Mindket

Chat agent that writes a report on one n8n creator

Newversion 1 · updated

Overview

An n8n workflow you chat with. Give it an n8n creator’s username, and an OpenAI agent reads that creator’s public weekly and monthly numbers and writes a Markdown report.

Chat agent that writes a report on one n8n creator is an n8n workflow in the Research category, listed by Mindket. It is free. This is version 1, last updated on . Download it on this page or copy its JSON, then import it into an n8n canvas. Nothing runs until you activate it in n8n.

At a glance

Runs in
  • n8n Cloud: import the file into a new workflow there, and delete the save step
  • Your own n8n server: the same file, with a folder on that machine for saved reports
  • The n8n chat window: type a username and read the report in the reply
  • A local install: also keeps a Markdown file for each report

Platform

Connects 1 app

How it works

Trigger

Chat message

It starts when you send a message in the n8n chat. Set first:

  • An OpenAI credential on the chat model
  • A folder path for the saved copy, if you keep it

Actions

  1. The agent takes the creator’s username from your message
  2. Its lookup tool downloads the creators and workflows stats files and sorts each by weekly inserts
  3. The lists are cut to the top 25 creators and the top 300 workflows and joined by username
  4. The tool keeps the one creator you asked for and returns their data
  5. The agent writes a Markdown report and replies with it, and a copy can be saved as a file

Result

A Markdown report on one creator with a summary, a table of workflows, an analysis and further insights

Integrations

What you need before you start.

OpenAI

Language model

Runs the agent that calls the lookup tool and writes the report.

NeedsOpenAI API key

Workflow check

Checked by Mindket on 13 Nov 2026

Steps
19 steps, starting when another workflow calls it or on a chat message
Not reached
1 node no run reaches: Ollama Chat Model
AI
1 step calls an AI model: n8n Creator Stats Agent
Sign-ins
Signs in to: OpenAI
API keys
No API key is left in the file
Step types
Mindket’s checker reads 11 of its 12 step types. It does not read: Read Write File

Read from the workflow’s file, not from a run.

About

What it is

This n8n workflow answers a chat message with a report on one n8n template creator. You type a username. An OpenAI agent calls a lookup tool, which reads two public stats files and keeps that creator and their most visited workflows. The agent then writes a Markdown report with a summary, a table of the workflows, an analysis and extra insights, and a copy can also be saved to a file. Twenty three nodes run it, beside thirteen sticky notes.

Who it suits

Template authors, community managers and n8n agencies who want to look one creator up on demand and read the picture in words, instead of scrolling through a long leaderboard table. It is the on demand one. Its sibling listing, Daily top n8n creators report by email, Drive and Telegram, runs by itself every day on the whole top ten. Skip this one if you want a standing report that needs no question.

Who uses it, and how
IndustryWho uses itHow they use itExample
CommunityCommunity managersLook up a creator before an interview or a featureA manager asks for one creator’s report before inviting them to a call.
AgenciesAutomation consultantsCheck how a creator’s templates are doing before copying their approachA consultant reads which of a creator’s workflows draw the most inserts.
Template authorsCreatorsSee their own numbers in plain wordsAn author asks for their own report each week and compares the figures.
ResearchAnalysts of the n8n ecosystemPull a quick profile into notesAn analyst saves the report as a file for a write-up.

You need a little n8n: one credential and one folder path, if you want the saved copy.

Where to use it

Any n8n that can reach OpenAI and the public stats files will run it. The report appears in the chat. The saved copy needs an n8n that can write to a folder.

  • n8n Cloud: import the file into a new workflow there, and delete the save step
  • Your own n8n server: the same file, with a folder on that machine for saved reports
  • The n8n chat window: type a username and read the report in the reply
  • A local install: also keeps a Markdown file for each report

Setup

Download saves a zip with workflow.json and Mindket’s setup notes in your downloads folder. Import the file, save it once, add one OpenAI credential and chat.

What you need first
NeedDetail
n8nOn n8n Cloud or on a server of your own
OpenAIAn API key
A folderOptional, for saved copies, on the machine that runs n8n
  1. In n8n, create a workflow, open its menu, choose Import from File and pick workflow.json. Save it, because the agent’s tool runs this same workflow by its own ID.
  2. Add an OpenAI credential and select it in gpt-4o-mini.
  3. To keep copies, replace <YOUR_FOLDER_PATH> in Save creator-summary.md with a folder on the machine that runs n8n. To skip them, delete that node and creator-summary.
  4. Open the chat, type a creator’s n8n username, spelled exactly, and send it.

How to use it

Type a username in the chat. The agent looks the creator up and writes the report. Read it in the reply, and find the saved copy in your folder if you set one.

What to change for a different result
To changeWhere
What the report holdsThe instructions in n8n Creator Stats Agent
How many creators and workflows are searchedTake Top 25 Creators and Take Top 300 Workflows
The modelgpt-4o-mini, or the disabled Ollama Chat Model for a local one
Where copies goSave creator-summary.md

Example

A community manager is about to invite a template author to a call. She opens the chat, types the author’s username and sends it.

The agent looks the author up and replies with a Markdown report. It holds a short summary, a table with each workflow’s weekly and monthly visitors and inserts, a note on why those workflows are popular and a few more observations. If the author is outside the weekly top 25, the agent says the data is unavailable. Check any figure you quote against the lookup, because a model can misstate a number.

For newcomers and experts

If you are new. n8n draws a workflow as boxes joined by lines, and each box, a node, does one job. An agent is a model that can call tools by itself. Here its only tool is another run of this same workflow. That run fetches the numbers.

For experts. The lookup is a second entry point in the same file, and the agent reaches it through a Workflow tool with a one field schema.

Where to look closer
NodeWhat it doesWhat to know
Workflow ToolRuns this workflow by its own ID and passes the usernameThe sub run starts at When Executed by Another Workflow and reads query.username
Global VariablesHolds the address of the two stats files and the usernameThe files are public lists, and Mindket’s copy reads them without a wrapper step
Merge Creators & WorkflowsJoins creators to workflows by usernameBoth lists are cut first, to the top 25 creators and the top 300 workflows
Filter By Creator UsernameKeeps the creator you asked forThe test is an exact, case sensitive match

Good to know

Only the weekly top creators are found. The model can slip on a number.

  • Data: the two stats files are public, and the workflow reads them live from the address in Global Variables. We fetched them on 12 November 2026, and they held 2391 creators and 11487 workflows
  • Reach: only a creator in the weekly top 25 is found, and only workflows in the weekly top 300 appear
  • Username: it must match exactly, including its case
  • Model: the file sets gpt-4o-mini. OpenAI’s deprecations page, read on 12 November 2026, gives 14 January 2027 as the shutdown of gpt-4o, gpt-4o-mini, gpt-4.1 and gpt-4.1-mini, with gpt-6-luna as the replacement
  • Repairs: the original copy expected a data wrapper that the files do not have, and it saved into its author’s own folder. Mindket’s copy drops the wrapper steps and holds a folder placeholder
  • Memory: Window Buffer Memory keeps the chat’s earlier turns, so a follow up can refer back
  • Billing: OpenAI bills each chat turn and each report
  • Your data: your message and the creator’s stats go to OpenAI
  • Credentials: the JSON holds none

README and files

README

Chat agent that writes a report on one n8n creator

An n8n workflow you talk to in a chat box. Give it the username of an n8n template creator, and an OpenAI agent looks up
that creator's weekly and monthly numbers and writes a Markdown report. The report appears in the chat, and a copy can
be saved to a folder on your computer.

How it differs from the daily report

Mindket lists a sibling workflow, Daily top n8n creators report by email, Drive and Telegram. This one waits for you. It
takes one username, answers in a chat and covers one creator. The sibling runs by itself every day, takes no input, covers
the top ten creators together and sends its report out by Google Drive, Gmail and Telegram. Pick this one to look
someone up on demand, and the other for a standing report.

What is inside

  • workflow.json: the workflow as n8n exports it, 23 nodes and 13 sticky notes. It holds no credential.
  • README.md: these notes.

What we changed from the original copy

  • The workflow reads two public stats files, one for creators and one for workflows, and expects each to arrive wrapped
    in a data field. Both files are plain lists with no such field. We fetched them on 12 November 2026, and they held
    2391 creators and 11487 workflows. The four steps that looked for the wrapper (Parse Creators Data,
    Split Out Creators, Parse Workflow Data and Split Out Workflows) are gone, and each sort step now takes the
    downloaded items directly.
  • Save creator-summary.md wrote into a folder on its author's computer. The path now reads <YOUR_FOLDER_PATH>.
  • Three long sticky notes are gone, and three others lost their links to outside pages. The rest keep short titles.

Before you start

  • An n8n instance, on n8n Cloud or your own server.
  • An OpenAI API key.
  • For the saved copy, an n8n that can write to a folder, such as a local install. The save step is optional.

Set it up

  1. In n8n, create a workflow, open its menu, choose Import from File and pick workflow.json. Save it. The agent's
    lookup tool is this same workflow, called by its own ID, so it must be saved first.
  2. Add an OpenAI credential and select it in gpt-4o-mini.
  3. To keep a copy of each report, replace <YOUR_FOLDER_PATH> in Save creator-summary.md with a folder on the machine
    that runs n8n. To skip it, delete that node and creator-summary.
  4. Open the chat, type a creator's n8n username, spelled exactly, and send it.

How a run goes

  1. When chat message received takes your message and gives it to n8n Creator Stats Agent.
  2. The agent's instructions ask for a Markdown report. It holds a summary, a table of the creator's workflows, an analysis
    and some extra insights. gpt-4o-mini is its model, with a temperature of 0.1, and Window Buffer Memory keeps the
    chat's earlier turns.
  3. The agent calls its tool, Workflow Tool, which runs this same workflow through When Executed by Another Workflow.
    It passes the username as query.username.
  4. In that second run, Global Variables sets the address of the two stats files and the username. stats_aggregate_creators
    and stats_aggregate_workflows download them.
  5. Each list is sorted by weekly inserters, highest first. Take Top 25 Creators and Take Top 300 Workflows cut them
    down, and Creators Data and Workflows Data keep the fields the report needs.
  6. Merge Creators & Workflows joins each creator to their workflows by username, Filter By Creator Username keeps
    the one creator you asked for, and Aggregate and Workflow Response hand the data back to the agent.
  7. The agent writes the report. creator-summary turns it into a text file for Save creator-summary.md, which writes a
    Markdown file named with the date and time. Summary Report runs last and sets the reply you read in the chat.

Change the look

  • What the report holds: the instructions in n8n Creator Stats Agent.
  • How many creators and workflows are searched: Take Top 25 Creators and Take Top 300 Workflows.
  • The model: gpt-4o-mini. The file holds a disabled Ollama Chat Model for a local model. Connect it in place of
    the OpenAI one to try that.
  • Where copies go: Save creator-summary.md.

Good to know

  • The facts below come from pages and n8n source read on 12 November 2026.
  • The stats files are public, and the workflow reads them live from the address in Global Variables. If their owner
    moves or reshapes them, the lookup fails until you update that address.
  • Only a creator in the weekly top 25 is found, and only workflows in the weekly top 300 appear in the table. For anyone
    else the tool returns nothing, and the agent says the data is unavailable.
  • The username must match exactly, including its case.
  • The model is gpt-4o-mini. OpenAI's deprecations page gives 14 January 2027 as the shutdown date of gpt-4o,
    gpt-4o-mini, gpt-4.1 and gpt-4.1-mini, and names gpt-6-luna as their replacement. Pick another model before that
    date.
  • When Executed by Another Workflow holds an example input with the username joe. It only shows the shape of the
    input, and the real value comes from the agent.
  • A language model writes the report and can misread a number. Check anything you quote against the lookup's data.
  • Billing: OpenAI bills each chat turn and each report.
  • Your data: your message and the creator's stats go to OpenAI. The stats files are fetched over the web.
  • Credentials: the JSON holds none.
Files
NOTICE.md  712 B
README.md  5 KB
workflow.json  25 KB

3 files, 31 KB, downloaded as a zip.

What’s new

  • Version 1 · 2026-11-12

Reviews

No ratings yet

Write a review

No reviews yet.

More from Mindket

See all from Mindket

anaksor-ocr

Sokheng · Kit

Reads Khmer and English text from documents, receipts and photos of signs, using a detector for text lines and a recogniser for each line. Suits developers who…

New

Qwen2.5-7B-Instruct as GGUF files in eight quantization sizes, to chat with locally through llama.cpp. For people who want a capable 7.6B model on their own co…

New

ACE-Step 1.5 XL SFT

ACE-Step · Kit

Generates music from text with a 4B diffusion decoder, 50 steps and guidance control, aiming for higher audio quality than the base. For creators with a GPU of…

New

Similar in Research

See all in Research

Merlin-Cancer-Super

AbdomenAtlas · Kit

Detects and outlines tumors in 9 organs on CT scans, trained with the R-Super method that learns from radiology reports. A research model for medical imaging g…

New

EarthJev

dBenf · Kit

Answers typed questions about satellite image patches from all 12 Sentinel-2 bands, returning a probability for each option without writing text. A Qwen3.5-0.8…

New

getting-over-it-rl-jax

zimmerk4 · Kit

Plays the full game Getting Over It from the bottom to the end with a small trained policy network that learned inside a JAX physics simulator. For reinforceme…

New