How do I install the Roas Forecasting skill?

Run npx skillmds@latest add irinabuht12-oss/roas-forecasting in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

What does the Roas Forecasting skill do?

19/ ROAS Forecasting — Google + Meta It is listed under Coding & Dev Tools on SkillMD.

Is Roas Forecasting safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Roas Forecasting?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Roas Forecasting free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Roas Forecasting?

irinabuht12-oss (@irinabuht12-oss) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Roas Forecasting by irinabuht12-oss

Name: Roas Forecasting
Author: irinabuht12-oss

File contents

19/ ROAS Forecasting — Google + Meta

What it does

Projects your ROAS for the next 30, 60, and 90 days based on current performance trends, seasonality patterns from your historical data, and planned budget or campaign changes. Gives you a range with confidence intervals, not a single number pretending to be precise.

How it works

Claude takes your trailing performance data, identifies the trend line (improving, declining, or stable), overlays seasonal patterns from the same period in prior years if available, and factors in any known upcoming changes (budget shifts, new campaigns, creative launches). It produces a forecast range showing best case, expected case, and conservative case.

Practical example

Your ecommerce account is averaging 4.2x ROAS in March. Claude's analysis shows ROAS typically dips 15-20% in April based on last year's data (post-spring-sale slowdown), your top creative set is showing early fatigue signals that will reduce efficiency by ~10% over the next 30 days, and you're planning a 20% budget increase which historically reduces marginal ROAS by 8-12%. 30-day forecast: 3.1x (conservative) to 3.6x (expected) to 4.0x (best case, if new creatives outperform).

What you get back

30/60/90 day ROAS projections with confidence ranges
Key assumptions behind each scenario (trend, seasonality, budget impact)
Risk factors that could push results toward the conservative end
Upside opportunities that could push toward best case
Revenue projections at each ROAS level tied to planned spend

When to use it

Monthly planning and client expectation setting
Before committing to budget increases with stakeholders
Quarterly business reviews where leadership wants revenue projections
When seasonal shifts are approaching and you need to model the impact on efficiency

Data access (Ryze MCP)

This skill works best with live account data. Connect the free Ryze MCP once and Claude reads your Google Ads, Meta Ads, GA4 and Search Console directly:

claude.ai / Claude Desktop: Settings → Connectors → Add custom connector → https://connector.get-ryze.ai/mcp
Claude Code: claude mcp add ryze --transport http https://connector.get-ryze.ai/mcp
Cursor: Settings → MCP → add the same URL

Setup guide: https://www.get-ryze.ai/how-to-connect-claude-to-google-meta-ads-mcp

---name: roas-forecastingdescription: 19/ ROAS Forecasting — Google + Meta---# 19/ ROAS Forecasting — Google + Meta## What it doesProjects your ROAS for the next 30, 60, and 90 days based on current performance trends, seasonality patterns from your historical data, and planned budget or campaign changes. Gives you a range with confidence intervals, not a single number pretending to be precise.## How it worksClaude takes your trailing performance data, identifies the trend line (improving, declining, or stable), overlays seasonal patterns from the same period in prior years if available, and factors in any known upcoming changes (budget shifts, new campaigns, creative launches). It produces a forecast range showing best case, expected case, and conservative case.## Practical exampleYour ecommerce account is averaging 4.2x ROAS in March. Claude's analysis shows ROAS typically dips 15-20% in April based on last year's data (post-spring-sale slowdown), your top creative set is showing early fatigue signals that will reduce efficiency by ~10% over the next 30 days, and you're planning a 20% budget increase which historically reduces marginal ROAS by 8-12%. 30-day forecast: 3.1x (conservative) to 3.6x (expected) to 4.0x (best case, if new creatives outperform).## What you get back- 30/60/90 day ROAS projections with confidence ranges- Key assumptions behind each scenario (trend, seasonality, budget impact)- Risk factors that could push results toward the conservative end- Upside opportunities that could push toward best case- Revenue projections at each ROAS level tied to planned spend## When to use it- Monthly planning and client expectation setting- Before committing to budget increases with stakeholders- Quarterly business reviews where leadership wants revenue projections- When seasonal shifts are approaching and you need to model the impact on efficiency## Data access (Ryze MCP)This skill works best with live account data. Connect the free Ryze MCP once and Claude reads your Google Ads, Meta Ads, GA4 and Search Console directly:- claude.ai / Claude Desktop: Settings → Connectors → Add custom connector → `https://connector.get-ryze.ai/mcp`- Claude Code: `claude mcp add ryze --transport http https://connector.get-ryze.ai/mcp`- Cursor: Settings → MCP → add the same URLSetup guide: https://www.get-ryze.ai/how-to-connect-claude-to-google-meta-ads-mcp

Frequently asked questions

Roas Forecasting