Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Device Performance Split

ASecurity

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.

1,590 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentsgoperformance

Works with

claude codeclaude desktopcursorclimcp

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add irinabuht12-oss/marketing-skills --skill device-performance-split --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Device Performance Split?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Device Performance Split
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/irinabuht12-oss-device-performance-split/badge)](https://www.skillsdirectory.com/skills/irinabuht12-oss-device-performance-split)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: device-performance-split
description: 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.
metadata:
  platform: Google and Meta
---

# 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

Attribution

irinabuht12-ossirinabuht12-oss
View sourceMore from irinabuht12-oss →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →