This workflow follows the Executecommand → HTTP Request recipe pattern — see all workflows that pair these two integrations.
The workflow JSON
Copy or download the full n8n JSON below. Paste it into a new n8n workflow, add your credentials, activate. Full import guide →
{
"name": "KZ-02-Classification",
"nodes": [
{
"parameters": {
"httpMethod": "POST",
"path": "events",
"responseMode": "responseNode",
"options": {}
},
"name": "Webhook /events",
"type": "n8n-nodes-base.webhook",
"typeVersion": 2,
"position": [
240,
300
]
},
{
"parameters": {
"conditions": {
"string": [
{
"value1": "={{$json.body.workflow}}",
"operation": "equal",
"value2": "02-classification"
}
]
}
},
"name": "Route 02",
"type": "n8n-nodes-base.if",
"typeVersion": 2,
"position": [
460,
300
]
},
{
"parameters": {
"tableId": "clips",
"filterType": "manual",
"matchType": "allFilters",
"filters": {
"conditions": [
{
"keyName": "clip_id",
"condition": "eq",
"keyValue": "={{$json.body.clip_id}}"
}
]
}
},
"name": "Load clip",
"type": "n8n-nodes-base.supabase",
"typeVersion": 1,
"position": [
680,
300
],
"credentials": {
"supabaseApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"command": "=set -e;\nKEY=\"$(jq -r '.[0].storage_key' <<<'{{JSON.stringify($json)}}')\";\nCLIP_ID=\"$(jq -r '.[0].clip_id' <<<'{{JSON.stringify($json)}}')\";\nDUR=\"$(jq -r '.[0].duration_s' <<<'{{JSON.stringify($json)}}')\";\nSRC=\"/tmp/${CLIP_ID}.mp4\";\nrclone copy r2:${R2_BUCKET}/${KEY} /tmp/;\nmkdir -p /tmp/${CLIP_ID};\nffmpeg -y -i ${SRC} -vf \"fps=5/${DUR},scale=720:-2\" /tmp/${CLIP_ID}/frame_%02d.jpg > /dev/null 2>&1;\nls /tmp/${CLIP_ID}/*.jpg | head -n 5;"
},
"name": "Sample 5 frames",
"type": "n8n-nodes-base.executeCommand",
"typeVersion": 1,
"position": [
900,
300
]
},
{
"parameters": {
"url": "https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-flash:generateContent",
"method": "POST",
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth",
"sendHeaders": true,
"headerParameters": {
"parameters": [
{
"name": "x-goog-api-key",
"value": "={{$env[\"GEMINI_API_KEY\"]}}"
}
]
},
"sendBody": true,
"specifyBody": "json",
"jsonBody": "={\n \"contents\":[{\"parts\":[{\"text\":\"You analyze landscaping footage. Return strict JSON: {service, phase, scene, time_of_day, weather, mood, overgrowth_level, water_state, machinery_visible, people_visible, viral_kind}. Schema documented at /prompts/. No prose.\"},{\"inline_data\":{\"mime_type\":\"image/jpeg\",\"data\":\"{{$json.frame1_b64}}\"}},{\"inline_data\":{\"mime_type\":\"image/jpeg\",\"data\":\"{{$json.frame2_b64}}\"}},{\"inline_data\":{\"mime_type\":\"image/jpeg\",\"data\":\"{{$json.frame3_b64}}\"}},{\"inline_data\":{\"mime_type\":\"image/jpeg\",\"data\":\"{{$json.frame4_b64}}\"}},{\"inline_data\":{\"mime_type\":\"image/jpeg\",\"data\":\"{{$json.frame5_b64}}\"}}]}],\n \"generationConfig\":{\"response_mime_type\":\"application/json\",\"temperature\":0.2}\n}"
},
"name": "Gemini Classify",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
1120,
220
]
},
{
"parameters": {
"command": "=whisper-ctranslate2 --model large-v3 --language auto --output_format srt --vad_filter True /tmp/{{$json.clip_id}}.mp4 > /tmp/{{$json.clip_id}}.srt && cat /tmp/{{$json.clip_id}}.srt"
},
"name": "Whisper Full",
"type": "n8n-nodes-base.executeCommand",
"typeVersion": 1,
"position": [
1120,
360
]
},
{
"parameters": {
"command": "=ffmpeg -i /tmp/{{$json.clip_id}}.mp4 -filter:v \"select='gt(scene,0.4)',showinfo\" -f null - 2>&1 | grep showinfo | awk -F 'pts_time:' '{print $2}' | awk '{print $1}' | paste -sd, -"
},
"name": "Scene Cuts",
"type": "n8n-nodes-base.executeCommand",
"typeVersion": 1,
"position": [
1120,
500
]
},
{
"parameters": {
"url": "https://api.openai.com/v1/chat/completions",
"method": "POST",
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth",
"sendHeaders": true,
"headerParameters": {
"parameters": [
{
"name": "Authorization",
"value": "=Bearer {{$env[\"OPENAI_API_KEY\"]}}"
}
]
},
"sendBody": true,
"specifyBody": "json",
"jsonBody": "={\n \"model\":\"gpt-4o\",\n \"temperature\":0.3,\n \"response_format\":{\"type\":\"json_object\"},\n \"messages\":[\n {\"role\":\"system\",\"content\":\"You are a viral short-form editor for landscaping/cleanup. Pick 3-8 candidate sub-clips. Use the moment-detection prompt at /prompts/moment-detection.md. Return JSON {candidates:[...]}\"},\n {\"role\":\"user\",\"content\":\"DURATION: {{$json.duration_s}}s\\nTAGS: {{$json.gemini_json}}\\nCUTS: {{$json.cuts_csv}}\\nTRANSCRIPT:\\n{{$json.srt}}\"}\n ]\n}"
},
"name": "GPT-4o Moments",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
1340,
380
]
},
{
"parameters": {
"batchSize": 1,
"options": {}
},
"name": "Loop Candidates",
"type": "n8n-nodes-base.splitInBatches",
"typeVersion": 3,
"position": [
1560,
380
]
},
{
"parameters": {
"url": "https://api.anthropic.com/v1/messages",
"method": "POST",
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth",
"sendHeaders": true,
"headerParameters": {
"parameters": [
{
"name": "x-api-key",
"value": "={{$env[\"ANTHROPIC_API_KEY\"]}}"
},
{
"name": "anthropic-version",
"value": "2023-06-01"
}
]
},
"sendBody": true,
"specifyBody": "json",
"jsonBody": "={\n \"model\":\"claude-sonnet-4-6\",\n \"max_tokens\":700,\n \"temperature\":0.2,\n \"system\":\"Use the viral-scoring rubric in /prompts/viral-scoring.md. Return strict JSON only.\",\n \"messages\":[{\"role\":\"user\",\"content\":\"Candidate: {{JSON.stringify($json.candidate)}}\\nContext: {{JSON.stringify($json.context)}}\"}]\n}"
},
"name": "Claude Score",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
1780,
380
]
},
{
"parameters": {
"url": "https://api.anthropic.com/v1/messages",
"method": "POST",
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth",
"sendHeaders": true,
"headerParameters": {
"parameters": [
{
"name": "x-api-key",
"value": "={{$env[\"ANTHROPIC_API_KEY\"]}}"
},
{
"name": "anthropic-version",
"value": "2023-06-01"
}
]
},
"sendBody": true,
"specifyBody": "json",
"jsonBody": "={\n \"model\":\"claude-sonnet-4-6\",\n \"max_tokens\":800,\n \"temperature\":0.7,\n \"system\":\"Use /prompts/hook-generator.md. 3 EN + 2 RU. Strict JSON.\",\n \"messages\":[{\"role\":\"user\",\"content\":\"Clip: {{JSON.stringify($json.metadata)}}\\nCandidate: {{JSON.stringify($json.candidate)}}\\nForbidden: {{JSON.stringify($json.forbidden_ids)}}\"}]\n}"
},
"name": "Claude Hooks",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
2000,
380
]
},
{
"parameters": {
"url": "https://api.anthropic.com/v1/messages",
"method": "POST",
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth",
"sendHeaders": true,
"headerParameters": {
"parameters": [
{
"name": "x-api-key",
"value": "={{$env[\"ANTHROPIC_API_KEY\"]}}"
},
{
"name": "anthropic-version",
"value": "2023-06-01"
}
]
},
"sendBody": true,
"specifyBody": "json",
"jsonBody": "={\n \"model\":\"claude-sonnet-4-6\",\n \"max_tokens\":1200,\n \"temperature\":0.6,\n \"system\":\"Use /prompts/caption-generator.md. Return JSON per platform.\",\n \"messages\":[{\"role\":\"user\",\"content\":\"Hook: {{$json.hook}}\\nClip: {{JSON.stringify($json.metadata)}}\\nCTA: {{$json.cta_strategy}}\"}]\n}"
},
"name": "Claude Captions",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
2220,
380
]
},
{
"parameters": {
"tableId": "candidates",
"dataMode": "autoMapInputData"
},
"name": "Insert Candidate",
"type": "n8n-nodes-base.supabase",
"typeVersion": 1,
"position": [
2440,
380
],
"credentials": {
"supabaseApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"url": "={{$env[\"N8N_EVENT_BUS_URL\"]}}/events",
"method": "POST",
"sendBody": true,
"specifyBody": "json",
"jsonBody": "={\n \"workflow\": \"03-edit-render\",\n \"candidate_id\": \"{{$json.candidate_id}}\"\n}"
},
"name": "Enqueue Render",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
2660,
380
]
}
],
"connections": {
"Webhook /events": {
"main": [
[
{
"node": "Route 02",
"type": "main",
"index": 0
}
]
]
},
"Route 02": {
"main": [
[
{
"node": "Load clip",
"type": "main",
"index": 0
}
]
]
},
"Load clip": {
"main": [
[
{
"node": "Sample 5 frames",
"type": "main",
"index": 0
},
{
"node": "Whisper Full",
"type": "main",
"index": 0
},
{
"node": "Scene Cuts",
"type": "main",
"index": 0
}
]
]
},
"Sample 5 frames": {
"main": [
[
{
"node": "Gemini Classify",
"type": "main",
"index": 0
}
]
]
},
"Gemini Classify": {
"main": [
[
{
"node": "GPT-4o Moments",
"type": "main",
"index": 0
}
]
]
},
"Whisper Full": {
"main": [
[
{
"node": "GPT-4o Moments",
"type": "main",
"index": 0
}
]
]
},
"Scene Cuts": {
"main": [
[
{
"node": "GPT-4o Moments",
"type": "main",
"index": 0
}
]
]
},
"GPT-4o Moments": {
"main": [
[
{
"node": "Loop Candidates",
"type": "main",
"index": 0
}
]
]
},
"Loop Candidates": {
"main": [
[
{
"node": "Claude Score",
"type": "main",
"index": 0
}
]
]
},
"Claude Score": {
"main": [
[
{
"node": "Claude Hooks",
"type": "main",
"index": 0
}
]
]
},
"Claude Hooks": {
"main": [
[
{
"node": "Claude Captions",
"type": "main",
"index": 0
}
]
]
},
"Claude Captions": {
"main": [
[
{
"node": "Insert Candidate",
"type": "main",
"index": 0
}
]
]
},
"Insert Candidate": {
"main": [
[
{
"node": "Enqueue Render",
"type": "main",
"index": 0
}
]
]
}
},
"settings": {
"executionOrder": "v1"
},
"tags": [
"kontent-zavod",
"classification",
"ai"
]
}
Credentials you'll need
Each integration node will prompt for credentials when you import. We strip credential IDs before publishing — you'll add your own.
supabaseApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
KZ-02-Classification. Uses supabase, executeCommand, httpRequest. Webhook trigger; 14 nodes.
Source: https://github.com/alexdmitrievi/Kontent_zavod_podryadpro/blob/claude/ai-content-factory-design-hzhVn/workflows/02-classification.json — original creator credit. Request a take-down →
Related workflows
Workflows that share integrations, category, or trigger type with this one. All free to copy and import.
Mastodon2MemosGitHubNotion. Uses httpRequest, executeCommand, s3, github. Webhook trigger; 34 nodes.
HTTP Request, Execute Command, S3 +2
2. Refresh Pipedrive tokens. Uses stopAndError, stickyNote, supabase, httpRequest. Webhook trigger; 29 nodes.
Stop And Error, Supabase, HTTP Request
This workflow provides an OAuth 2.0 auth token refresh process for better control. Developers can utilize it as an alternative to n8n's built-in OAuth flow to achieve improved control and visibility.
Stop And Error, Supabase, HTTP Request
Buildnbloom - Typeform to Tier 1 Call. Uses supabase, airtable, httpRequest. Webhook trigger; 17 nodes.
Supabase, Airtable, HTTP Request
Ai Assistant Workflow. Uses supabase, httpRequest, emailSend. Webhook trigger; 14 nodes.
Supabase, HTTP Request, Email Send