January 22, 2026

Apify + Slack, turn Reels into clear prompt briefs

Lisa Granqvist Partner Workflow Automation Expert

Get a free AI assessment → ⬇️ Use template

You find a Reel that’s doing numbers, drop it into a team chat, and then… nothing. No shared understanding. No repeatable “why this works.” Just a link that disappears under a pile of other links.

This is the stuff that slows down content leads the most, but marketing managers and agency operators feel it too. With Apify Slack briefs automation, you turn any public Instagram Reel or TikTok URL into a structured prompt brief your team can actually use (and reuse).

Below you’ll see how the workflow runs, what comes out the other end, and how to adapt it for your own channels and creative process.

How This Automation Works

The full n8n workflow, from trigger to final output:

n8n Workflow Template: Apify + Slack, turn Reels into clear prompt briefs

Click to explore

flowchart LR

    subgraph sg0["form_ Flow"]
        direction LR
        n0["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/form.svg' width='40' height='40' /></div><br/>form_trigger"]
        n1@{ icon: "mdi:swap-horizontal", form: "rounded", label: "switch_platform", pos: "b", h: 48 }
        n2["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/httprequest.dark.svg' width='40' height='40' /></div><br/>scrape_ig_reel"]
        n3["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/httprequest.dark.svg' width='40' height='40' /></div><br/>download_ig_reel"]
        n4["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/httprequest.dark.svg' width='40' height='40' /></div><br/>scrape_tiktok"]
        n5["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/httprequest.dark.svg' width='40' height='40' /></div><br/>download_tiktok"]
        n6@{ icon: "mdi:cog", form: "rounded", label: "tiktok_to_base64", pos: "b", h: 48 }
        n7@{ icon: "mdi:swap-vertical", form: "rounded", label: "set_tiktok_result", pos: "b", h: 48 }
        n8["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/httprequest.dark.svg' width='40' height='40' /></div><br/>analyze_tiktok"]
        n9@{ icon: "mdi:swap-vertical", form: "rounded", label: "set_base_prompt", pos: "b", h: 48 }
        n10@{ icon: "mdi:swap-vertical", form: "rounded", label: "build_final_tiktok_prompt", pos: "b", h: 48 }
        n11@{ icon: "mdi:swap-vertical", form: "rounded", label: "build_final_ig_prompt", pos: "b", h: 48 }
        n12@{ icon: "mdi:cog", form: "rounded", label: "ig_to_base64", pos: "b", h: 48 }
        n13["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/httprequest.dark.svg' width='40' height='40' /></div><br/>analyze_ig_reel"]
        n14@{ icon: "mdi:swap-vertical", form: "rounded", label: "set_ig_result", pos: "b", h: 48 }
        n15["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/slack.svg' width='40' height='40' /></div><br/>send_prompt_msg"]
        n16@{ icon: "mdi:cog", form: "rounded", label: "Convert to File", pos: "b", h: 48 }
        n17["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/slack.svg' width='40' height='40' /></div><br/>upload_file"]
        n17 --> n15
        n0 --> n9
        n12 --> n13
        n4 --> n10
        n14 --> n16
        n8 --> n7
        n2 --> n11
        n16 --> n17
        n13 --> n14
        n5 --> n6
        n9 --> n1
        n1 --> n2
        n1 --> n4
        n3 --> n12
        n6 --> n8
        n7 --> n16
        n11 --> n3
        n10 --> n5
    end

    %% Styling
    classDef trigger fill:#e8f5e9,stroke:#388e3c,stroke-width:2px
    classDef ai fill:#e3f2fd,stroke:#1976d2,stroke-width:2px
    classDef aiModel fill:#e8eaf6,stroke:#3f51b5,stroke-width:2px
    classDef decision fill:#fff8e1,stroke:#f9a825,stroke-width:2px
    classDef database fill:#fce4ec,stroke:#c2185b,stroke-width:2px
    classDef api fill:#fff3e0,stroke:#e65100,stroke-width:2px
    classDef code fill:#f3e5f5,stroke:#7b1fa2,stroke-width:2px
    classDef disabled stroke-dasharray: 5 5,opacity: 0.5
    class n0 trigger
    class n1 decision
    class n2,n3,n4,n5,n8,n13 api
    classDef customIcon fill:none,stroke:none
    class n0,n2,n3,n4,n5,n8,n13,n15,n17 customIcon

The Problem: Viral videos don’t turn into reusable briefs

Most teams “save” great Reels and TikToks the same way. Someone pastes a link into Slack, adds a quick comment like “do this,” and hopes everyone sees the same thing. But the details that matter are buried inside the clip: lighting, camera movement, shot timing, environment, pacing, and why the hook lands. If you don’t capture those while the video is in front of you, you end up rewatching it five times, arguing over what to copy, and still sending a vague prompt to whoever’s producing the next version. That’s how good ideas die in the handoff.

It adds up fast. Here’s where it breaks down in real life.

People interpret the same video differently, so the “brief” becomes a debate instead of a plan.
Manual note-taking misses technical cues (lens feel, grading, camera path), which means the remake looks close but not right.
Links get lost in Slack threads, and you can’t search “that moody handheld kitchen reel” reliably later.
When you want to scale output, you’re forced to re-analyze from scratch instead of building a library of proven formats.

The Solution: Apify + Gemini analysis, delivered as a Slack-ready brief

This workflow turns a single URL into something your team can execute. You submit an Instagram Reel or TikTok link through a simple intake form (or route it in from a chat trigger), and n8n handles the messy parts behind the scenes. It uses Apify to scrape and download the public video, converts the file into base64 so it can be analyzed, and then sends that content to a vision-capable AI model (Gemini 2.5 Pro via HTTP request) for a deep forensic breakdown. Finally, it posts a clean summary to Slack and uploads a prompt file your editor, creative strategist, or AI-video tool can use immediately.

The workflow starts with a URL and a base prompt that you control. From there it routes by platform, analyzes the clip, and outputs two things in Slack: a readable summary plus a file that preserves the full “Generative Manifest” for reuse.

What You Get: Automation vs. Results

What This Workflow Automates

Results You’ll Get

It fetches Instagram or TikTok video data automatically via Apify and HTTP requests.
The video is downloaded and converted to base64 so analysis can run without manual file handling.
Gemini vision analysis produces a structured breakdown using your saved base prompt.
Slack receives both a quick summary and an attached prompt file for the full brief.

Most teams cut “brief creation” from about 30 minutes down to a few minutes per clip.
You get consistent language for shot timing, camera movement, lighting, and framing across your whole team.
Handoffs improve because the next person receives a real brief, not a link and a vibe.
You build a searchable archive of prompt files in Slack for formats that keep working.
Creative alignment gets easier, which means fewer revision loops and less back-and-forth.

Example: What This Looks Like

Say your team reviews 10 competitor clips every Monday. Manually, even “quick” analysis is maybe 20 minutes per video once you rewatch, take notes, and write something coherent, so you’re at about 3 hours. With this workflow, you paste each URL into the intake form (around 1 minute each), then wait for processing and get the brief posted into Slack with a prompt file attached. The human time drops to about 10 minutes total, and the results are far more detailed than rushed notes.

What You’ll Need

n8n instance (try n8n Cloud free)
Self-hosting option if you prefer (Hostinger works well)
Apify for scraping and downloading public videos.
Slack to deliver summaries and upload prompt files.
Google Gemini API key (get it from Google Cloud Console with Gemini enabled).

Skill level: Intermediate. You’ll connect a few accounts, add keys, and paste channel IDs without writing code.

Don’t want to set this up yourself? Talk to an automation expert (free 15-minute consultation).

How It Works

URL intake through a form trigger. Someone submits a public Instagram Reel or TikTok link using the workflow’s intake form. Clean. No “where did you find that link?” messages later.

Platform routing and video retrieval. A router checks the URL type, then calls the right Apify/HTTP path to fetch metadata and download the clip. If it’s Instagram, it follows the Instagram branch. TikTok goes through the TikTok branch.

AI analysis with a reusable base prompt. The file gets converted into base64, then sent to Gemini vision analysis using an HTTP request. Your “Compose Base Prompt” node controls the depth and structure, so you can push it toward shot-by-shot timing, creative direction, or AI-video prompt formatting for tools like Veo or Sora.

Slack delivery plus a downloadable prompt file. n8n posts a summary into Slack and uploads a file version of the full “Generative Manifest.” That file is what people grab later when they want to recreate the format quickly.

You can easily modify the base prompt to fit your brand voice, then change the Slack destination to a different channel based on team or client. See the full implementation guide below for customization options.

Step-by-Step Implementation Guide

Step 1: Configure the Form Trigger

Set up the intake form that starts the workflow and captures the video URL.

Add the Intake Form Trigger node and set Form Title to Reverse Engineer Short Form Video.
Set Form Description to Provide an IG Reel url or a TikTok url..
In Form Fields, create a required field labeled Url with placeholder https://www.instagram.com/reel/DKzbAvyoCMJ/.
(Optional) Keep Flowpast Branding as a visual note for documentation and team context.

Step 2: Route the Request by Platform

Use a switch to determine whether the incoming URL is Instagram or TikTok and send it down the appropriate path.

Add Route by Platform after Compose Base Prompt.
Create a rule for Instagram that checks if Url contains instagram.com with Left Value set to {{ $('Intake Form Trigger').item.json.Url }}.
Create a rule for TikTok that checks if Url contains tiktok.com with Left Value set to {{ $('Intake Form Trigger').item.json.Url }}.

Route by Platform sends Instagram URLs to Fetch Instagram Data and TikTok URLs to Fetch TikTok Data based on matching rules.

Step 3: Connect Instagram and TikTok Data Sources

Configure the platform data fetch, prompt assembly, and video retrieval for each branch.

In Fetch Instagram Data, set URL to https://api.apify.com/v2/acts/apify~instagram-api-scraper/run-sync-get-dataset-items and Method to POST.
Set JSON Body in Fetch Instagram Data to { "directUrls": [ "{{ $('Intake Form Trigger').item.json.Url }}" ], "resultsLimit": 1, "resultsType": "posts" }.
Credential Required: Connect your httpHeaderAuth credentials in Fetch Instagram Data.
In Assemble IG Prompt, set prompt to {{ $('Compose Base Prompt').item.json.prompt }} --- Video Caption: {{ $json.caption }} Video Hashtags: {{ $json.hashtags.join(",") }}.
In Retrieve IG Video, set URL to {{ $('Fetch Instagram Data').item.json.videoUrl }} and ensure the response format is file.
In Fetch TikTok Data, set URL to https://api.apify.com/v2/acts/apidojo~tiktok-scraper/run-sync-get-dataset-items and Method to POST.
Set JSON Body in Fetch TikTok Data to { "maxItems": 1, "startUrls": [ "{{ $('Intake Form Trigger').item.json.Url }}" ] }.
Credential Required: Connect your httpHeaderAuth credentials in Fetch TikTok Data.
In Assemble TikTok Prompt, set prompt to {{ $('Compose Base Prompt').item.json.prompt }} --- Video Title: {{ $json.title }} Video Hashtags: {{ $json.hashtags.join(",") }}.
In Retrieve TikTok Video, set URL to {{ $('Fetch TikTok Data').item.json.video.url }} and ensure the response format is file.
Configure IG Video to Base64 and TikTok Video to Base64 with Operation set to binaryToPropery.

⚠️ Common Pitfall: If the Apify request returns no items, confirm the input URL is a public post and matches the platform rule in Route by Platform.

Step 3: Set Up AI Analysis Nodes

Send the base64 video and assembled prompt to the Gemini endpoint for analysis.

In Analyze IG Clip, set URL to https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-pro:generateContent and Method to POST.
Set JSON Body in Analyze IG Clip to { "contents": [ { "parts": [ { "inline_data": { "mime_type": "video/mp4", "data": "{{ $json.data }}" } }, { "text": {{ JSON.stringify($('Assemble IG Prompt').item.json.prompt) }} } ] } ] }.
Credential Required: Connect your httpHeaderAuth credentials in Analyze IG Clip.
In Analyze TikTok Clip, set URL to https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-pro:generateContent and Method to POST.
Set JSON Body in Analyze TikTok Clip to { "contents": [ { "parts": [ { "inline_data": { "mime_type": "video/mp4", "data": "{{ $json.data }}" } }, { "text": {{ JSON.stringify($('Assemble TikTok Prompt').item.json.prompt) }} } ] } ] }.
Credential Required: Connect your httpHeaderAuth credentials in Analyze TikTok Clip.

Tip: If Gemini returns errors, verify that TikTok Video to Base64 and IG Video to Base64 output a data field and that the video size is within API limits.

Step 4: Configure Output and Slack Delivery

Store the AI responses, convert them to a file, and post the results to Slack.

In Store IG Result, map result to {{ $json.candidates[0].content.parts[0].text }}.
In Store TikTok Result, map result to {{ $json.candidates[0].content.parts[0].text }}.
In Generate Prompt File, set Operation to toText, Source Property to result, and Binary Property Name to prompt.md.
In Upload Prompt File, set Resource to file and Binary Property Name to prompt.md.
Credential Required: Connect your slackOAuth2Api credentials in Upload Prompt File.
In Post Slack Summary, set Text to *AI Video Generator Prompt:* ``` {{ $json.permalink }} ``` and choose your target Channel.
Credential Required: Connect your slackOAuth2Api credentials in Post Slack Summary.

⚠️ Common Pitfall: If Slack uploads succeed but the summary message is missing, verify that Upload Prompt File outputs a permalink field for Post Slack Summary.

Step 5: Test and Activate Your Workflow

Validate the full execution path for both platforms before turning the workflow on.

Click Execute Workflow and submit an Instagram URL in Intake Form Trigger to validate the IG branch.
Run a second test with a TikTok URL to validate the TikTok branch.
Successful execution results in a Slack file upload from Upload Prompt File and a message from Post Slack Summary containing the file permalink.
Once tests pass, toggle the workflow Active to enable production use.

🔒

Unlock Full Step-by-Step Guide

Get the complete implementation guide + downloadable template

Common Gotchas

Apify credentials can expire or be missing permissions. If scraping fails, check your Apify token status and actor access in the Apify console first.
If you’re using Wait nodes or external rendering, processing times vary. Bump up the wait duration if downstream nodes fail on empty responses.
Slack uploads can fail if the bot isn’t allowed to upload files in that channel. Verify the app scopes and the channel ID, then test with a small file first.

Frequently Asked Questions

How long does it take to set up this Apify Slack briefs automation?

About 30–60 minutes if you already have your Apify, Gemini, and Slack accounts ready.

Do I need coding skills to automate Apify Slack briefs?

No. You will mostly copy API keys, connect Slack, and paste a channel ID.

Is n8n free to use for this Apify Slack briefs workflow?

Yes. n8n has a free self-hosted option and a free trial on n8n Cloud. Cloud plans start at $20/month for higher volume. You’ll also need to factor in Gemini API usage plus your Apify plan for scraping.

Where can I host n8n to run this automation?

Two options: n8n Cloud (managed, easiest setup) or self-hosting on a VPS. For self-hosting, Hostinger VPS is affordable and handles n8n well. Self-hosting gives you unlimited executions but requires basic server management.

Can I customize this Apify Slack briefs workflow for a different brief format?

Yes, and it’s the best part. Update the prompt text in the “Compose Base Prompt” node to match your exact brief template, then keep the rest of the workflow the same. Common tweaks include adding a “hook formula” section, forcing output in JSON for easy parsing, or asking for a shorter version that fits in one Slack message. If you want separate outputs for editors vs. strategists, you can route to different Slack channels using the same analysis result.

Why is my Slack connection failing in this workflow?

Usually it’s missing scopes or the app isn’t allowed in the target channel. Reconnect Slack in n8n, confirm the bot can post and upload files, and double-check you’re using the right channel ID. If you’re posting to private channels, the bot must be invited first.

How many videos can this Apify Slack briefs automation handle?

It can handle a lot, but you’re limited by your n8n plan, Apify limits, and the Gemini API quota.

Is this Apify Slack briefs automation better than using Zapier or Make?

Often, yes, because this workflow is doing heavier lifting than a typical two-step Zap. You’re downloading a video, converting it, sending it to a vision model, then creating and uploading a file, which is the kind of multi-stage flow that gets awkward (and expensive) in some no-code tools. n8n also gives you the self-hosting option, which helps if you plan to analyze lots of clips without watching task counts. That said, if your version is “send URL to Slack with a summary,” Zapier or Make can be fine. Talk to an automation expert if you want help choosing.

Once this is running, “found a good Reel” stops being a dead end. You get a reusable brief in Slack, a prompt file your team can pull later, and a process you can repeat without thinking too hard.

Need Help Setting This Up?

Our automation experts can build and customize this workflow for your specific needs. Free 15-minute consultation—no commitment required.

Lisa Granqvist

Workflow Automation Expert

Expert in workflow automation and no-code tools.

{
"id": null,
"meta": {
"instanceId": "078898d9fe31fcbac169426e92ca8e7de22273f18fbbfe419b65c50970bcbd59",
"templateCredsSetupCompleted": null,
"templateId": null
},
"name": "Automated Short Video Analysis Workflow",
"tags": [],
"nodes": [
{
"id": "flowpast-topbar-6104",
"name": "Flowpast Branding",
"type": "n8n-nodes-base.stickyNote",
"position": [
0,
20
],
"parameters": {
"color": 7,
"width": 1180,
"height": 80,
"content": "## Flowpast.com | Automation Workflow Library\n**\ud83d\udcd6 Full tutorial & setup guide:** flowpast.com"
},
"typeVersion": 1
},
{
"id": "feeaf14f-cc61-4a85-9a80-8456356aa551",
"name": "Intake Form Trigger",
"type": "n8n-nodes-base.formTrigger",
"position": [
1080,
240
],
"webhookId": "8db8f807-4b93-4a74-81b6-290cc1d459e8",
"parameters": {
"options": [],
"formTitle": "Reverse Engineer Short Form Video",
"formFields": {
"values": [
{
"fieldLabel": "Url",
"placeholder": "https://www.instagram.com/reel/DKzbAvyoCMJ/",
"requiredField": true
}
]
},
"formDescription": "Provide an IG Reel url or a TikTok url."
},
"typeVersion": 2.2
},
{
"id": "a473cf43-ed18-479b-bc08-53173715c355",
"name": "Route by Platform",
"type": "n8n-nodes-base.switch",
"position": [
710,
250
],
"parameters": {
"rules": {
"values": [
{
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "c5641e00-9155-4ca8-b4cd-90798531103a",
"operator": {
"type": "string",
"operation": "contains"
},
"leftValue": "={{ $('Intake Form Trigger').item.json.Url }}",
"rightValue": "=instagram.com"
}
]
}
},
{
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "4da252f9-8606-476f-85a3-23f95b6f6e72",
"operator": {
"type": "string",
"operation": "contains"
},
"leftValue": "={{ $('Intake Form Trigger').item.json.Url }}",
"rightValue": "tiktok.com"
}
]
}
}
]
},
"options": []
},
"typeVersion": 3.2
},
{
"id": "9361eaaa-5a19-4001-8809-e9ea7c44125d",
"name": "Fetch Instagram Data",
"type": "n8n-nodes-base.httpRequest",
"position": [
480,
120
],
"parameters": {
"url": " https://api.apify.com/v2/acts/apify~instagram-api-scraper/run-sync-get-dataset-items",
"method": "POST",
"options": [],
"jsonBody": "={\n    \"directUrls\": [\n      \"{{ $('Intake Form Trigger').item.json.Url }}\"\n    ],\n    \"resultsLimit\": 1,\n    \"resultsType\": \"posts\"\n}",
"sendBody": true,
"specifyBody": "json",
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth"
},
"credentials": {
"httpHeaderAuth": {
"id": "credential-id",
"name": ""
}
},
"typeVersion": 4.2
},
{
"id": "abe8f70a-2b3a-4c69-ba07-d6ee790f2302",
"name": "Retrieve IG Video",
"type": "n8n-nodes-base.httpRequest",
"position": [
130,
130
],
"parameters": {
"url": "={{ $('Fetch Instagram Data').item.json.videoUrl }}",
"options": {
"response": {
"response": {
"responseFormat": "file"
}
}
}
},
"typeVersion": 4.2
},
{
"id": "aad88865-ba23-4619-a172-8413863b127d",
"name": "Fetch TikTok Data",
"type": "n8n-nodes-base.httpRequest",
"position": [
530,
430
],
"parameters": {
"url": "https://api.apify.com/v2/acts/apidojo~tiktok-scraper/run-sync-get-dataset-items",
"method": "POST",
"options": [],
"jsonBody": "={\n    \"maxItems\": 1,\n    \"startUrls\": [\n        \"{{ $('Intake Form Trigger').item.json.Url }}\"\n    ]\n}",
"sendBody": true,
"specifyBody": "json",
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth"
},
"credentials": {
"httpHeaderAuth": {
"id": "credential-id",
"name": ""
}
},
"typeVersion": 4.2
},
{
"id": "efe3daec-2f18-43c0-8e28-4ce84c33a68b",
"name": "Retrieve TikTok Video",
"type": "n8n-nodes-base.httpRequest",
"position": [
175,
435
],
"parameters": {
"url": "={{ $('Fetch TikTok Data').item.json.video.url }}",
"options": {
"response": {
"response": {
"responseFormat": "file"
}
}
}
},
"typeVersion": 4.2
},
{
"id": "e6124831-b97f-4eb7-b3c0-8192339d2aa3",
"name": "TikTok Video to Base64",
"type": "n8n-nodes-base.extractFromFile",
"position": [
0,
495
],
"parameters": {
"options": [],
"operation": "binaryToPropery"
},
"typeVersion": 1
},
{
"id": "380927ac-d7cb-4c66-9020-c905d0d0932d",
"name": "Store TikTok Result",
"type": "n8n-nodes-base.set",
"position": [
360,
620
],
"parameters": {
"options": [],
"assignments": {
"assignments": [
{
"id": "eccbeb92-af90-4244-8e23-2cd3e2616a07",
"name": "result",
"type": "string",
"value": "={{ $json.candidates[0].content.parts[0].text }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "246e1bc4-8a3e-483b-acb9-3fdd87ed51b5",
"name": "Analyze TikTok Clip",
"type": "n8n-nodes-base.httpRequest",
"position": [
125,
560
],
"parameters": {
"url": "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-pro:generateContent",
"method": "POST",
"options": [],
"jsonBody": "={\n  \"contents\": [\n    {\n      \"parts\": [\n        {\n          \"inline_data\": {\n            \"mime_type\": \"video/mp4\",\n            \"data\": \"{{ $json.data }}\"\n          }\n        },\n        {\n          \"text\": {{ JSON.stringify($('Assemble TikTok Prompt').item.json.prompt) }}\n        }\n      ]\n    }\n  ]\n}",
"sendBody": true,
"specifyBody": "json",
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth"
},
"credentials": {
"httpHeaderAuth": {
"id": "credential-id",
"name": ""
}
},
"typeVersion": 4.2
},
{
"id": "b013129b-1662-4f47-8f89-d7668368b507",
"name": "Compose Base Prompt",
"type": "n8n-nodes-base.set",
"position": [
845,
330
],
"parameters": {
"options": [],
"assignments": {
"assignments": [
{
"id": "f302b2c5-43cb-41f0-91f5-e91f72397ae4",
"name": "prompt",
"type": "string",
"value": "=**Your Persona:** You are a \"Digital Twin Architect,\" a specialized AI analyst with a dual mastery of forensic video analysis and generative AI video synthesis. Your function is to deconstruct a source video into its absolute, quantifiable components and then architect a \"Generative Manifest\"\u2014a flawless, multi-part prompt designed to compel an AI video model to render a perfect digital replica. You do not interpret; you transcribe reality into data.\n\n**Your Mission:** Your sole objective is to analyze the provided short-form video and produce a **Generative Manifest**. This manifest must be so detailed that it leaves no room for creative interpretation by the target AI video model (Google Veo, Sora, etc.). The goal is not a similar video; it is a shot-for-shot, motion-for-motion, photon-for-photon digital twin.\n\n**The Process: Forensic Deconstruction**\n\nBefore writing the manifest, you will perform a deep forensic analysis, dissecting the video across multiple layers. Think like a VFX artist creating a CG replica of a live-action shot.\n\n**Layer 1: The Global Aesthetic & Physics Core**\nThis is the foundational DNA of the video.\n*   **Visual Medium:** Is it emulating a specific film stock (e.g., Kodak Vision3 50D 35mm, Ektachrome 16mm)? Or is it a specific digital camera sensor (e.g., ARRI Alexa 65, RED Komodo, a high-end smartphone sensor)? Note the inherent grain, noise pattern, and sharpness.\n*   **Color Science & Grading:** Be precise. \"Cinematic teal and orange\" is too vague. Specify \"A high-contrast color grade with crushed blacks, lifted mid-tones, desaturated blues, and a heavy push of orange into the skin tones. The overall white balance is shifted slightly warm, around 4500K.\"\n*   **Lens Emulation:** Identify the characteristics of the lens. \"Emulating a Cooke Anamorphic/i SF 50mm lens, creating distinct oval bokeh, soft lens flares, and slight edge distortion.\" Or \"Emulating a sterile, hyper-sharp Zeiss Supreme Prime lens with zero chromatic aberration.\"\n*   **Physics & Reality Engine:** Define the environmental physics. \"Hyperrealistic physics model. All fluid dynamics (water, steam) must be viscous and turbulent. Fabric simulation must show weight and react to air currents. Particle effects (dust motes, sparks) must be dense and interact with light.\"\n\n**Layer 2: Per-Shot Deconstruction**\nBreak the video into a numbered sequence of shots. For EACH shot, you must detail the following:\n\n*   **Shot ID & Absolute Timing:**\n    *   `[SHOT X]`\n    *   `DURATION:` Start time to end time (e.g., 0.0s - 3.2s).\n\n*   **Camera Specification:**\n    *   `FRAMING:` Extreme Close-Up (ECU), Medium Shot (MS), etc.\n    *   `ANGLE:` Low Angle, High Angle, etc.\n    *   `MOVEMENT:` Be precise. Not \"pan,\" but \"A slow, 15-degree pan to the right with a smooth ease-in and ease-out, taking 2.0 seconds, starting at the 1.0s mark of the shot. The motion is perfectly stable, as if on a geared head tripod.\" Not \"handheld,\" but \"Subtle, high-frequency handheld shake emulating a person breathing, with a maximum vertical displacement of 2 pixels.\"\n\n*   **Subject & Action Choreography:**\n    *   `SUBJECT(S):` Hyper-specific descriptions. \"Male, early 30s, olive skin, short black hair, with a 3-day stubble. Wearing a navy blue heavyweight cotton t-shirt with visible fabric weave and slight pilling on the collar.\"\n    *   `ACTION MANIFEST:` A time-stamped log of all actions. \"At 0.5s, the subject's right hand enters the frame from the left. At 0.7s, his fingers make contact with the ceramic mug. At 1.2s, a micro-expression of concentration appears: slight furrowing of the brow, lips press together.\"\n\n*   **Lighting & Environmental Detail:**\n    *   `LIGHTING BLUEPRINT:` \"A single, large, soft key light (emulating a 4x4 silk diffuser) is positioned camera left and slightly high, creating a Rembrandt lighting pattern on the subject's face. A weak, cool-toned fill light (approx. 6000K) from the right prevents shadows from being completely black. A hard rim light from behind separates the subject from the background.\"\n    *   `ENVIRONMENT STATE:` \"The background shows a plaster wall with visible texture and a 2-inch scuff mark three feet to the right of the subject's head. Dust motes are visible, floating slowly in the shafts of light.\"\n\n*   **Focus & Depth Plane:**\n    *   `DEPTH OF FIELD:` \"Extremely shallow depth of field (emulating f/1.4 aperture). The focal plane is locked precisely on the subject's leading eyeball.\"\n    *   `FOCUS DYNAMICS:` \"At 2.5s, a slow, deliberate rack focus begins, shifting the focal plane from the subject's eye to the coffee cup in their hand over 0.7 seconds.\""
}
]
}
},
"typeVersion": 3.4
},
{
"id": "5ac6e027-8874-4541-8d2a-da1db0d76586",
"name": "Assemble TikTok Prompt",
"type": "n8n-nodes-base.set",
"position": [
300,
440
],
"parameters": {
"options": [],
"assignments": {
"assignments": [
{
"id": "aab55ec6-6c4b-4e60-a576-62812f91299f",
"name": "prompt",
"type": "string",
"value": "={{ $('Compose Base Prompt').item.json.prompt }}\n---\nVideo Title: {{ $json.title }}\nVideo Hashtags: {{ $json.hashtags.join(\",\") }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "3ff33483-c6f5-4022-b4ba-4fc8f75b1141",
"name": "Assemble IG Prompt",
"type": "n8n-nodes-base.set",
"position": [
355,
200
],
"parameters": {
"options": [],
"assignments": {
"assignments": [
{
"id": "aab55ec6-6c4b-4e60-a576-62812f91299f",
"name": "prompt",
"type": "string",
"value": "={{ $('Compose Base Prompt').item.json.prompt }}\n---\nVideo Caption: {{ $json.caption }}\nVideo Hashtags: {{ $json.hashtags.join(\",\") }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "e57ad5a9-be69-406c-a491-dba6bccd04a0",
"name": "IG Video to Base64",
"type": "n8n-nodes-base.extractFromFile",
"position": [
0,
210
],
"parameters": {
"options": [],
"operation": "binaryToPropery"
},
"typeVersion": 1
},
{
"id": "c7602bc6-c215-45da-8d1e-1efb88fd1598",
"name": "Analyze IG Clip",
"type": "n8n-nodes-base.httpRequest",
"position": [
165,
235
],
"parameters": {
"url": "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-pro:generateContent",
"method": "POST",
"options": [],
"jsonBody": "={\n  \"contents\": [\n    {\n      \"parts\": [\n        {\n          \"inline_data\": {\n            \"mime_type\": \"video/mp4\",\n            \"data\": \"{{ $json.data }}\"\n          }\n        },\n        {\n          \"text\": {{ JSON.stringify($('Assemble IG Prompt').item.json.prompt) }}\n        }\n      ]\n    }\n  ]\n}",
"sendBody": true,
"specifyBody": "json",
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth"
},
"credentials": {
"httpHeaderAuth": {
"id": "credential-id",
"name": ""
}
},
"typeVersion": 4.2
},
{
"id": "08b0dd73-dcdb-4c5f-bff3-b7ffeab4d7f1",
"name": "Store IG Result",
"type": "n8n-nodes-base.set",
"position": [
295,
290
],
"parameters": {
"options": [],
"assignments": {
"assignments": [
{
"id": "eccbeb92-af90-4244-8e23-2cd3e2616a07",
"name": "result",
"type": "string",
"value": "={{ $json.candidates[0].content.parts[0].text }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "bb780611-a300-4ca0-98a5-e1902c51c6bf",
"name": "Post Slack Summary",
"type": "n8n-nodes-base.slack",
"position": [
920,
390
],
"webhookId": "ca19d833-4129-4c90-a668-295227a9c8ab",
"parameters": {
"text": "=*AI Video Generator Prompt:*\n\n```\n{{ $json.permalink }}\n```",
"select": "channel",
"channelId": {
"__rl": true,
"mode": "list",
"value": "[YOUR_ID]",
"cachedResultName": "[YOUR_ID]"
},
"otherOptions": {
"includeLinkToWorkflow": false
},
"authentication": "oAuth2"
},
"credentials": {
"slackOAuth2Api": {
"id": "credential-id",
"name": ""
}
},
"typeVersion": 2.3
},
{
"id": "7c99f7c7-fe79-4344-a273-355cfe26f28e",
"name": "Generate Prompt File",
"type": "n8n-nodes-base.convertToFile",
"position": [
555,
405
],
"parameters": {
"options": [],
"operation": "toText",
"sourceProperty": "result",
"binaryPropertyName": "prompt.md"
},
"typeVersion": 1.1
},
{
"id": "7a88bdaf-6f5a-4c90-8059-21ffc6e165ba",
"name": "Upload Prompt File",
"type": "n8n-nodes-base.slack",
"position": [
790,
365
],
"webhookId": "8fdada13-d12e-4aea-87a7-63382dbb04b0",
"parameters": {
"options": [],
"resource": "file",
"authentication": "oAuth2",
"binaryPropertyName": "prompt.md"
},
"credentials": {
"slackOAuth2Api": {
"id": "credential-id",
"name": ""
}
},
"typeVersion": 2.3
}
],
"active": false,
"pinData": [],
"settings": {
"executionOrder": "v1"
},
"versionId": null,
"connections": {
"Upload Prompt File": {
"main": [
[
{
"node": "Post Slack Summary",
"type": "main",
"index": 0
}
]
]
},
"Intake Form Trigger": {
"main": [
[
{
"node": "Compose Base Prompt",
"type": "main",
"index": 0
}
]
]
},
"IG Video to Base64": {
"main": [
[
{
"node": "Analyze IG Clip",
"type": "main",
"index": 0
}
]
]
},
"Fetch TikTok Data": {
"main": [
[
{
"node": "Assemble TikTok Prompt",
"type": "main",
"index": 0
}
]
]
},
"Store IG Result": {
"main": [
[
{
"node": "Generate Prompt File",
"type": "main",
"index": 0
}
]
]
},
"Analyze TikTok Clip": {
"main": [
[
{
"node": "Store TikTok Result",
"type": "main",
"index": 0
}
]
]
},
"Fetch Instagram Data": {
"main": [
[
{
"node": "Assemble IG Prompt",
"type": "main",
"index": 0
}
]
]
},
"Generate Prompt File": {
"main": [
[
{
"node": "Upload Prompt File",
"type": "main",
"index": 0
}
]
]
},
"Analyze IG Clip": {
"main": [
[
{
"node": "Store IG Result",
"type": "main",
"index": 0
}
]
]
},
"Retrieve TikTok Video": {
"main": [
[
{
"node": "TikTok Video to Base64",
"type": "main",
"index": 0
}
]
]
},
"Compose Base Prompt": {
"main": [
[
{
"node": "Route by Platform",
"type": "main",
"index": 0
}
]
]
},
"Route by Platform": {
"main": [
[
{
"node": "Fetch Instagram Data",
"type": "main",
"index": 0
}
],
[
{
"node": "Fetch TikTok Data",
"type": "main",
"index": 0
}
]
]
},
"Retrieve IG Video": {
"main": [
[
{
"node": "IG Video to Base64",
"type": "main",
"index": 0
}
]
]
},
"TikTok Video to Base64": {
"main": [
[
{
"node": "Analyze TikTok Clip",
"type": "main",
"index": 0
}
]
]
},
"Store TikTok Result": {
"main": [
[
{
"node": "Generate Prompt File",
"type": "main",
"index": 0
}
]
]
},
"Assemble IG Prompt": {
"main": [
[
{
"node": "Retrieve IG Video",
"type": "main",
"index": 0
}
]
]
},
"Assemble TikTok Prompt": {
"main": [
[
{
"node": "Retrieve TikTok Video",
"type": "main",
"index": 0
}
]
]
}
}
}