How to Outline a Make.com Scenario from a Trigger and Action List
Make scenarios fail when they insert Slack and mint a webhook. You connected HubSpot, Sheets, and Gmail. That is the whole chain. Not n8n.
The matching generator is the Make.com Scenario Outline from a Trigger and Action List prompt. Browse related cards in the PromptDig library (Browse more prompts). When a filled run survives, share the version you actually use (Share a prompt).
Chain Trigger then Actions in order
Outline a Make.com scenario from pasted triggers and actions. No invented apps, webhooks, or mappings. Start by filling Inputs, not by asking the model to remember last week's run. If a field is blank, write NONE or NOT IN INPUTS and leave it blank through Generate. The card is built so the model cannot honestly invent a number, owner, URL, or command that you did not paste.
Paste these fields before you hit run:
Make.com plan and region I use: [Plan]
Trigger module I already connected: [Trigger]
Action modules I already connected, in order: [Actions]
Field mappings I can prove (source -> target): [Map]
Filters and routers I allow (or NONE): [Filters]
Error handler I allow (or NONE): [Errors]
Webhook URL I may print (or NONE): [Hook]
What I must never call: [Never]
Words I must not use: [Banned]
Scheduling I can prove (or NONE): [Schedule]
That inventory is the honesty ledger. Anything that does not appear there is forbidden in the draft. If you catch yourself adding a nice-to-have after the run, you are no longer using the card. You are ghostwriting. Put the extra fact in Inputs and run again.
Map only the field pairs you proved
Generate is numbered on purpose. Do not skip a step because the first paragraph looked done. The early steps exist to stop later prose from smuggling claims.
Walk the Generate list in order:
- Honesty ledger: plan, trigger, every action app, mappings, hook, schedule. Forbidden: apps and URLs not listed.
- Module chain: Trigger then Actions in order. Number them. Do not insert a router unless Filters names one.
- Mapping table: only Map rows. Missing fields write NOT IN INPUTS rather than guessing.
- Filters: only Filters. If NONE, linear chain.
- Errors: only Errors. If NONE, default scenario-level halt, do not invent a Slack alert.
- Hook: only Hook. If NONE, no webhook URL.
- Schedule: only Schedule. If NONE and Trigger is not polling, write schedule not specified.
- Compliance pass: quote Banned words, n8n nodes, invented apps. Cut them.
If a step asks for a version lock, quote the version from Inputs in the output. If a step asks for a refuse list, keep the refuse list in the published artifact, not in a sidebar you delete. Reviewers should see what the model was not allowed to do.
No router unless Filters named one
Most failures are the same shape: a missing field gets a confident fill. A conversion rate appears. A Gradle task appears. A flash point appears. A caption appears on a job that asked for slide text only. Your review is to search the draft for numbers, names, and commands, then grep Inputs. No match means cut.
Honor the constraints as hard stops, not vibes:
- Make.com scenario outline only. Not n8n, Zapier, Jira automation, or GitHub Actions.
- Never invent an app, webhook, or mapping.
- Do not add modules that are not in Trigger or Actions.
- If Hook is NONE, do not mint a URL.
- No emojis.
When the card says not legal advice, not certification, not an exam dump, or not a caption engine, that sentence belongs at the top of the output. Deleting it to look more finished is how you inherit risk.
Not n8n, Zapier, or GitHub Actions
Finish with the compliance pass the prompt already asks for. Quote the banned-word hits. Cut them. Print character counts when the job has a cap. Print word counts when the job has a budget. List gaps as gaps. Five missing facts are more useful than one smooth paragraph.
Tags on the card (make.com scenario outline, integromat scenario from list, no invented make apps) are a reminder of the job shape, not an invitation to wander into a neighboring cluster. If you need a different surface, open a different PromptDig card rather than stretching this one.
Fill the card, then run
Replace every bracket. Run on ChatGPT, Claude, or Gemini. Read the ledger first, then the artifact. If the model invents a commit, KPI, DOI, PEL, bid, or logo, discard the run. Tighten Inputs. Run again. Share the filled card that survived, not the first draft that sounded done.