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": "Roaster",
"nodes": [
{
"parameters": {},
"type": "n8n-nodes-base.manualTrigger",
"typeVersion": 1,
"position": [
-640,
-256
],
"id": "1158b13f-21cd-4363-a0f1-3326f2ed505d",
"name": "When clicking \u2018Execute workflow\u2019"
},
{
"parameters": {
"authentication": "oAuth2",
"operation": "get",
"guildId": {
"__rl": true,
"value": "https://discord.com/channels/1404025893466144768",
"mode": "url",
"__regex": "https:\\/\\/discord.com\\/channels\\/([0-9]+)"
},
"channelId": {
"__rl": true,
"value": "https://discord.com/channels/1404025893466144768/1406611739696431177",
"mode": "url",
"__regex": "https:\\/\\/discord.com\\/channels\\/[0-9]+\\/([0-9]+)"
}
},
"type": "n8n-nodes-base.discord",
"typeVersion": 2,
"position": [
-400,
-256
],
"id": "ea9a240c-e9be-4fab-978b-ca6dd25a4b4b",
"name": "Get a channel",
"credentials": {
"discordOAuth2Api": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"resource": "message",
"guildId": {
"__rl": true,
"value": "1404025893466144768",
"mode": "list",
"cachedResultName": "AiStoryTelling",
"cachedResultUrl": "https://discord.com/channels/1404025893466144768"
},
"channelId": {
"__rl": true,
"value": "1406611739696431177",
"mode": "list",
"cachedResultName": "roaster",
"cachedResultUrl": "https://discord.com/channels/1404025893466144768/1406611739696431177"
},
"content": "={{ $json.text }}",
"options": {}
},
"type": "n8n-nodes-base.discord",
"typeVersion": 2,
"position": [
704,
-240
],
"id": "99181712-0cdc-4ab8-a505-fff898dbbcb2",
"name": "Send a message",
"credentials": {
"discordBotApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"rule": {
"interval": [
{
"field": "cronExpression",
"expression": "0/30 * * * * *"
}
]
}
},
"type": "n8n-nodes-base.scheduleTrigger",
"typeVersion": 1.2,
"position": [
-656,
-432
],
"id": "dd8a45a4-f309-4c07-b4ac-b19a5163829d",
"name": "Schedule Trigger"
},
{
"parameters": {
"model": "qwen2.5:7b-instruct-q4_K_M",
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.lmChatOllama",
"typeVersion": 1,
"position": [
320,
-80
],
"id": "ff26f566-5913-48d7-b506-3918a944573d",
"name": "Ollama Chat Model1",
"credentials": {
"ollamaApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"conditions": {
"options": {
"caseSensitive": true,
"leftValue": "",
"typeValidation": "strict",
"version": 2
},
"conditions": [
{
"id": "710deaac-62ed-4046-9497-f890a35fdf7b",
"leftValue": "={{ $json.author.username }}",
"rightValue": "Roaster",
"operator": {
"type": "string",
"operation": "equals",
"name": "filter.operator.equals"
}
},
{
"id": "abbe7c0f-0484-4a15-b26b-0c8ee92ef740",
"leftValue": "={{ $json.author.bot }}",
"rightValue": "true",
"operator": {
"type": "string",
"operation": "equals",
"name": "filter.operator.equals"
}
}
],
"combinator": "and"
},
"options": {}
},
"type": "n8n-nodes-base.if",
"typeVersion": 2.2,
"position": [
32,
-256
],
"id": "7d377005-30be-426a-9bd1-9949c0003b73",
"name": "If"
},
{
"parameters": {
"jsCode": "const input = $input.first().json.output;\nconst tagRe = /<\\s*\\/?\\s*think\\b[^>]*>/gi; \n\nlet depth = 0;\nlet last = 0;\nlet out = \"\";\n\n for (const m of input.matchAll(tagRe)) {\n const i = m.index;\n if (i == null) continue;\n\n // append plain text only when we're not inside a <think> block\n if (depth === 0) out += input.slice(last, i);\n\n const tag = m[0];\n const isClosing = /^<\\s*\\/\\s*think/i.test(tag);\n const isSelfClosing = /^<\\s*think\\b[^>]*\\/\\s*>/i.test(tag);\n\n if (isClosing) {\n depth = Math.max(0, depth - 1);\n } else if (!isSelfClosing) {\n depth += 1; // entering a <think> block\n }\n last = i + tag.length; // skip the tag itself\n }\n\n // add any trailing text if we're not still inside a <think> block\n if (depth === 0 && last < input.length) {\n out += input.slice(last);\n }\n\n\nreturn { \"output\": out.toString() };\n\n"
},
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
480,
304
],
"id": "1e173817-2b07-402d-9502-93f279b9c26c",
"name": "Code"
},
{
"parameters": {
"resource": "message",
"operation": "get",
"guildId": {
"__rl": true,
"value": "1404025893466144768",
"mode": "list",
"cachedResultName": "AiStoryTelling",
"cachedResultUrl": "https://discord.com/channels/1404025893466144768"
},
"channelId": {
"__rl": true,
"value": "1406611739696431177",
"mode": "list",
"cachedResultName": "roaster",
"cachedResultUrl": "https://discord.com/channels/1404025893466144768/1406611739696431177"
},
"messageId": "={{ $json.last_message_id }}",
"options": {}
},
"type": "n8n-nodes-base.discord",
"typeVersion": 2,
"position": [
-176,
-256
],
"id": "a8239c01-85f2-4ee1-a8db-98b847d02bb8",
"name": "Get a message",
"credentials": {
"discordBotApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"promptType": "define",
"text": "=You are Roaster, a stand-up comic bot for Discord. Your job is to deliver a single, vicious roast about the author\u2019s last message. You must be witty, punchy, and brutal. YOU WILL REPLY IN THE LANGUAGE OF THE CONTENT. You are the most sarcastic creature ever invented, and you will give your mind boggling witty roasting reply to user called \"{{ $json.author.global_name }}\" that made the fatal mistake of saying \"{{ $json.content }}\". YOUR REPLY SHOULD BE ONLY 1 PARAGRAPH of MAX 50 words. do not start the reply with \"oh\" or \"ah\".",
"batching": {}
},
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"typeVersion": 1.7,
"position": [
320,
-240
],
"id": "914d561a-e32a-471e-aefd-4c976e0cb5c4",
"name": "Basic LLM Chain"
}
],
"connections": {
"When clicking \u2018Execute workflow\u2019": {
"main": [
[
{
"node": "Get a channel",
"type": "main",
"index": 0
}
]
]
},
"Get a channel": {
"main": [
[
{
"node": "Get a message",
"type": "main",
"index": 0
}
]
]
},
"Send a message": {
"main": [
[]
]
},
"Schedule Trigger": {
"main": [
[
{
"node": "Get a channel",
"type": "main",
"index": 0
}
]
]
},
"Ollama Chat Model1": {
"ai_languageModel": [
[
{
"node": "Basic LLM Chain",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"If": {
"main": [
[],
[
{
"node": "Basic LLM Chain",
"type": "main",
"index": 0
}
]
]
},
"Code": {
"main": [
[]
]
},
"Get a message": {
"main": [
[
{
"node": "If",
"type": "main",
"index": 0
}
]
]
},
"Basic LLM Chain": {
"main": [
[
{
"node": "Send a message",
"type": "main",
"index": 0
}
]
]
}
},
"active": false,
"settings": {
"executionOrder": "v1"
},
"versionId": "f86920cb-f290-4420-842f-3d7b4a503084",
"meta": {
"templateCredsSetupCompleted": true
},
"id": "rO8CM3NmesxRvReZ",
"tags": []
}
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.
discordBotApidiscordOAuth2ApiollamaApi
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
Roaster. Uses discord, lmChatOllama, chainLlm. Event-driven trigger; 9 nodes.
Source: https://github.com/gctanita/understandingImageGeneration/blob/1879da0429c9519c247337194a95429e43d6c7c6/n8n/Roaster.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.
Github_To_Discord_Agent. Uses github, chainLlm, lmChatOllama, discord. Event-driven trigger; 15 nodes.
Episode 11: AI shorts factory app. Uses httpRequest, googleSheets, lmChatOpenAi, lmChatOllama. Event-driven trigger; 96 nodes.
My workflow 53. Uses formTrigger, httpRequest, lmChatOpenAi, form. Event-driven trigger; 74 nodes.
Episode 23: UGC with nanobanana. Uses lmChatOpenAi, lmChatOllama, lmChatDeepSeek, lmChatOpenRouter. Event-driven trigger; 74 nodes.
This workflow is perfect for creators, solopreneurs, and personal brands who want to consistently publish bold, high-performing content on X (Twitter) — without writing a single line themselves. After