheets

Quick overview This workflow runs hourly to read Stripe transaction logs from Google Sheets, normalize and load them into Supabase, then uses Groq (OpenAI-compatible chat completions) to detect anomalies and, when found, records incidents in Supabase and posts an alert to Slack while logging errors back to Google Sheets. How it works Runs every hour on a schedule. Reads raw Stripe-like transaction rows from a Google Sheets worksheet and normalizes fields (for example converting cents to USD and parsing risk scores). Inserts the cleaned transactions into a Supabase table for analytics. Sends the inserted transaction data to Groq’s chat completions API with a prompt to return an anomaly result as strict JSON. Parses the Groq response into structured fields and checks whether an anomaly is flagged. If an anomaly is true, writes an incident record to a Supabase incident_logs table and posts an alert message to a Slack channel. If Supabase, Groq, or Slack steps error, appends an error entry (including node name, severity, and transaction_id) to an error_logs sheet in Google Sheets. Setup Connect Google Sheets OAuth2 credentials and set the spreadsheet and worksheet IDs for the raw input sheet and the error_logs sheet. Connect Supabase credentials and ensure the analytics_data and incident_logs tables exist with columns matching the fields used (for example transaction_id, amount, risk_score, anomaly_type, severity, ai_label, and record_id). Add your Groq API key (or replace the Authorization header) and confirm the model name and endpoint URL are correct for your Groq account. Connect Slack OAuth2 credentials and select the target channel for anomaly alerts.

BeginnerManual Trigger

Route law firm review requests with Twilio SMS, Google Reviews and email

Quick overview This workflow uses webhooks, Twilio SMS, SMTP email, and a Bar-Compliance Guardrail sub-workflow to request client ratings 48 hours after matters close. It routes replies so 4–5 star clients get a Google Reviews link, while 1–3 star clients receive a private feedback form and trigger firm alerts. How it works Receives a matter-close event via a webhook from your practice management system. Normalizes the payload, verifies the matter is actually closed and a client phone number exists, and stops if the event is not eligible. Builds a rating-request SMS from project variables and waits 48 hours before sending. Runs the message through the Bar-Compliance Guardrail to check opt-outs and log the outbound message, then sends the rating request via Twilio and emails the firm a confirmation. Receives the client’s inbound Twilio reply via a second webhook, extracts a 1–5 rating (ignoring opt-outs and non-rating texts), and routes based on the score. For 4–5 ratings, runs a compliance check and texts the Google Reviews link; for 1–3 ratings, runs a compliance check, texts a private feedback form link, and emails the firm an immediate alert. Setup Create and connect Twilio credentials in n8n, and configure your Twilio number’s “When a message comes in” webhook to POST to the workflow’s /webhook/review-reply URL. Create and connect an SMTP email credential, and set project variables for FIRM_EMAIL and FIRM_FROM_EMAIL so firm notifications send correctly. Set project variables for FIRM_NAME, FIRM_TWILIO_NUMBER, FIRM_GOOGLE_REVIEW_URL, and FIRM_FEEDBACK_URL to populate the outbound SMS content. Set up the Bar-Compliance Guardrail workflow and add its workflow ID to the GUARDRAIL_WORKFLOW_ID project variable so opt-out checks and compliance logging run before every message. Copy the /webhook/review-request production URL into your practice management system webhook settings and ensure it sends matter status, client name, and client phone (plus matter identifiers) on closure events. If self-hosting, use Postgres (not SQLite) so the 48-hour wait can resume reliably after restarts.

Beginner

Why Choose Us?

AI-Powered n8n Templates

GPT-4 powered intelligent engine that generates custom n8n templates from simple descriptions

Premium Quality n8n Templates

Every n8n template is tested and verified to ensure reliability and practical automation value

One-Click Import

Support one-click import to n8n, start using immediately

Ready to Get Started?

Start using AI to generate n8n templates now, or explore our comprehensive n8n templates library with 7000+ proven workflows

Start AI Generation Browse Templates

Summarize Google Reviews into monthly owner digests with Claude and Supabase

BeginnerManual Trigger

by Pedro Olavarria