irinabuht12-oss
Install Device Performance Split
Pick your agent. Every command is ready to paste.
npx skills add irinabuht12-oss/marketing-skills --skill device-performance-splitThe open skills CLI detects your agents (Claude Code, Cursor, Codex and 70+ more) and installs to the right folder. Add -g to install globally.
01
Install it
Run the command above, or upload the folder in Claude.
02
Ask naturally
Describe the task. Your agent loads device-performance-split when the request matches its description.
03
Name it if needed
If it does not trigger, say “use the device-performance-split skill”. In Codex, type $device-performance-split.
The skill itself
SKILL.md
25/ Device Performance Split — Google + Meta
What it does
Analyzes how your campaigns perform across mobile, desktop, and tablet. Identifies where device performance diverges significantly and recommends bid adjustments, campaign splits, or creative/landing page changes to capture the gap.
How it works
Claude segments all your campaign data by device type and compares CPA, CVR, CTR, bounce rate, and average order value. It identifies campaigns where one device significantly outperforms or underperforms others, then determines whether the issue is ad-side (creative not working on mobile), landing-page-side (poor mobile experience), or audience-side (different intent by device).
Practical example
Your B2B lead gen campaigns show desktop CPA at $41 with 3.8% CVR and mobile CPA at $78 with 1.6% CVR. But mobile accounts for 58% of clicks because that's where the impressions are. Claude digs deeper and finds the landing page form has 9 fields that are painful on mobile, and the page load time on mobile is 4.2 seconds vs 1.8 on desktop. Recommendation: create a simplified mobile form (3 fields), fix mobile page speed, and reduce mobile bid adjustments by 25% until the fixes are live to stop the bleeding.
What you get back
- Device performance comparison across all campaigns with key metrics
- Campaigns with the largest device performance gaps flagged
- Root cause analysis: is the gap from creative, landing page, or audience differences
- Bid adjustment recommendations by device per campaign
- Campaign split recommendations for cases where devices need completely different strategies
When to use it
- When CPA is higher than expected and you haven't checked device splits
- After landing page redesigns to verify mobile experience didn't break
- When mobile traffic share increases but conversions don't follow
- For ecommerce accounts where mobile browsing vs desktop purchasing creates attribution confusion
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?utm_source=github&utm_content=marketing-skills
Tips for Device Performance Split
- • Start a fresh session after installing so your agent picks up the new skill.
- • It is part of a pack with 40 skills. Install only the ones you need with --skill to keep triggers precise.
- • If two skills overlap, mention the one you want by name.
Questions about Device Performance Split
What does the Device Performance Split skill do?
Analyzes how your campaigns perform across mobile, desktop, and tablet. Identifies where device performance diverges significantly and recommends bid adjustments, campaign splits, or creative/landing page changes to capture the gap. Platform: Google and Meta.
How do I install Device Performance Split?
Run "npx skills add irinabuht12-oss/marketing-skills --skill device-performance-split" in your project. The skills CLI installs it for Claude Code, Cursor, Codex and 70+ other agents. In Claude on the web, upload the skill folder as a ZIP under Customize > Skills.
Does Device Performance Split work in Cursor and Codex?
Yes. Device Performance Split uses the open SKILL.md format, so it works in Claude Code, Claude, Cursor, OpenAI Codex, Gemini CLI, GitHub Copilot and other agents that support agent skills.
Is Device Performance Split free?
Device Performance Split is open source on GitHub. It is free to install; check the license before commercial use.
Who made Device Performance Split?
Device Performance Split is published by irinabuht12-oss in the irinabuht12-oss/marketing-skills repository, together with 39 other skills.
