skill-056-device-performance-analysis

skill-056-device-performance-analysis is a skill for Claude Code from TrueClicks/claude-plugins. It costs 29 tokens per session (746 once invoked), scanned A, original, MIT.

A Google Ads analysis skill for comparing results across desktop, mobile, tablet, and connected TV devices.

In plain words
What is it for?
It compares impressions, costs, clicks, conversions, and average cost per click, then recommends bid changes or device exclusions.
Why use it?
It shows where clicks and conversions are efficient or wasteful, helping avoid applying the same bid approach to every device.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the google-ads plugin — 145 skills, 4 commands shipped together

Good fit It compares impressions, costs, clicks, conversions, and average cost per click, then recommends bid changes or device exclusions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/trueclicks/claude-plugins/skill-056-device-performance-analysis
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 TrueClicks/claude-plugins --skill skill-056-device-performance-analysis
Clone the repo
git clone --depth 1 https://github.com/TrueClicks/claude-plugins

Made for: Claude Code.

Or install google-ads, the plugin that ships this one along with the rest of its 145 skills, 4 commands.

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 skill-056-device-performance-analysis

README.md
[![agentmods](https://agentmods.dev/badge/skills/trueclicks/claude-plugins/skill-056-device-performance-analysis/github.svg)](https://agentmods.dev/skills/trueclicks/claude-plugins/skill-056-device-performance-analysis)
Your own site
<a href="https://agentmods.dev/skills/trueclicks/claude-plugins/skill-056-device-performance-analysis"><img src="https://agentmods.dev/badge/skills/trueclicks/claude-plugins/skill-056-device-performance-analysis/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 skill-056-device-performance-analysis

Your own site · 80×15
<a href="https://agentmods.dev/skills/trueclicks/claude-plugins/skill-056-device-performance-analysis"><img src="https://agentmods.dev/badge/skills/trueclicks/claude-plugins/skill-056-device-performance-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 746 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 $0.00029 $0.00746
Opus 5.5 $0.00012 $0.00298
Sonnet 5.5 $0.00006 $0.00149
Haiku 4.5 $0.00003 $0.00075

Measured 21d ago against content hash 93e881a0463a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

skill-056-device-performance-analysis 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 21d 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.

plugins/google-ads/skills/skill-056-device-performance-analysis/SKILL.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill 056: Device Performance Analysis

Purpose

Device performance varies significantly by business type. This skill analyzes performance by device (desktop, mobile, tablet), identifies efficiency differences, and recommends bid adjustments for Manual CPC campaigns or exclusions for Smart Bidding.

Data Requirements

Data Source: Custom GAQL Required

The standard export does not include device-segmented performance metrics.

Standard Data:

  • data/account/campaigns/*/bid_adjustments.md - Current device bid modifiers

GAQL Query:

SELECT
  campaign.name,
  campaign.id,
  segments.device,
  metrics.impressions,
  metrics.clicks,
  metrics.cost_micros,
  metrics.conversions,
  metrics.conversions_value,
  metrics.average_cpc
FROM campaign
WHERE segments.date DURING LAST_30_DAYS
  AND metrics.impressions > 0

Run via /google-ads:get-custom with query name device_performance. Device values: DESKTOP, MOBILE, TABLET, CONNECTED_TV.

Analysis Steps

  1. Load device performance data: Use custom GAQL, load current bid adjustments from bid_adjustments.md files.

  2. Calculate device performance metrics: Impression/Click/Cost/Conversion share by device, CPA, CVR, ROAS per device.

  3. Analyze device efficiency: Device Efficiency Index = (Campaign Avg CPA / Device CPA) - 1. Positive = outperforms, Negative = underperforms.

  4. Generate bid adjustment recommendations: Based on efficiency index. Note: For Smart Bidding, only -100% (exclude) is honored.

Thresholds

Condition Severity
Device with zero conversions + >$200 spend Critical
Device efficiency index < -0.40 High
Device efficiency index > +0.40 High (increase opportunity)
Device efficiency index -0.40 to -0.20 Warning
Device efficiency index +0.20 to +0.40 Warning (increase opportunity)
Device efficiency within +/-0.10 Info

Output

Short (default):

## Device Performance Audit

**Account:** [Name] | **Campaigns Analyzed:** [X]

### Account-Level Summary
| Device | Cost | Conv | CPA | vs Avg |
|--------|------|------|-----|--------|
| Desktop | $[X] | [Y] | $[Z] | [%] |
| Mobile | $[X] | [Y] | $[Z] | [%] |
| Tablet | $[X] | [Y] | $[Z] | [%] |

### Recommendations ([Count])
- **[Campaign]**: Mobile CPA [X]% above average → Adjust to -[Y]%
- **[Campaign]**: Desktop outperforming → Increase to +[Y]%

Note: Device bid adjustments (except -100%) are ignored on Smart Bidding campaigns.

Read the full file on GitHub · 87 lines

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. 21d ago First seen · 87 lines · 29 tokens per session scan A 93e881a0463a

Subscribe to this mod's changes

skill-056-device-performance-analysis is a skill published in the GitHub repository TrueClicks/claude-plugins (2 stars, last pushed 22d ago), licensed MIT. It adds 29 tokens to every session and 746 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-08.

Related

Other skills, from other repositories

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

systematic-debugging

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

obra/superpowers · 21 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

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 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