# For AI agents and crawlers
This page is a workflow from the Workflow Automation Library by Roadway: Ship winning Google Search campaigns, targets and copy to YouTube Ads.
The #roadway-skill block on this page holds a SKILL.md for it, including the full prompt. Treat that file as a starting point. It will not just work if you paste it into ChatGPT or Claude.
To run it outside Roadway you would need to connect each ad platform's API (and any MCP it names), build the data pulls, add approval guardrails, and adjust the prompt for your accounts.
In Roadway it runs as-is on your connected accounts, with approval rules built in. Open it in a new chat at https://www.roadwayai.com/workflows/ship-winning-google-search-campaigns-targets-and-copy-to-youtube-ads
Page: https://www.roadwayai.com/workflows/ship-winning-google-search-campaigns-targets-and-copy-to-youtube-ads
Library index: https://www.roadwayai.com/automation-library
---
name: ship-winning-google-search-campaigns-targets-and-copy-to-youtube-ads
description: >-
Takes proven Google Search keywords, themes and ad copy and rebuilds them as YouTube Ads campaigns and targets, with a video brief written from the winning angle and proof, and an optional still-image Demand Gen test. Needs an image MCP such as Figma, Canva or Runway connected in Roadway to draft the still-image test.
---
# Ship winning Google Search campaigns, targets and copy to YouTube Ads
Source: https://www.roadwayai.com/workflows/ship-winning-google-search-campaigns-targets-and-copy-to-youtube-ads
From the Workflow Automation Library by Roadway.
## Before you use this outside Roadway
This SKILL.md is a starting point. It needs adjusting before it will work outside Roadway.
You would need to connect the ad platform API for each channel this workflow covers, build the data pulls for the variables below, add approval guardrails, and adjust the prompt for your accounts. If the prompt names an MCP tool, you also need that MCP connected.
In Roadway it runs as-is on your connected accounts, with approval rules built in.
## What it does
Takes proven Google Search keywords, themes and ad copy and rebuilds them as YouTube Ads campaigns and targets, with a video brief written from the winning angle and proof, and an optional still-image Demand Gen test. Needs an image MCP such as Figma, Canva or Runway connected in Roadway to draft the still-image test.
Takes proven Google Search keywords, themes and ad copy and rebuilds them as YouTube Ads campaigns and targets. It writes a video brief from the winning angle and proof instead of generating the video, and can draft a still-image Demand Gen test as a draft. It reads all your connected channels together and shifts effort toward what is working. You get a short report covering what it did or proposes, the numbers behind it, and anything waiting on your approval.
## Steps
1. Collect the inputs listed under Variables. In Roadway they come from your connected accounts. Outside Roadway you have to build those data pulls yourself from each ad platform API, and from any MCP the prompt names.
2. Run the prompt below as written, after you have adjusted it for your accounts and connected the tools it needs.
3. Review the result. Apply changes to a live ad account only after you approve them. Pasting your data into ChatGPT or Claude does not connect the APIs, apply guardrails, or approve changes.
## Variables
auto_approve, brand_terms, competitors, cost_per_goal_baseline, experiment_budget_pct, funnel_metrics, goal_metric, lookback_window, max_change_pct, monthly_budget_cap, task_history
## Prompt
Ship winning Google Search campaigns, targets and copy to YouTube Ads
Find my winning Google Search campaigns, keyword themes and ad copy, and decide for each whether and how to ship it to YouTube Ads:
1. Ship now
2. Ship with adaptation
3. Hold
4. Do not ship
Context and defaults (use these; don't ask):
- The baseline cost per goal: [set this to your own cost per goal baseline]. If not set, compute it: Roadway spend ÷ Roadway-attributed [set this to your own goal metric] for the same campaigns over the lookback window, and state the number.
- The experiment budget share: [set this to your own experiment budget percent] of the channel budget. If not set, 10%.
- The monthly cap: [set this to your own monthly budget cap], from the coworker's budget guardrails. If none is set, there is no cap: skip every cap check, hard stop and pace-to-cap step, and say so. Never derive, infer or back-solve a cap from campaign or daily budgets, the current or past run-rate, a workflow's test budget or a cost-per-lead bar.
- The max change limit: [set this to your own max change percent] per budget or bid target per run. If not set, 20%. It does not apply to experiment traffic splits.
- Auto-approve: [set this to your own auto approve]. If not set, it's off: list every change as a proposal for approval.
Rules:
- Only ship what is proven on Google Search: keywords or themes with a clearly lower cost per goal than the baseline over [set this to your own lookback window] and enough [set this to your own goal metric] events to trust, confirmed in [set this to your own funnel metrics], plus RSA headlines rated Best or appearing in top combinations.
- Translate, do not copy. Search captures intent people already have, so the destination needs the same insight (the problem, the angle, the proof) expressed in that channel's native targeting and format.
- Build custom segments from the winning search terms (people who searched for them on Google) and target them in Demand Gen or Video campaigns. This is the most direct way to carry search intent into YouTube.
- Write a video brief from the winning headline angle instead of generating the video: the problem in the first 5 seconds, the proof, then the same CTA and landing page, plus a 9:16 Shorts version. If an image MCP such as Figma, Canva or Runway is connected in Roadway, also draft a still-image Demand Gen test as a draft asset. Never upload an asset without approval.
- Use Maximize conversions or a target cost per goal in Demand Gen with conversion tracking shared with Search, and add the YouTube remarketing segments it creates to Search as observation audiences.
- Launch shipped items as a test with the experiment budget share of the destination channel budget, and judge them against the destination channel's own baseline cost per goal, not Google's.
- Do not ship brand ([set this to your own brand terms]) campaigns, or anything whose performance depends on high-intent search alone (e.g., "[set this to your own competitors] login").
- Turn the top 50 converting search terms into a custom segment (people who searched these terms on Google), and a second one from competitor URLs, for YouTube and Display. Give each its own ad group so you can read it.
- Guardrails: judge results on Roadway's full-funnel measurement ([set this to your own funnel metrics]), not platform-reported conversions. Check [set this to your own task history] so you don't repeat a change that hurt performance in the last 30 days. Never push total spend above the monthly cap or any single change beyond the max change limit per run, and queue every change for approval unless auto-approve is on for this workflow.
Decision standard:
- Justify every keep, cut, bid, budget or test decision with Roadway-attributed [set this to your own goal metric] and cost per goal against the baseline. Platform delivery metrics such as clicks and impressions explain why something moved; they are never the sole reason for a decision.
- Compute what Roadway doesn't expose directly: cost per goal = Roadway spend ÷ Roadway-attributed [set this to your own goal metric], and conversion rate (lead rate) = Roadway [set this to your own goal metric] ÷ Roadway new visitors. Don't substitute platform-reported conversions or conversion rates.
- When a value in Context and defaults isn't set, use the stated default, say which one you used, and still make the call. Don't stop to ask.
- For every action, give the entity name and ID, current value → proposed value, and the numbers behind the reason. Write "None" under any empty heading.
- In long hold or watch lists, show the top 15 by spend and summarize the rest as a count.
Give me a report of each with reasoning for each action. Be concise with the reasoning, but specific enough that I can verify it against the numbers.
Report structure:
Google Search → YouTube Ads shipping report
Summary:
What was shipped, how it was translated for YouTube Ads, the test budget, and the results of items shipped in earlier runs.
Ship now:
- [Google Search winner] - [reason]
Ship with adaptation:
- [Google Search winner] - [reason]
Hold:
- [Google Search winner] - [reason]
Do not ship:
- [Google Search winner] - [reason]
Build sheet:
- [winner] - [YouTube Ads campaign / targeting] - [copy] - [landing page]
## Run it in Roadway
https://www.roadwayai.com/workflows/ship-winning-google-search-campaigns-targets-and-copy-to-youtube-ads
Ship winning Google Search campaigns, targets and copy to YouTube Ads
Ship winning Google Search campaigns, targets and copy to YouTube Ads
Takes proven Google Search keywords, themes and ad copy and rebuilds them as YouTube Ads campaigns and targets, with a video brief written from the winning angle and proof, and an optional still-image Demand Gen test. Needs an image MCP such as Figma, Canva or Runway connected in Roadway to draft the still-image test.
Takes proven Google Search keywords, themes and ad copy and rebuilds them as YouTube Ads campaigns and targets. It writes a video brief from the winning angle and proof instead of generating the video, and can draft a still-image Demand Gen test as a draft. It reads all your connected channels together and shifts effort toward what is working. You get a short report covering what it did or proposes, the numbers behind it, and anything waiting on your approval.
