Opening Problem Statement
Meet Joe, a community manager responsible for tracking the most influential creators and popular workflows in the n8n ecosystem. Every day, Joe manually downloads data from GitHub repositories, combs through numerous metrics like unique weekly visitors and inserters, and crafts detailed reports highlighting community contributions. The process is tedious and error-prone, taking hours each day that Joe could spend on more impactful community engagement. With fast-changing data and multiple sources to reconcile, missing trends or misreporting key contributors is a real risk — costing the community time and stalling growth.
Joe wants a reliable, automated solution that pulls the latest stats, aggregates creators and workflow data, synthesizes insights using AI, and delivers clean reports to his inbox, Google Drive, and Telegram channels — without heavy manual effort.
What This Automation Does
This n8n workflow solves Joe’s challenge by automating the entire reporting process of the n8n creator leaderboard. Here’s what it does when triggered—either by schedule or manually:
- Automatically fetches raw JSON statistics about n8n creators and workflows from a GitHub repository.
- Splits the aggregated JSON data into individual creator and workflow entries for detailed processing.
- Sorts the data to identify the top creators by unique weekly inserters and top workflows by weekly insertions.
- Selects the top 10 creators and top 50 workflows based on recent activity metrics.
- Uses powerful AI models—from OpenAI’s GPT-4o-mini to Google’s Gemini Chat—to generate a comprehensive Markdown report summarizing contributors’ impact and key workflow features.
- Converts Markdown reports into HTML for email formatting and saves them to Google Drive, emails reports to specified recipients, and optionally sends highlights via Telegram.
By automating these steps, Joe saves multiple hours of manual labor daily and gains reliable, actionable insights to foster community growth.
Prerequisites ⚙️
- n8n account (cloud or self-hosted) with access to workflows and credentials.
- GitHub JSON data source for n8n community leaderboard statistics (publicly hosted repository URLs provided in the workflow).
- OpenAI API credentials
- Google Gemini (PaLM) API credentials
- Google Drive API credentials
- Gmail OAuth2 credentials
- Telegram API credentials (optional)
If you prefer to self-host n8n for full control and cost efficiency, consider services like Hostinger for easy deployment.
Step-by-Step Guide to Set Up and Use This Workflow
Step 1: Configure the Schedule Trigger
Navigate to the Schedule Trigger node.
Set it to run daily at a specific hour (default is 22:00). This ensures the workflow updates leaderboard stats every day without manual execution.
You should see the trigger rule set with an interval of one hour of the day.
Common mistake: Forgetting to enable the trigger after setup.
Step 2: Define Global Variables
Open the Global Variables node.
Set the base URL under path to point to the GitHub raw JSON files repository:
https://raw.githubusercontent.com/teds-tech-talks/n8n-community-leaderboard/refs/heads/main/
Set filenames for workflows and creators JSON files:
stats_aggregate_workflows and stats_aggregate_creators respectively.
Set the current date variable with:
{{$now.format('yyyy-MM-dd')}}
Expected outcome: Other nodes can dynamically fetch up-to-date JSON files.
Common mistake: Typos in URLs or variable names cause data fetch failure.
Step 3: Fetch Creators and Workflow Data via HTTP Request Nodes
Configure the stats_aggregate_creators and stats_aggregate_workflows nodes.
Both use HTTP Request (GET method by default) to fetch the JSON files formed by combining path + filename + .json.
Confirm that the URLs are formed dynamically using expressions.
On execution, the raw JSON data about community contributors and workflow stats will be pulled into the workflow.
Common mistake: HTTP 404 errors due to incorrect paths or missing files.
Step 4: Parse the JSON Data into Arrays
Use the Parse Creators Data and Parse Workflow Data Set nodes.
Extract the data array from the JSON objects.
This prepares the data for splitting and further processing.
Expected outcome: Clean arrays ready for further manipulation.
Common mistake: Incorrect reference to data fields leads to null results.
Step 5: Split Data into Individual Entries
Use Split Out Creators and Split Out Workflows SplitOut nodes.
This breaks down the arrays into individual JSON objects, each representing one creator or workflow.
This step is crucial to allow sorting and filtering individually.
Expected outcome: Stream of items, each with one creator or workflow.
Common mistake: Forgetting to set the correct field to split out (‘data’) will cause node failure.
Step 6: Sort Creators and Workflows by Activity
Use Sort By Top Weekly Creator Inserts and Sort By Top Weekly Workflow Inserts Sort nodes.
Sort creators in descending order by sum_unique_weekly_inserters, workflows by unique_weekly_inserters.
This ranks community members and workflows by recent insertion activity.
Expected outcome: Highest active creators and workflows appear first.
Common mistake: Sorting on wrong fields or ascending instead of descending.
Step 7: Limit to Top Creators and Workflows
The Take Top 10 Creators and Take Top 50 Workflows Limit nodes trim the data to manageable and meaningful numbers.
This helps focus the report on the most impactful community contributors.
Expected outcome: Reduced dataset with just the top players.
Common mistake: Forgetting to set max items or zeroing out output.
Step 8: Prepare Data for Merging
Set nodes Creators Data and Workflows Data map relevant fields (names, usernames, bio, stats) for each item.
This normalizes the data structure for merging.
Expected outcome: Clean, well-defined data fields.
Common mistake: Missing or mismatched field names.
Step 9: Merge Creator and Workflow Data
The Merge Creators & Workflows node combines the datasets by matching usernames.
Choose the enrichInput1 join mode, so workflows enrich the creators’ data.
Expected outcome: Each creator entry includes their associated workflows and stats.
Common mistake: Incorrect join mode causes data loss or duplication.
Step 10: Aggregate Merged Data
Use the Aggregate node (aggregateAllItemData) to consolidate combined entries into a single comprehensive JSON object.
This prepares for AI analysis and report generation.
Expected outcome: Single aggregated data item with full stats.
Common mistake: Skipping or misconfiguring aggregate options.
Step 11: Generate AI-Powered Report
Invoke the n8n Creators Stats Agent (LangChain Agent node with OpenAI GPT-4o-mini).
This agent uses a system prompt directing it to create a detailed Markdown report highlighting workflow features, community impact, and contributors’ influence.
It utilizes the merged and aggregated data along with a custom AI tool for pulling creator stats.
Expected outcome: Richly formatted Markdown report generated dynamically.
Common mistake: Invalid API keys or exceeded quota causing failures.
Step 12: Save Report Locally and to Google Drive
The creator-summary node converts the Markdown to a file, then Save creator-summary.md writes it locally.
The Google Drive node uploads the Markdown content as a text file to your drive in the root folder.
Expected outcome: Accessible report backups locally and in your cloud storage.
Common mistake: Invalid file paths or missing credentials causes file write failures.
Step 13: Convert Markdown to HTML and Send Emails
Convert Markdown to HTML nodes transform reports so email clients can render tables and formatting properly.
Two Gmail nodes send out emails: one with the full creators & workflows report, another listing the top 10 workflows.
Fill in correct sendTo email addresses and verify OAuth2 credentials.
Expected outcome: Recipients receive beautifully formatted report emails.
Common mistake: Misconfigured Gmail credentials or spam filters blocking emails.
Step 14: Use Google Gemini AI to Create Top 10 Workflows List
The Google Gemini Chat Model node generates a concise, hyperlink-rich list of the top 10 workflows using LangChain chainLlm.
This output is converted to HTML and sent via Gmail and optionally via Telegram Top 10 Workflows List node.
Expected outcome: Clean highlight list shared across multiple channels.
Common mistake: Incorrect chat model keys or invalid chat prompt JSON.
Customizations ✏️
- Add More Metrics: In the
Parse Creators DataandParse Workflow Datanodes, add fields like “sum_unique_monthly_inserters” or “bio” to enrich report content. - Change Reporting Frequency: Adjust the Schedule Trigger node interval to run hourly or weekly depending on your reporting needs.
- Email Recipients: Modify the
sendTofields in Gmail Creators & Workflows Report and Gmail Top 10 Workflows List nodes to send emails to multiple stakeholders. - Local Save Path: In the Save creator-summary.md node, change the file path to a network drive or different folder for team access.
- Enable Telegram Notifications: Configure the Telegram Top 10 Workflows List with your chat ID for real-time community alerts.
Troubleshooting 🔧
Problem: “HTTP Request nodes fail with 404 errors”
Cause: Incorrect URL in Global Variables’ path or filenames.
Solution: Verify URL correctness. Test fetching the raw JSON manually in a browser.
Problem: “AI Agent node returns incomplete or empty report”
Cause: API key issues with OpenAI or Google Gemini or malformed input data.
Solution: Check credentials and ensure the aggregated data contains all necessary fields.
Problem: “Emails not delivered”
Cause: Invalid Gmail OAuth credentials or spam filtering.
Solution: Reauthenticate Gmail node credentials and verify sender email. Check spam or whitelist the sender.
Pre-Production Checklist ✅
- Verify all API credentials (OpenAI, Google Gemini, Gmail, Google Drive) are active and valid.
- Confirm URLs in the Global Variables node are reachable and return correct JSON data.
- Run the workflow manually and check logs for any node failures.
- Check output at each stage for expected data structure (parse, split, sort, merge).
- Test email and Telegram output nodes with test addresses.
- Backup current report files and data before deployment.
Deployment Guide
Activate the workflow in your n8n instance by setting the Schedule Trigger node active.
Monitor initial runs in the executions panel for any errors.
Adjust trigger times or nodes based on the volume of data or desired reporting cadence.
Logs and outputs can be viewed in n8n for troubleshooting.
Consider setting up alerting on node failures for proactive monitoring.
FAQs
Q: Can I replace OpenAI with only Google Gemini?
A: Yes, you can modify the workflow to rely solely on Google Gemini AI nodes for report generation, but combining both yields richer insights.
Q: Does this workflow consume many API credits?
A: The workflow uses AI models with moderate token usage per run and multiple API calls to Gmail and Google Drive. Monitor your usage to control costs.
Q: Is my community data safe?
A: All data is pulled from public GitHub repositories and handled securely via OAuth credentials. Ensure you secure your API keys and access tokens.
Q: Can this handle a large number of creators/workflows?
A: Yes, but performance depends on your n8n instance capacity. Adjust limits and pagination if needed.
Conclusion
By following this guide, you automated the complete process of aggregating, analyzing, and reporting on the n8n community’s creator leaderboard. Joe can now produce daily insightful reports within minutes instead of hours, freeing up precious time and reducing errors. This workflow empowers community managers, contributors, and enthusiasts to recognize top creators and trending workflows with ease.
Next steps? Explore automating notifications for new creators joining the leaderboard, integrating Slack channels for real-time engagement, or expanding the report to include detailed workflow performance metrics.
Keep experimenting with n8n’s powerful automation combined with AI to deliver community value like never before!