Browse 12,955 Workflows

By Muhammad Bin Zohaib

Quick overview Paste a public YouTube video URL and use Gemini to mine real viewer comments for recurring questions, problems, objections, tutorial requests, content opportunities, and product or service ideas. How it works Enter a public YouTube video URL, choose how many comments to analyze, and select relevance or time-based ordering. The workflow uses the YouTube Data API v3 to retrieve the video's title, channel, views, likes, comment count, and public comment threads. Comments and available replies are cleaned, low-value or spam-like comments are filtered, duplicate text is removed, and each useful comment receives a stable evidence ID such as C001. Gemini analyzes only the collected comments to identify recurring questions, problems, complaints, feature requests, objections, tutorial requests, purchase intent, and other audience signals. The workflow converts the strongest signals into actionable content ideas, hooks, and potential product or service opportunities while keeping one-off observations separate from repeated patterns. A complete report is rendered directly in the n8n form, including an executive summary, audience signals, engagement context, content opportunities, product or service opportunities, caveats, and clickable links back to the original YouTube comments. Setup Create a Google Cloud project and enable the YouTube Data API v3 in Google Cloud Console. Create an API key under APIs & Services → Credentials, then add it to an n8n HTTP Query Auth credential using: Name: key Value: your YouTube Data API key Attach that credential to both Get Video Details and Get YouTube Comments. Connect a Google Gemini Chat Model credential to the AI Agent. You can use a Gemini model available through its free tier, or swap the chat model for another compatible provider or model available to you. Requirements An n8n instance with access to the Form, HTTP Request, Code, AI Agent, and Google Gemini Chat Model nodes. A Google Cloud project with the YouTube Data API v3 enabled and a YouTube API key. Customization Change the comment limit, relevance/time ordering, minimum comment length, junk-comment filters, evidence ranking logic, AI prompt, and report sections to fit your research use case. Replace the Google Gemini Chat Model with another compatible n8n chat model or provider when needed. You can also extend the workflow with additional outputs such as Google Sheets, email, Slack, or a database. Additional info No paid scraper is required. The workflow reads public YouTube data directly through the official YouTube Data API and analyzes the cleaned evidence with the connected AI model. The workflow is designed to be evidence-first: AI-generated signals and opportunities are tied back to actual comment evidence IDs, helping users distinguish repeated audience demand from isolated comments. An n8n automation workflow template by Muhammad Bin Zohaib.

By Guillaume Duvernay

Quick overview Give an AI coding agent one authenticated webhook for structured LLM batches. The agent prepares prompts and JSON schemas in a script; n8n processes the first 50 calls in parallel, returns ordered results, and records who used the service. How it works The Webhook accepts a POST request with an X-API-Key header and a calls array. Each call contains systemPrompt, userMessage, a JSON-encoded jsonSchema string, and an aiMode of small or big. Use one mode per request. Check Auth* looks up the token in the users Data Table. Unknown tokens receive HTTP 401. For accepted requests, Insert log stores the user's email and the full submitted calls payload, including prompts, schemas, and modes. Prepare Calls* restores the request body after authentication, and Split Calls creates one item per call. Limit to 50 passes the first 50 items. It silently drops any extras, so clients should split larger jobs and check result counts. Basic LLM Chain* processes the retained items in parallel. Model Selector routes small to GPT 6 Luna and big to Gemini 3.8 Flash. Structured Output Parser applies each call's schema. Adjust the chain's batch size and delay to match provider rate limits. Aggregate Responses* collects the results. Respond to Webhook returns ordered {query, output} entries, one per processed call. query echoes the submitted input; callers should inspect each output and handle item-level failures. Setup Create a users Data Table with string columns email and auth_token. Create a logs Data Table with string columns user and log in the same n8n project. Add one users row per person. For this example, generate a unique 12-character alphanumeric auth_token with a cryptographically secure random generator and deliver it privately. Your organization can use its own token system instead. In Check Auth, select the imported workflow itself. In Get team member, select the users table and filter on auth_token using ai_auth_key. In Insert log, select the logs table. Configure an OpenRouter credential in GPT 6 Luna and 3.8 Flash. If you replace either model or provider, reconnect the model nodes and verify the small and big rules in Model Selector. Publish the workflow and copy the production URL from Webhook. Give each user that URL and their personal token through a verified private channel. They store them as unquoted EXTERNALIZED_AI_URL=... and EXTERNALIZED_AI_API_TOKEN=... values in a local .env. Run one cheap test call, then a small batch. Check the JSON response, the 401 response for a bad token, and the logs table. Logs retain submitted prompts and source text; restrict table access and set an appropriate retention policy. Requirements An n8n instance with Data Tables, LangChain nodes, and a reachable production webhook. An OpenRouter account and credential, or replacement model credentials configured in the model nodes. A secure way to issue and privately deliver a personal token to each user. Customization Replace GPT 6 Luna and Gemini 3.8 Flash with other models or providers while keeping the small and big contract for callers. For per-call model selection, measured cost, reasoning effort, or other model types, replace the model branch with direct OpenRouter API calls. This is an extension to the two-model template. Replace the users table with your own identity store. A separate onboarding workflow could deliver tokens through a private Slack DM after verifying the requester's identity. Additional info jsonSchema is a JSON-encoded string, not a nested object. Send one aiMode per request. Limit to 50 silently drops extra calls, and individual calls may fail without a usable output. The response echoes inputs under query. The logs table stores all submitted calls, including those beyond the 50 processed items, with prompts and source text. Restrict access and retention. Model outputs and measured cost are not in the log. OpenRouter docs: https://openrouter.ai/docs/quickstart. An n8n automation workflow template by Guillaume Duvernay.

By SkipPlay

Quick overview This workflow generates long-form developer SEO articles using OpenAI, publishes them to a website API, and pings IndexNow for fast indexing, running either on a 2-day schedule or via an on-demand webhook. How it works Runs every 2 days on a schedule or receives an on-demand POST request via a webhook. Selects a predefined Suno API keyword/topic (or uses webhook-provided overrides) and prepares the article brief and target slug. Calls the OpenAI Chat Completions API to generate a structured JSON SEO article including markdown content and FAQs. Parses the AI output, computes word count, and generates Schema.org JSON-LD for TechArticle, FAQPage, and BreadcrumbList. Publishes the article payload (content, metadata, and schemas) to the sunoapi.top blog publishing endpoint if basic quality checks pass. Sends the published URL to the IndexNow API for near-instant search engine indexing and returns a JSON status response to the webhook caller. Setup Add an OpenAI API key (or compatible provider key) and replace the Authorization header value in the OpenAI HTTP request. Configure the publishing secret by setting the x-sync-secret header value expected by your https://sunoapi.top/api/blog/publish endpoint. If you use IndexNow, set your IndexNow key and keyLocation URL in the IndexNow request body and host the key file at that location. If triggering externally, copy the webhook URL for the POST /sunoapi-generate-content endpoint and configure the calling system to send optional topic/keyword override fields. An n8n automation workflow template by SkipPlay.

By Webz.io

Quick overview This workflow runs daily at 08:00 to search Webz.io news for multiple topics, uses OpenAI GPT-4.1-mini to curate a structured digest, posts the digest to Slack, and archives each selected story to Google Sheets. How it works Runs every morning at 08:00 based on the workflow timezone. Reads the digest configuration (topics list, lookback days, article count, and Slack channel) and splits it into one item per topic. For each topic, uses OpenAI GPT-4.1-mini to call the Webz.io news search tool and select up to five significant articles, returning structured fields (headline, publisher, why it matters, URL). Merges all topic results, removes duplicate URLs across topics, and formats a single Slack-ready digest message while building a per-story archive dataset. If there are no stories across all topics, the workflow stops without posting or archiving anything. If there are stories, posts the digest to the configured Slack channel and appends one row per story to Google Sheets. Setup Add an OpenAI credential to the OpenAI Chat Model node (or replace the model with another tool-calling chat model). Create a Bearer Auth credential with your Webz.io API token and attach it to the Webz.io news search node. Add a Slack credential with chat:write and channels:read, invite the bot to your target channel, and set the channel name in Digest settings. Add a Google Sheets OAuth credential, select the target spreadsheet and sheet, and ensure it has headers: date, topic, headline, publisher, why_it_matters, url. Update Digest settings with your comma-separated topics, lookback window, and article count, and set Workflow Settings → Timezone so the 08:00 schedule matches your local time. An n8n automation workflow template by Webz.io.

By Zvid

Quick overview For event organizers using self-hosted n8n: turn a Google Sheets calendar or Eventbrite events into branded vertical announcement, seven-day reminder and final-call videos. Zvid renders each due video, records completed links and provides a gated Watch video preview. How it works Run manually or on the daily 8am schedule. Config supplies branding, reminder timing, timezone offset and optional background music. Check the music URL before building the video. Unreachable or oversized music is disabled so the workflow can continue without it. Read the Google Sheets event calendar or the first 50 live events from the configured Eventbrite organization. Skip past events and events with no video due today. Choose the due video: a final-call reminder one day before the event, a seven-day reminder by default, or an initial announcement. Existing output cells or the Eventbrite send ledger prevent repeated videos. The default limit is one render per run. Build a vertical 1080×1920 Zvid project with event details, branding and optional music, then validate it with the Zvid node before submission. With the default dryRun=false, submit a paid render and poll for completion within bounded limits. Optional dryRun=true saves a draft only when the installed Zvid node supports Project → Create; released v0.1.8 does not support that optional branch. After completion, write Status and the matching PromoUrl, Video7d or Video1d cell in Google Sheets, or update the Eventbrite ledger. The gated Watch video step downloads completed media; open Binary → data → View. The finished URL remains available if downloading fails. Setup Use self-hosted n8n. Before configuring Zvid credentials, install @zvid/n8n-nodes-zvid from Settings → Community nodes; a workspace owner/admin may need to install it. Create an API key at https://app.zvid.io/api-keys and select a Zvid credential with base URL https://api.zvid.io on every Zvid node. For Google Sheets, connect OAuth credentials and select the same spreadsheet and tab in both Sheets nodes. Add these headers: EventName, DateISO, Venue, City, TicketUrl, ImageUrl, Status, PromoUrl, Video7d, Video1d. Enter EventName and a future ISO date/time in DateISO. Leave Status, PromoUrl, Video7d and Video1d empty for a new event. In Config, select source=sheet, set branding and timezoneOffsetHours, and keep maxRendersPerRun=1 for the initial test. Leave todayOverride empty for the real date; use it only for a deliberate rehearsal. Past events are skipped, and reminders run on their configured due day. For the optional Eventbrite source, set source=eventbrite and eventbriteOrgId, then select an HTTP Bearer Auth credential on Fetch Eventbrite. This template reads the first 50 live events and tracks completed sends in workflow data. Use licensed, publicly accessible images and music within your Zvid plan limits; the default fallback image is 1080×1440. Run the manual trigger and inspect Watch video before activating the daily schedule. dryRun=false spends Zvid credits; the tested default video used about 14 credits. Draft mode requires Project → Create support, absent from released v0.1.8. Requirements Self-hosted n8n with @zvid/n8n-nodes-zvid installed; a Zvid API key and rendering credits; Google Sheets OAuth credentials and an event calendar, or an Eventbrite bearer token and organization ID; rights to all supplied media. Customization Change brand colors, fonts, event copy, fallback image, music and firstReminderDays in Config. Set timezoneOffsetHours for your event calendar. Keep the single-render default while testing, then adapt throughput deliberately to your Zvid plan. Additional info Social publishing is not included. To intentionally render a test event again, clear only that row’s Status and the matching output cell; past events still remain ineligible. The scheduled and manual render path uses dryRun=false. Optional draft previews require a Zvid node version with Project → Create support; released v0.1.8 does not expose it. Full setup and field reference: https://github.com/Zvid-io/zvid-n8n/blob/master/workflows/event-countdown-videos.md Zvid help: https://zvid.io/contact. An n8n automation workflow template by Zvid.

By DataDrifter

Quick overview This workflow runs nightly to inventory your WordPress plugins and themes via the WordPress REST API, checks them against the WPScan vulnerability database within your API quota, stores scan history in an n8n Data Table, and emails a report of any applicable issues. How it works Runs every night at 03:30 on a schedule. Validates the scan settings (site URL, email addresses, and per-run lookup limit) and fetches the remaining daily API quota from WPScan. Retrieves the installed plugins and themes from the WordPress REST API and loads prior check timestamps from an n8n Data Table. Selects which components to scan based on the available quota, prioritizing active components and those checked least recently. Queries WPScan for each selected component and filters vulnerabilities to only those that affect the installed version. Upserts the results (including last checked time and findings) into the wpscan_scan_history Data Table. Builds a plain-text report (including items not checked or lookup failures) and sends it by SMTP email when configured to do so. Setup Create an n8n Data Table named wpscan_scan_history with String columns component, kind, slug, version, last_checked, findings and a Number column affected_count. Add a WordPress Application Password for an administrator user and configure an n8n HTTP Basic Auth credential for the WordPress REST API requests. Create a WPScan API token and configure an n8n Header Auth credential with Authorization: Token token=YOUR_TOKEN. Add an SMTP credential for the email node and set the allowed sender address. Update site_url, notify_email, notify_from, and (optionally) wp_core_version, max_lookups_per_run, and alert_only_on_findings in the Scan settings before activating the workflow. Requirements A WordPress site with the REST API reachable from n8n A WordPress administrator account (for the Application Password) A WPScan API token (free tier: 25 lookups a day) n8n with Data tables, and an SMTP server for the report Customization Set wp_core_version to include WordPress core in the scan Set alert_only_on_findings to true to email only when something is found Raise max_lookups_per_run if you have a paid WPScan plan Change the time in the schedule trigger Additional info This is a known-vulnerability check, not a malware scanner, firewall or penetration test. The Application Password is administrator-level because listing plugins requires it; revoke it when you stop using this workflow. Full setup guide: https://datadrifter.io/wordpress-plugin-vulnerabilities-wpscan-api/. An n8n automation workflow template by DataDrifter.

By Takahiro Shimizu

Quick overview This workflow turns a LINE Official Account into a plant care assistant that can analyze plant photos and answer follow-up questions, using Google Gemini for AI responses and n8n Data Tables to store plant profiles, observations, conversation history, and the user’s language preference. How it works Receives an incoming LINE Messaging API webhook event and routes it based on whether the message is an image or text. For image messages, downloads the image from the LINE content API and loads the user’s active plant, preferred language, and recent conversation history from n8n Data Tables. Sends the image and context to Google Gemini to identify the plant (or defer when uncertain) and assess visible health symptoms, possible causes, and care advice. If the image matches the active plant, keeps the existing plant identity; if it is a new plant, upserts a plant profile and updates the user’s active plant; if uncertain, asks for a better diagnostic photo without changing the active plant. Stores the image-based analysis as a plant observation in an n8n Data Table and replies to the user in LINE with a formatted summary and confidence. For text messages, loads the user’s active plant, recent observations, and conversation history, then asks Google Gemini to generate a contextual reply. Saves the user and assistant messages to conversation history, updates the saved preferred language only when the user explicitly requests a language change, and replies in LINE. Setup Create a LINE Official Account, enable the Messaging API, and configure the webhook URL to point to the workflow’s production webhook path (plantcare-line-webhook). Add a LINE Messaging API channel access token as an HTTP Header Auth credential in n8n and use it for the LINE content download and reply requests. Add a Google Gemini (Google PaLM) API credential for the two Gemini nodes used for image analysis and chat responses. Create four n8n Data Tables named plant_users, plants, plant_observations, and conversations with the columns used in the workflow, and select the correct table IDs in each Data Table node. An n8n automation workflow template by Takahiro Shimizu.

By MADIAD

Quick overview This workflow auto-replies to Facebook Page comments using an OpenRouter-powered AI Agent with Postgres chat memory and a Supabase vector knowledge base, while keeping that knowledge base synced from PDFs in Google Drive (new, updated, and deleted files). How it works Receives Meta webhook requests and returns the hub.challenge value to complete Facebook webhook verification when required. Extracts the incoming Facebook comment details, ignores non-comment events, and skips comments authored by the Page itself to prevent reply loops. Fetches the original Facebook post message via the Facebook Graph API to provide context for the reply. Uses an AI Agent backed by an OpenRouter chat model, Postgres chat memory (per post and user), and a Supabase vector-store retrieval tool to draft a concise response. Posts the AI-generated text back to Facebook as a reply to the specific comment via the Facebook Graph API. Monitors Google Drive folders for PDF creations, updates, and “trash” events, then extracts text, generates OpenAI embeddings, and inserts or deletes matching vectors in Supabase to keep the knowledge base in sync. Setup Create and connect Facebook Graph API credentials, subscribe your Facebook App/Page to the webhook, and configure Meta to call this workflow’s webhook URL. Add an OpenRouter API credential and select the model you want the AI Agent to use. Add Postgres credentials and ensure the database is reachable for storing chat history sessions. Add Supabase credentials, create a documents table for vector storage, and ensure the vector store configuration matches your embeddings. Add Google Drive OAuth credentials and update the folder IDs to the Drive folders you want to watch for new PDFs, updated PDFs, and trashed files. An n8n automation workflow template by MADIAD.

By WIKIIII

Quick overview This workflow reads video prompts from Google Sheets, generates an AI video using Google Veo3 via fal.run, saves the file to Google Drive, creates an SEO-friendly title with OpenAI, uploads the video to YouTube via upload-post.com, and writes the video and YouTube links back to the sheet. How it works Starts manually and fetches rows from Google Sheets where the VIDEO column is empty. Builds a generation prompt from the sheet data and submits it to fal.run (Google Veo3) to create a video. Waits and polls fal.run for the video request status until it returns COMPLETED. Retrieves the completed video URL from fal.run and uses OpenAI (gpt-4o-mini) to generate a YouTube-optimized title from the original prompt. Downloads the video file, uploads it to Google Drive, and updates the originating Google Sheets row with the fal.run video URL. Sends the video file and generated title to upload-post.com to upload it to YouTube, then updates the same Google Sheets row with the resulting YouTube URL. Setup Add Google Sheets OAuth2 credentials and set the target spreadsheet/document and sheet tab used for reading and updating rows. Create a fal.ai account, add an HTTP Header Auth credential with Authorization: Key , and ensure it is selected on the Veo3 HTTP requests. Add OpenAI credentials for the title-generation step and select the model you want to use. Create an upload-post.com API key, add an HTTP Header Auth credential with Authorization: Apikey , and replace YOUR_USERNAME in the upload request with your upload-post profile username. Set the Google Drive OAuth2 credential and choose the destination folder where uploaded videos should be stored. An n8n automation workflow template by WIKIIII.

By Pavel Zamorev

Quick overview This workflow runs daily (or manually) to check Apple App Store search rankings for a configured keyword list using SerpApi, then appends each keyword’s rank, result count, group, and date to a Google Sheets tab for ongoing ASO tracking. How it works Runs on a daily schedule or via a manual trigger for testing. Builds a queue of keywords and settings (including SerpApi API keys, App Store app ID, locale, and Google Sheets IDs) from an in-workflow configuration. Processes keywords one at a time and waits 1 second between requests to reduce the chance of hitting rate limits. Queries the SerpApi Apple App Store Search API for each keyword and requests up to the configured number of results. Parses the SerpApi organic results to find your app’s position by matching the configured App Store ID, or records a value like ">N" (or "ERROR") when not found or when the API returns an error. Appends one row per keyword to Google Sheets with keyword, group, position, apps (results count), and date. Setup Create a SerpApi account and add one or more SerpApi API keys in the workflow configuration (replacing the placeholder values) and enable at least one keyword group. Set your numeric Apple App Store app ID, storefront country/language, and desired result limit in the configuration. Create a Google Sheets spreadsheet with a tab named position and columns keyword, group, position, apps, and date, then paste the spreadsheet ID into the configuration. Connect your Google Sheets OAuth2 credentials in the Google Sheets append step. Run the workflow once with the manual trigger to confirm rows append correctly, then enable the daily schedule if desired. An n8n automation workflow template by Pavel Zamorev.

By youssef farhan

Quick overview This workflow runs every morning to scrape new Spitogatos.gr property listings via Apify, logs each new listing (including agent phone details and key property metrics) to Google Sheets, and sends a single Telegram message summarizing the listings that match your price-per-m² or price-cut criteria. How it works Runs every day at 08:00 on a schedule. Builds the Spitogatos.gr search parameters (locations, listing type, property type, price/size filters, and time window) from the configured values. Uses Apify (Spitogatos.gr Scraper actor) to fetch listings first published within the selected period. Skips listings that were already sent in previous executions by deduplicating on the listing ID. Formats each new listing into a structured record with price, area, €/m², rooms, floor, year built, neighbourhood/region, agent/agency details, phone, and the listing link. Appends every formatted listing as a new row in Google Sheets. Filters the listings to keep only deals that match your max €/m² threshold or have a price cut (when enabled), then aggregates them into a single payload. Sends one Telegram message (up to 20 listings) with clickable links and key details, noting if more results are available in Google Sheets. Setup Create a free Apify account (https://apify.com/?fpr=youssef) and connect it in the Apify node with OAuth or an API token. The workflow runs the Spitogatos.gr Scraper actor (ID: aAohRNwnunh3U1L6d). Connect Google Sheets credentials and paste your target Google Sheet URL into the workflow configuration (the value used for the Google Sheets document). Create a Telegram bot with @BotFather, connect Telegram credentials in n8n, and set your target Telegram chat ID in the workflow configuration. Update the search filters (locations, listingType, propertyType, priceMax, areaMin, roomsMin, postedWithin, and maxPages) and optionally set maxPricePerM2 and alertOnPriceCuts before activating the workflow. Requirements An Apify account (https://apify.com/?fpr=youssef), the free plan works. Google Sheets and a Telegram bot connected in n8n. Customization Set maxPricePerM2 (for example 2500) to be alerted only about listings under that price per square metre; use rent in listingType to track rentals instead of sales; add more areas in English or Greek, separated by commas; swap the Telegram node for Slack, Discord or Gmail. Additional info Area names work in English or Greek (Kolonaki, Kolonaki (Thiva), Glyfada), and the results carry the agency name, contact name and phone number, so you can call the agent directly. Skip listings already sent is n8n’s Remove Duplicates node keyed on the listing id, so a daily schedule never repeats a home. Actor page and full input docs: https://apify.com/fayoussef/spitogatos-scraper?fpr=youssef. An n8n automation workflow template by youssef farhan.

By Zvid

Quick overview This workflow runs daily (or on manual test) to turn the newest post from an RSS feed into a coordinated social kit using OpenRouter for copy and Zvid for rendering, producing a LinkedIn square video, an X teaser video, and an Open Graph share image. How it works Runs every day at 9am (or when triggered manually) and loads the workflow configuration values. Reads the configured RSS feed, picks the newest post, and stops if that post was already processed in a previous production run. Fetches the blog post page (with feed text as fallback), then sends the article text to OpenRouter to generate JSON copy for the LinkedIn video, X teaser, and Open Graph image. Checks the configured background music URL with an HTTP HEAD request and skips the audio track if it is unreachable or exceeds the size limit. Builds project JSON for each enabled asset, validates the payload and credit quote with the Zvid node, then follows the configured dryRun branch. Optional dryRun=true creates draft projects and returns editor links with a credit estimate. This branch requires an installed Zvid node version exposing Project → Create; AI calls may still incur charges. With the default dryRun=false, renders one asset at a time, retries explicit rate-limit rejections, and polls each job within the configured timeout. Run summary returns media links; the gated Watch video step opens completed videos and the share image for review. Setup Install @zvid/n8n-nodes-zvid from Settings → Community nodes before configuring credentials. A workspace owner/admin may need to install it. Create your Zvid API key at https://app.zvid.io/api-keys, then select a Zvid API credential with Base URL https://api.zvid.io on every Zvid node. Add an OpenRouter API credential for the OpenRouter Chat Completions request used to generate the kit copy. Update the Config values (feedUrl, brandName, domainOverride, brand colors/fonts, output toggles, durations, and musicUrl) to match your blog and branding. The template defaults to dryRun=false: running it spends Zvid render credits, and AI usage may charge separately. To preview drafts with dryRun=true, first confirm your installed Zvid node exposes Project → Create. Test manually, inspect every output, and only then enable the daily schedule. Requirements An n8n workspace that permits the Zvid community package, funded Zvid and OpenRouter accounts, a public RSS feed and article page, and permission to use the source content and any background music. Customization In Config, adjust branding, fonts, copy labels, timing, music, the OpenRouter model and output toggles. Keep at least one of makeLinkedInVideo, makeXTeaser and makeOgImage enabled. Additional info Manual tests can rebuild the newest post; the last-post marker persists only on production executions. Review the copy against the source article before sharing. This workflow generates assets but does not publish to social platforms. Full guide: https://github.com/Zvid-io/zvid-n8n/blob/master/workflows/blog-content-kit.md. An n8n automation workflow template by Zvid.