agentmods.dev

device-performance-split

device-performance-split is a skill for Claude Code from amirjahfar1/Google-Search-Console-GSC-MCP. It costs 33 tokens per session (386 once invoked), scanned A, original, MIT.

A Search Console comparison of a website’s search performance on mobile phones, desktop computers, and tablets. It compares clicks, impressions, click-through rate, and average ranking position.

In plain words
What is it for?
Use it to investigate mobile search problems, compare device-specific rankings and traffic, and find queries with desktop clicks but almost no mobile clicks.
Why use it?
Overall figures can hide a problem affecting only one type of device. The comparison highlights mobile queries that perform much worse than desktop queries.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the google-search-console-gsc-mcp plugin — 12 skills, 1 MCP server shipped together

not rated 0repo 1mo ago A scan 33 tokens original MIT

Good fit Use it to investigate mobile search problems, compare device-specific rankings and traffic, and find queries with desktop clicks but almost no mobile clicks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/amirjahfar1/google-search-console-gsc-mcp/device-performance-split
View source ↗ amirjahfar1/Google-Search-Console-GSC-MCP
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add amirjahfar1/Google-Search-Console-GSC-MCP --skill device-performance-split
Clone the repo
git clone --depth 1 https://github.com/amirjahfar1/Google-Search-Console-GSC-MCP

Made for: Claude Code.

Or install google-search-console-gsc-mcp, the plugin that ships this one along with the rest of its 12 skills, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for device-performance-split

README.md
[![agentmods](https://agentmods.dev/badge/skills/amirjahfar1/google-search-console-gsc-mcp/device-performance-split/github.svg)](https://agentmods.dev/skills/amirjahfar1/google-search-console-gsc-mcp/device-performance-split)
Your own site
<a href="https://agentmods.dev/skills/amirjahfar1/google-search-console-gsc-mcp/device-performance-split"><img src="https://agentmods.dev/badge/skills/amirjahfar1/google-search-console-gsc-mcp/device-performance-split/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for device-performance-split

Your own site · 80×15
<a href="https://agentmods.dev/skills/amirjahfar1/google-search-console-gsc-mcp/device-performance-split"><img src="https://agentmods.dev/badge/skills/amirjahfar1/google-search-console-gsc-mcp/device-performance-split.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 386 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00033 $0.00386
Opus 5 $0.00016 $0.00193
Sonnet 5 $0.00007 $0.00077
Haiku 4.5 $0.00003 $0.00039

Measured 10d ago against content hash b5884313d36e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

device-performance-split scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/device-performance-split/SKILL.md · 34 lines

What it actually says

Device Performance Split

Compare clicks, impressions, CTR, and position across MOBILE, DESKTOP, and TABLET to catch device-specific problems. Google is mobile-first, so mobile issues carry the most weight.

Steps

  1. Call list_properties to confirm the exact site_url.
  2. Call get_advanced_search_analytics three times, once per device, each with:
    • dimensions=query
    • filters=[{"dimension":"device","operator":"equals","expression":"MOBILE"}] (repeat with DESKTOP, TABLET)
    • row_limit=1000, sort_by=clicks
    • Same start_date/end_date across all three calls (default: last 28 days)
  3. Aggregate totals per device (sum clicks, sum impressions, weighted-average CTR and position).
  4. Compare mobile vs desktop:
    • If mobile CTR is meaningfully lower than desktop CTR, flag it.
    • If mobile average position is worse than desktop by more than 2 spots, flag it — possible mobile rendering/usability issue.
  5. Identify the top 10 queries where mobile clicks are near-zero but desktop clicks are high — candidates for a device-specific problem.

Output format

  • Summary table: Device | Clicks | Impressions | CTR | Avg Position | % of total clicks
  • Alerts section: any mobile-vs-desktop gaps found
  • Top 10 "mobile underperforming" queries table

If a mobile gap is found, follow up with indexing-audit on the affected pages — mobile usability problems often surface as fetch or coverage issues in URL Inspection.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 34 lines · 33 tokens per session scan A b5884313d36e

Subscribe to this mod's changes

device-performance-split is a skill published in the GitHub repository amirjahfar1/Google-Search-Console-GSC-MCP (0 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 386 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-01.

Analytics and metricsMarketing and SEO
Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens