Sign in

/Catalogue/Prompt/irinabuht12-oss/irinabuht12-oss-marketing-skills-channel-mix-optimizer

Origin: github
Communityv0.1.0Prompt github.com/irinabuht12-oss/marketing-skills/tree/main/skills/channel-mix-optimizer

channel-mix-optimizer

Given your total budget, recommends the optimal split across Google Search, PMax, Meta prospecting, Meta retargeting, and any other active channels based on your last 60-90 days of marginal ROAS and CPA by channel. Tells you where each additional dollar produces the best return. Platform: Google and Meta.

by irinabuht12-oss · updated 1d ago · imported from GitHub

Watch · 0 Send for moderation
Installs0+0/7d
Security score98/100
Retention 14d0%
GitHub stars2K

Skill logic

Execution graph
User message
Prompt rewrites behaviour
Response

SKILL.md

View on GitHub ↗

15/ Channel Mix Optimizer — Google + Meta

What it does

Given your total budget, recommends the optimal split across Google Search, PMax, Meta prospecting, Meta retargeting, and any other active channels based on your last 60-90 days of marginal ROAS and CPA by channel. Tells you where each additional dollar produces the best return.

How it works

Claude calculates marginal efficiency for each channel — not average ROAS (which hides diminishing returns), but what your last dollar spent in each channel actually returned. It builds an efficiency curve per channel and recommends the allocation that maximizes total conversions or revenue within your budget constraint.

Practical example

You're spending $80K/month split evenly across 4 channels: Google Search ($20K), PMax ($20K), Meta prospecting ($20K), Meta retargeting ($20K). Claude's analysis shows Google Search still has headroom with marginal CPA at $34, Meta retargeting is maxed out with marginal CPA at $72 (the audience pool is exhausted), and PMax has middling marginal returns. Recommended reallocation: Google Search $32K, PMax $18K, Meta prospecting $22K, Meta retargeting $8K. Projected result: 23% more conversions at the same total spend.

What you get back

  • Current allocation vs recommended allocation with dollar amounts
  • Marginal CPA and ROAS for each channel at current and proposed spend levels
  • Projected total conversion and revenue impact of the reallocation
  • Diminishing returns curve for each channel showing where efficiency drops off
  • Sensitivity analysis showing how the recommendation changes if budget increases or decreases by 20%

When to use it

  • Monthly or quarterly budget allocation reviews
  • When total budget changes and you need to redistribute
  • When a new channel is added and you need to figure out how much to shift from existing channels
  • During planning season when building annual media plans with projected outcomes

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

Discussion

No comments yet — start the thread.

Sign in to join the discussion.

/More from irinabuht12-oss/marketing-skills

irinabuht12-oss· 1d agoCommunity
ab-test-analyzer

Prompts · v0.1.0

Statistical significance calculator for A/B test results with sample size requirements, segment breakdowns, and hypothesis generation. Use when feeding test results, checking statistical significance, calculating sample sizes, analyzing experiment outcomes, or generating next test ideas based on results. Platform: Google and Meta.

#ai-visibility#claude-code#claude-desktop

0 2K
irinabuht12-oss· 1d agoCommunity
ab-test-setup-and-analysis

Prompts · v0.1.0

Designs statistically valid split tests for ads, audiences, landing pages, or bid strategies. Calculates required sample sizes before you start, monitors results during the test, and calls winners when statistical significance is actually reached — not when you feel like one is winning. Platform: Google and Meta.

#ai-visibility#claude-code#claude-desktop

0 2K
irinabuht12-oss· 1d agoCommunity
account-structure-review

Prompts · v0.1.0

Evaluates your campaign and ad set structure against your actual goals and budget. Flags over-segmentation that fragments your data, under-segmentation that hides performance differences, budget allocation issues, and consolidation opportunities that would improve algorithmic delivery and your ability to optimize. Platform: Google and Meta.

#ai-visibility#claude-code#claude-desktop

0 2K
irinabuht12-oss· 1d agoCommunity
ad-copy-variant-generator

Prompts · v0.1.0

Analyzes your top performing ads, identifies what's working in the hooks, CTAs, messaging angles, and formats, then generates new variants that follow the same winning patterns while introducing enough variation to test meaningfully. Platform: Google and Meta.

#ai-visibility#claude-code#claude-desktop

0 2K