Code Workflows
1.006 Ergebnisse — ausschließlich quellenverknüpfte n8n-Referenzen
Capture real estate leads with Google Sheets, Gmail, and Slack
Quick Overview This workflow captures real estate property inquiries via a webhook, saves the lead to Google Sheets, sends an auto-reply email through Gmail, and posts a notification to a Slack channel before returning a JSON confirmation to the website. How it works Receives a POST request from your website form through a webhook endpoint. Extracts and standardizes the lead details (name, email, phone, property ID, and message) from the incoming request. Appends the inquiry details to a Google Sheets CRM spreadsheet. Sends an acknowledgement email to the prospect using Gmail with the referenced property details. Posts a new-lead alert to your agent team in Slack. Returns a JSON response (for example, { "status": "received" }) to confirm the submission was accepted. Setup Connect Google Sheets OAuth credentials and update the target spreadsheet and sheet tab used to store new leads. Connect Gmail OAuth credentials and customize the subject/body of the auto-reply message. Connect Slack OAuth credentials and choose the channel where agent notifications should be posted. Copy the webhook URL from the webhook trigger and configure your website inquiry form to send a POST request with n
Create work4all incoming invoices from Microsoft Outlook supplier emails
Quick Overview This workflow polls a Microsoft Outlook folder for new supplier emails, sends each message to a companion n8n sub-workflow that creates an incoming invoice in work4all, and then categorizes the email (green/yellow/red) and emails errors via Outlook. How it works Runs every minute on a schedule. Fetches all emails from a specified Microsoft Outlook folder that are not already categorized as Red or Green, downloading any attachments. Sends each email to a companion sub-workflow that extracts invoice data from attachments and creates the incoming invoice in work4all. If the sub-workflow returns errors, sends an error notification email via Microsoft Outlook and categorizes the original message as Red. If no errors occur, categorizes the message as Green when booking is clean, or as Yellow + Green when a supplier was created or an account/tax key was set automatically. Setup Import and publish the companion workflow "Create a work4all incoming invoice from email attachments using AI" and select it in the Execute Workflow step. Add Microsoft Outlook credentials with permission to read the target mailbox and send emails. Update the Outlook folder ID to monitor and ensure t
WScrape business emails from Google Maps to Google Sheets
Quick overview This workflow takes a list of Google Maps search queries, extracts candidate business website URLs from the search results, visits each site, scrapes email addresses from the page content, and appends cleaned, deduplicated emails to Google Sheets fully automated, no manual research needed. How it works A manual trigger fires with a pinned list of Google Maps search queries, each representing a location and business type combination. A query loop iterates through each query, launching a sub-workflow execution per query and applying a configurable wait between executions to reduce request bursts. The sub-workflow sends an HTTP GET to the Google Maps search results URL for that query and reads the raw HTML response. A code node extracts all URLs from the HTML using a regex pattern, after which a filter node removes known system domains such as Google, gstatic, schema.org, and Wix internals, and a deduplication node removes repeated URLs before visiting. A URL loop processes each candidate business website one at a time, fetching the page HTML and passing it into the email processing flow. A code node applies a regex to the fetched page content to extract email-shaped st
WFetch and parse Amazon SP-API reports into structured TSV rows
Quick Overview This workflow manually requests an Amazon Selling Partner (SP-API) report, polls until it is ready, downloads the report document, optionally decompresses it if it is GZIP, and parses the TSV contents into one n8n item per row. How it works Starts when you run the workflow manually. Uses Login with Amazon (LWA) to exchange your refresh token, client ID, and client secret for an access token. Calls the Amazon SP-API Reports API to create a report for the configured report type and marketplace. Polls the Amazon SP-API until the report processing status is DONE (or errors if it fails or times out). Fetches the report document metadata and downloads the report file from the provided URL. If the document is GZIP-compressed, decompresses the file and then parses the TSV into structured JSON items, outputting one item per row. Setup Create and authorize Amazon SP-API (Login with Amazon) credentials, then fill in the refresh_token, client_id, and client_secret values in the Config step. Set the correct SP-API endpoint region (EU/NA/FE), report_type, and marketplace_ids values in the Config step. If you want to store or route results, add downstream nodes after the parsed row
Monitor website changes with PolyDoc screenshots and email alerts
Quick Overview This workflow checks a website URL every 6 hours, detects content changes by hashing the normalized HTML, and when a change is found it uses PolyDoc to capture a full-page screenshot and emails the PNG as an attachment. How it works Runs every 6 hours on a schedule. Sets the target URL to monitor and fetches the page HTML with an HTTP request. Normalizes the HTML (removing scripts/styles/comments), hashes it, and compares it with the previous run stored in workflow static data. If the hash changed, PolyDoc captures a full-page PNG screenshot of the URL. Sends an email with the screenshot attached and the monitored URL in the subject and body. Setup Update the monitored website URL in the Settings step. Add your PolyDoc API credentials to the PolyDoc screenshot step. Configure an SMTP email credential and set the to/from email addresses in the email step.
Detect competitor launch signals from ads with OpenAI and Google Sheets
Quick Overview This workflow runs weekly to scan competitor ad copy from Meta, Google Ads, and LinkedIn via Adyntel, detects newly emerging terms, uses OpenAI to assess launch signals, and records results in Google Sheets while sending a Slack alert when a launch signal is detected. How it works Runs every week on a schedule (Monday) to start the competitor monitoring cycle. Reads competitors marked as Pending from Google Sheets and processes them one by one. For each competitor domain, pulls current ads from Meta, Google Ads, and LinkedIn using Adyntel and combines the results. Extracts and deduplicates ad titles and body copy, then loads the competitor’s previously known terms from Google Sheets. Extracts candidate new terms from this week’s ad copy, filters for terms that recur across multiple ads, and decides whether there are meaningful new terms to analyze. If meaningful new terms exist, sends the context to OpenAI to classify the terms and determine whether a product launch signal is present, then appends the signal record and the newly classified terms to Google Sheets. If no meaningful new terms exist, appends baseline terms from this week’s ad titles to Google Sheets to p
Sync Shopify customers with Cegid Y2 on create or update
Quick overview This workflow receives Shopify customer create/update webhooks and syncs the customer record to CEGID Y2 by creating the customer when missing or updating the existing customer when CEGID reports a duplicate. How it works Receives a POST webhook from Shopify when a customer is created or updated. Builds a CEGID Y2 customer payload with identifiers, tax/currency details, and the default store/workspace settings. Formats the customer address and chooses whether to send individual or company contact details based on whether a company name is present. Sends the assembled payload to CEGID Y2 to create the customer. If CEGID returns a “customer already exists” error, extracts the existing CEGID customer ID from the error message and sends a PATCH request to update that customer in CEGID. If the create request fails for any other reason, stops the workflow and surfaces the CEGID error. Setup In Shopify, create a customer webhook for create/update events and point it to this workflow’s webhook URL, matching the allowed shop domain. Add CEGID Y2 HTTP Basic Auth credentials and ensure the API user has permission to create and update customers. Update the CEGID API base URL, wo
WRoute real estate buyer and seller leads with Claude and Google Sheets
Quick Overview This workflow hosts an n8n lead-capture form, uses Anthropic Claude to score and classify real estate inquiries, then routes ready leads to Gmail and Google Sheets while logging early-stage leads to a separate Google Sheets tab. How it works Receives a new submission from an n8n Form trigger with contact details, intent, area, budget, timeline, financing status, and notes. Normalizes the submitted fields (for example trimming strings, lowercasing email, and adding a timestamp) for consistent downstream processing. Sends the normalized lead details to the Anthropic Messages API (Claude) to return a strict JSON classification, summary, timeline band, financing readiness, recommended agent role, and score. Parses the Claude JSON response, clamps the score to a 1–10 range, and calculates whether the lead is “ready” (score 7). If the lead is ready, sends a formatted Gmail alert to the agent and appends the lead to the “Active Leads” tab in Google Sheets. If the lead is not ready, appends the lead to the “Nurture Leads” tab in Google Sheets. Returns a confirmation message to the form submitter after the lead is routed. Setup Create an Anthropic HTTP Header Auth credential
WRoute law firm client intakes with Claude and Google Sheets
Quick Overview This workflow hosts an n8n intake form for a law firm, sends each submission to Anthropic Claude for classification and qualification, logs the result to Google Sheets, emails the intake team for qualified matters via Gmail, and returns a neutral confirmation page to the submitter. How it works Receives a client intake submission through an n8n hosted form. Normalizes the submission into consistent fields (contact details, matter type, incident date, and narrative). Sends the normalized intake to Anthropic Claude to classify practice area, assess urgency and time sensitivity, flag conflict-check needs, and decide whether the matter is qualified. Parses Claude’s JSON response and merges the analysis back into the intake record. If the matter is qualified, sends an HTML alert email via Gmail to the intake team and appends the intake details to the “Qualified Intakes” tab in Google Sheets. If the matter is not qualified, appends the submission and decline reason to the “Declined Intakes” tab in Google Sheets. Returns a confirmation message to the submitter stating the intake was received and that no attorney-client relationship has been formed. Setup Create an Anthropic
Analyze skill gaps for target jobs with BrowserAct, LinkedIn and GPT-4o-mini
Quick Overview This workflow collects a student’s skills and target role via an n8n Form, scrapes top LinkedIn job postings with BrowserAct, and uses OpenAI GPT-4o-mini to generate a skill gap report with courses and a 90-day plan, saving results to Google Sheets and emailing them via Gmail. How it works Receives a student submission from an n8n Form with name, email, target role, current skills, experience level, location, and weekly learning hours. Validates the inputs, converts the skills list into an array, and builds a LinkedIn job search URL for the chosen role and location. Uses BrowserAct to open the LinkedIn job search in a real browser and extract text from up to 20 job postings. Cleans and normalizes the scraped job text and combines it with the student profile data. Sends the student profile and job-posting text to OpenAI GPT-4o-mini to extract in-demand skills, identify missing skills with priority, recommend three free courses, and generate a 13-week learning plan. Parses the model output into labeled sections, calculates matched and missing skill counts, and appends the full report as a new row in Google Sheets. Sends a formatted HTML email via Gmail to the student w
Collect and structure Kuaishou video comments with JustOneAPI
Quick overview Use this n8n workflow template to collect Kuaishou video comments with JustOneAPI. This template is for content researchers, marketing teams, community operations teams, analysts, and automation builders who want to collect structured comment data from a Kuaishou video inside n8n. How it works The workflow starts with a single configuration node where you add your JustOneAPI token, the Kuaishou video ID, and an optional pcursor value. It then requests the Kuaishou video comment endpoint, reads the returned root comments and sub-comment groups, and formats them into a structured comment collection. The final output includes comment counts, pagination information, normalized root comments, sub-comments grouped by root comment, debug information, and raw API responses for inspection and troubleshooting. The workflow leaves pcursor empty by default for the first request. You can use the returned nextPcursor value to continue from another page when supported by the API response. Setup Import the workflow into n8n. Open the Set API Request Parameters node. Add your JustOneAPI token. Replace the placeholder value for videoId. Leave pcursor empty for the first request, or ad
Draft and approve Gmail replies with OpenAI and CustomJS
Quick Overview This workflow pulls unread Gmail messages, generates draft replies with OpenAI, and publishes an approval dashboard via CustomJS. When you approve or edit a draft in the dashboard, it posts back to a webhook that sends the reply in Gmail and marks the original message as read. How it works Runs manually to fetch unread messages from Gmail. Filters out messages from common no-reply senders to avoid automated emails. Uses OpenAI (GPT-5) to generate a draft reply from the email subject, snippet, sender, and recipient. Compiles the original emails and AI drafts into a single HTML approval dashboard and publishes it as a CustomJS page. Receives an approval submission from the dashboard via an n8n webhook containing the edited reply text plus the Gmail message and thread IDs. Replies to the original Gmail message with the approved text and then marks the message as read. Setup Connect Gmail OAuth2 credentials for the Gmail nodes that read messages, reply, and mark messages as read. Add an OpenAI API credential and select the model you want to use for draft generation. Add your CustomJS credentials and confirm the target page name used to publish the dashboard. Set your n8n
CQualify LinkedIn leads and draft multi-step outreach with Airtable, Apify and Claude
Quick overview This workflow pulls unprocessed leads from Airtable, enriches them with LinkedIn profile, company, and post data via Apify, optionally scrapes the company website with Firecrawl, then uses Anthropic Claude to qualify leads and draft multi-step LinkedIn outreach messages, saving results back to Airtable. How it works Runs when you manually execute the workflow. Reads qualification and writing prompts from Airtable, then searches Airtable for leads where the “Réponse” and “Match” fields are empty. Iterates through each lead and uses Apify to fetch LinkedIn profile details, marking the Airtable record as “Likedin pas dispo” when the profile cannot be retrieved. For available profiles, uses Apify to fetch company details when a company LinkedIn URL exists and, if a website is available, uses Firecrawl to scrape the homepage and clean the returned markdown. Uses Apify to fetch recent LinkedIn posts for the lead and selects a relevant recent personal post URL to include in the enrichment dataset. Sends the consolidated lead, company, homepage, and post data to Anthropic Claude to decide whether the lead matches the qualification criteria, marking non-matching leads as “Fal
Draft and revise technical articles with OpenRouter in a content pipeline
Quick Overview This subworkflow is triggered by a parent content pipeline, uses OpenRouter (via an AI Writer Agent) to draft or revise a technical article from a brief, research notes, and optional reviewer feedback, and returns the updated pipeline state with the current draft and word count. How it works Receives input from a parent workflow containing the brief, research notes, and optionally a previous draft plus reviewer feedback. Sends the brief, research JSON, and any revision context to an AI Writer Agent backed by OpenRouter to generate a fresh draft or revise the prior draft. Parses the agent’s JSON response, extracts the draft text and word count (or calculates it if missing), and flags whether the output is a revision. Merges the extracted fields back into the original input and returns the updated state (including currentDraft) to the parent workflow. Setup Add an OpenRouter API credential and select it for the OpenRouter chat model used by the Writer Agent. Ensure the parent workflow passes the expected fields (for example brief, research, and optionally previousDraft and feedbackNotes) when calling this subworkflow. Update the Writer Agent system prompt if you need a
Score and critique content drafts with OpenRouter and LangChain
Quick Overview This subworkflow is called by a parent n8n pipeline to review a content draft against a provided brief using an OpenRouter chat model, returning structured scores, issues, and revision notes the parent can use to decide whether to iterate or accept the draft. How it works Receives the full pipeline state from a parent workflow execution, including the brief and current draft text. Sends the brief and draft to a LangChain Agent configured as an editorial “LLM-as-a-Judge” using an OpenRouter chat model. Produces a JSON review containing 1–10 scores for accuracy, tone, completeness, and clarity, plus an averaged overall score, issues list, and actionable revision notes. Parses the model output, falls back to a zero-score error review if parsing fails, and merges the review back into the original input object. Returns the enriched payload (original fields plus a review object) to the parent workflow for threshold-based decision-making. Setup Add an OpenRouter API credential and select the model you want to use in the OpenRouter chat model node. Ensure the parent workflow passes the expected fields (at minimum brief and currentDraft) when calling this subworkflow. Save th
Get Douyin user published videos and first video details with JustOneAPI
Use this n8n workflow to get published videos from a Douyin user and fetch details for the first video with JustOneAPI. Who’s it for This template is for creator research teams, marketing teams, creator operations teams, analysts, and automation builders who want to inspect a Douyin account’s published videos and collect the first video’s detail data in a reusable n8n workflow. What this workflow does The workflow starts from a Douyin secUid and sends a request to the User Published Videos V3 endpoint. It keeps the raw video list response, extracts video IDs from data.aweme_list, selects the first unique aweme_id by default, then requests video details with the Video Details V2 endpoint. The workflow returns both the selected video from the list and the detailed video data in a structured format, while also keeping raw outputs for inspection and troubleshooting. This makes it useful for account monitoring, video research, content archiving, creator analysis, and building downstream reporting workflows. What you need A JustOneAPI token A Douyin user secUid An n8n environment with HTTP Request node support Set up Import the workflow into n8n. Open the Prepare API and User Data node.
Search Douyin videos by keyword and get the first video detail with JustOneAPI
Use this n8n workflow to search Douyin videos by keyword and get the first video detail with JustOneAPI. Who’s it for This template is for creator research teams, content operations teams, marketing teams, analysts, and automation builders who want to search Douyin video content and collect the first matched video detail in a reusable format. What this workflow does The workflow starts from a Douyin search keyword and sends a request to the Douyin Video Search V4 endpoint. It keeps the raw search response, extracts the first available video ID from the returned search results, then sends a second request to the Douyin Video Details V2 endpoint. The workflow keeps both raw API responses for inspection and troubleshooting, and also converts the selected video detail into a cleaner structured output for downstream use. This makes it useful for content discovery, video research, creator analysis, campaign monitoring, competitor research, content archiving, and automated reporting workflows. What you need A JustOneAPI token A Douyin search keyword An n8n environment with HTTP Request node support Set up Import the workflow into n8n. Open the Prepare / Config node. Add your JustOneAPI to
Host an AI Gmail reply approval inbox with OpenAI and CustomJS
Quick overview Build super flexible and customizable Human-in-the-Loop (HITL) processes with n8n and CustomJS. Instead of letting AI reply autonomously, this workflow fetches data, drafts responses, and hosts interactive approval pages via CustomJS—ensuring full human quality control over your automations with optional custom domain hosting. How it works Trigger: Set to run manually (or scheduled on a cron job). Fetch Emails: Pulls unread messages from your Gmail inbox. Filter: Discards standard no-reply and notification addresses. AI Generation: OpenAI analyzes the email text and subject line to write a suggested reply. Build Dashboard: A Code node merges the dataset into a premium HTML template. Upsert Page: The CustomJS node hosts the generated HTML instantly. Setup Configure the Base URL: Open the Build Approval Page Code node, locate the configuration section (around line 22), and replace the placeholder with your actual n8n instance URL: Connect CustomJS: Add your CustomJS API token to your n8n to allow the workflow to automatically push and host the generated process pages. Activate Webhook: Ensure your n8n webhook node is set to "Production" so it can reliably receive the a
Get Taobao and Tmall product reviews with JustOneAPI
Get Taobao and Tmall product reviews with JustOneAPI Use this workflow to fetch product reviews for a specified Taobao or Tmall item and turn the review response into a structured output inside n8n. Who’s it for This template is for ecommerce researchers, marketplace operators, product analysts, customer feedback teams, and automation builders who want to review buyer feedback for a specific Taobao or Tmall product. What this workflow does The workflow starts manually and prepares all API and review parameters in one configuration node. It then sends a request to the Taobao/Tmall product review endpoint through JustOneAPI, stores the raw review response for debugging, and builds a structured review output from the returned data.comments array. The final output includes request metadata, page information, review summary counts, cleaned review records, review photos, appended reviews, buyer display information, SKU information from the reviewed item, sharing metadata, and the raw API response for review. How to set up Open Set API and Review Parameters Add your JustOneAPI token Replace TARGET_TAOBAO_ITEM_ID with the product item ID you want to inspect Optionally adjust orderType and
Search Taobao and Tmall products and get the first product detail with JustOneAPI
Search Taobao and Tmall products and get first product detail with JustOneAPI Use this workflow to search Taobao and Tmall products by keyword, extract product IDs from the returned search results, and fetch product detail data for the first selected product with JustOneAPI. Who’s it for This template is for ecommerce researchers, marketplace operators, product analysts, and automation builders who want to quickly inspect Taobao or Tmall product search results and retrieve one structured product detail record inside n8n. What this workflow does The workflow starts with a manual trigger and prepares all search inputs in one configuration node. It then searches Taobao and Tmall products by keyword, stores the raw search response for debugging, extracts item IDs from data.model.itemList, and uses the first selected itemId to fetch product details. The final output includes cleaned product information, image URLs, SKU summary data, SKU details, SKU property values, the original search source product, and the raw product detail response for review. How to set up Open Set API and Search Parameters Add your JustOneAPI token Update keyword Optionally adjust sort, tmall, startPrice, endPric
Reconcile Google Drive invoice PDFs with OpenAI, Sheets, Slack and Gmail
How it works Watches a Google Drive folder and triggers automatically when a new invoice PDF is uploaded Extracts raw text from the PDF and passes each invoice through an OpenAI powered agent that returns structured fields like vendor, amount, due date, and line items Fans the enriched data to three parallel outputs: a Google Sheets log, a Slack alert for overdue invoices, and a weekly summary email to Finance via Gmail Set up steps Connect Google Drive, Google Sheets, Gmail, Slack, and OpenAI credentials (~15 minutes total) Works best with text based PDFs; scanned invoices need OCR upstream of the extraction step Keep full setup details and prompt tuning tips in the sticky notes inside the workflow
Get Xiaohongshu keyword suggestions with JustOneAPI
Use this workflow to expand one Xiaohongshu keyword into structured keyword suggestions with JustOneAPI. It is useful for topic research, content planning, creator operations, search trend discovery, and downstream Xiaohongshu automations. How it works The workflow starts from one config node where you add your JustOneAPI token and the keyword you want to expand. It then: sends the keyword to the Xiaohongshu Keyword Suggestions endpoint returns the raw API response for debugging extracts structured suggestion items from the response separates note suggestions and goods suggestions outputs a cleaned result that can be reused in other workflows What you can do with it You can use this template to: discover related Xiaohongshu note search keywords identify goods-oriented suggestion terms collect keyword ideas before note search or note detail workflows send cleaned keyword suggestions into Sheets, Airtable, Notion, databases, or AI enrichment steps Setup Import the workflow into n8n Open the Prepare API and Keyword Inputs node Paste your JustOneAPI token Replace the sample keyword with your own query Run the workflow Output The workflow returns: the raw JustOneAPI response a cleaned s
Resolve Xiaohongshu share links to final URLs with JustOneAPI
This workflow resolves Xiaohongshu share links into their final redirect URLs so you can extract the real destination before sending it to later steps in your automation. It is useful for content research, link normalization, note routing, and building workflows that depend on the final Xiaohongshu page URL instead of the original short share link. How it works Open the Config node and paste a Xiaohongshu share link. Add your JustOneAPI token in the authentication field. Run the Share Link Resolution request node. The workflow returns the resolved redirect URL, which you can pass to downstream steps for parsing, storage, or further analysis. What you can do with it Expand Xiaohongshu short share links into final destination URLs Normalize inbound links before saving them to databases or sheets Route resolved URLs into note analysis or scraping workflows Build automations that start from copied share links Setup Import this workflow into n8n Open the Config node Paste your Xiaohongshu share link Add your JustOneAPI token Execute the workflow to get the final redirect URL
Generate client-ready workflow diagrams from sales call transcripts with Claude
Who it's for This workflow is for automation agencies and n8n consultants who conduct discovery calls with prospects and want to instantly turn conversation transcripts into polished, client-ready workflow diagrams — without manual canvas work. How it works A consultant pastes a sales call transcript into a form trigger. A first AI agent (Claude) parses the transcript and extracts structured workflow briefs — one per identified business process — with titles, tools, logic, and step-by-step descriptions. A code node splits the output into individual workflow items, one per identified process. A second AI agent generates a complete n8n workflow JSON for each brief, using French business-oriented node names and proper canvas positioning. A code node validates and parses the generated JSON to ensure structural integrity. A third AI agent clusters nodes into logical business groups and generates canvas layout coordinates and sticky note annotations. A fourth AI agent renames all nodes with clear, descriptive French labels following a consistent naming convention. All renames and layout changes are applied, and the finalized workflow is published directly to an n8n instance via the API.