Review n8n workflows from Slack with Claude Opus and GitHub skills
Ready for 3.0What this workflow does
This AI workflow has 34 nodes and runs on Slack events. Along the way it connects Slack, HTTP Request and OpenRouter Chat Model. It also calls raw.githubusercontent.com and api.github.com over HTTP.
How it runs
Trigger: On Slack events.
- Keep mentions and DMs (Filter): keeps only the items that match a condition
- Add Eyes Reaction (Slack): work with reaction
- Parse URL (Edit Fields (Set)): sets 5 fields: channel, ts, thread_ts…
- Valid URL? (If): checks a condition and branches into true / false
- Get Top-Level Workflow (n8n): get
- Remove Reaction (Bad URL) (Slack): remove (reaction)
- Fetch Review Checklist (HTTP Request): calls raw.githubusercontent.com
- Remove Reaction (Fetch Failed) (Slack): remove (reaction)
- Post Error: Bad URL (Slack): uses Slack
- Fetch Skill Files Index (HTTP Request): calls api.github.com
…plus 18 more steps. See the full node list below.
Services it uses
HTTP calls to: raw.githubusercontent.com, api.github.com
Before you upgrade to n8n 3.0
Nothing in this workflow is removed in n8n 3.0, so it should import and run after the upgrade.
- Still check Slack Trigger requires a signing secret on the Slack API credential (Slack: @mention or DM).
Nodes used (15)
- Slack Trigger
n8n-nodes-base.slackTrigger - Filter
n8n-nodes-base.filter - Slack
n8n-nodes-base.slack - Edit Fields (Set)
n8n-nodes-base.set - If
n8n-nodes-base.if - n8n
n8n-nodes-base.n8n - HTTP Request
n8n-nodes-base.httpRequest - Split Out
n8n-nodes-base.splitOut - Aggregate
n8n-nodes-base.aggregate - Merge
n8n-nodes-base.merge - AI Agent
@n8n/n8n-nodes-langchain.agent - Http Request Tool
n8n-nodes-base.httpRequestTool - Structured Output Parser
@n8n/n8n-nodes-langchain.outputParserStructured - OpenRouter Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenRouter - No Operation, do nothing
n8n-nodes-base.noOp
From the author
Quick overview A Slack bot that reviews any n8n workflow on demand. Mention it or DM it a workflow URL and it replies in-thread with a graded review, plain-English overview, and findings tiered as Must Fix, Should Fix, and Nice to Have. How it works 1.…