# For AI agents and crawlers
This page is a workflow from the Workflow Automation Library by Roadway: Swap in weather and local event creative by market.
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/swap-in-weather-and-local-event-creative-by-market
Page: https://www.roadwayai.com/workflows/swap-in-weather-and-local-event-creative-by-market
Library index: https://www.roadwayai.com/automation-library
---
name: swap-in-weather-and-local-event-creative-by-market
description: >-
An opt-in workflow for ecommerce brands. Checks the forecast and local events by market, then swaps in matching ad copy and adjusts bids, like rain gear before a storm. Needs the Shopify MCP connected in Roadway to check stock.
---
# Swap in weather and local event creative by market
Source: https://www.roadwayai.com/workflows/swap-in-weather-and-local-event-creative-by-market
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
An opt-in workflow for ecommerce brands. Checks the forecast and local events by market, then swaps in matching ad copy and adjusts bids, like rain gear before a storm. Needs the Shopify MCP connected in Roadway to check stock.
Each run, the agent checks the forecast and local events for your markets with web research, then matches them to products that have sold well in those conditions before. For a match it swaps in fitting ad copy and creative and adjusts bids in that market, and it only pushes products the Shopify MCP shows are in stock. Everything rolls back after the weather or event passes. The weather and event data come from web research, not from the Shopify MCP. It is opt-in and built for ecommerce brands.
## 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, funnel_metrics, goal_metric, inventory_levels, local_conditions, margin_data, max_change_pct, monthly_budget_cap, seasonality_calendar, target_geos, task_history
## Prompt
Swap in weather and local event creative by market
Read [set this to your own local conditions] for the next 3-7 days across [set this to your own target geos], and decide for each market and product group:
1. Swap creative and raise bids
2. Swap creative only
3. Lower bids
4. No change
Context and defaults (use these; don't ask):
- Weather and local events by market: [set this to your own local conditions]. If it isn't set, look up the forecast and local event listings with web research on each run and say which sources you used. If that fails, say so and skip the rules that depend on it.
- The countries and regions to target: [set this to your own target geos]. If it isn't available, say so and skip the rules that depend on it.
- The seasonality calendar: [set this to your own seasonality calendar]. If not set, assume no seasonal adjustment and say so.
- Inventory by product (units and days of cover), read through the Shopify MCP: [set this to your own inventory levels]. If it isn't available, say so and skip the rules that depend on it.
- Product margin data (price, cost of goods, shipping cost): [set this to your own margin data]. If it isn't available, say so and skip the rules that depend on it.
- 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:
- This is an opt-in workflow for ecommerce brands. If the business does not sell products online, say so and stop.
- Weather and event data come from web research, not from the Shopify MCP. Use the Shopify MCP only to check stock before you push a product. If it is not connected, say so and treat stock as unknown.
- Look for a forecast change of 8+ degrees, rain, snow or heat across 2+ days, or a local event with 5,000+ attendees, in a market that makes a meaningful share of revenue. If not set, 3%+ of revenue.
- Map conditions to products using [set this to your own seasonality calendar] and past sales by weather in Roadway revenue data: only act on pairings that have clearly lifted revenue before. If not set, a lift of at least 10%.
- Swap creative and raise bids by up to [set this to your own max change percent] for the market, and change the same market at most once a week. Swap creative only when stock or margin is weak ([set this to your own inventory levels], [set this to your own margin data]).
- Lower bids on products that suffer (outdoor items in a storm), but only where delivery risk is real, such as heavy items in bad weather.
- Roll everything back 24 hours after the condition passes, and keep tone sensitive to disasters: never run weather-based promos during emergencies.
- 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:
Local conditions creative report
Summary:
The markets and conditions found, the creative swaps and bid changes, and the gain.
Swap creative and raise bids:
- [market] - [reason]
Swap creative only:
- [market] - [reason]
Lower bids:
- [market] - [reason]
No change:
- [market] - [reason]
## Run it in Roadway
https://www.roadwayai.com/workflows/swap-in-weather-and-local-event-creative-by-market
Swap in weather and local event creative by market
Swap in weather and local event creative by market
An opt-in workflow for ecommerce brands. Checks the forecast and local events by market, then swaps in matching ad copy and adjusts bids, like rain gear before a storm. Needs the Shopify MCP connected in Roadway to check stock.
Each run, the agent checks the forecast and local events for your markets with web research, then matches them to products that have sold well in those conditions before. For a match it swaps in fitting ad copy and creative and adjusts bids in that market, and it only pushes products the Shopify MCP shows are in stock. Everything rolls back after the weather or event passes. The weather and event data come from web research, not from the Shopify MCP. It is opt-in and built for ecommerce brands.
